It has three components:

1. Use tiny habits

2. Journal about my habits every day (as little as two words)

3. Make sure it’s fun

1. Use tiny habits

A while back I met the founder of a habit-formation-software company. When I asked what theory his software was based on he pointed me towards a book called Tiny Habits by BJ Fogg. I had heard of the more popular Atomic Habits which was published a year earlier, but according to my recommender (and online reviewers) Tiny Habits offered a more complete and opinionated guide.

I gave it a read, thought it was great, and now follow the book’s prescriptions, making tiny-habit “recipes” that look like the following:

The recipes for the habits I make are all like this: after some trigger (such as another action I’m already regularly taking), I perform some very simple (“tiny”) behavior, then I celebrate. The celebration rewards the tiny behavior and causes it to stick. In the example above, though I truly intended to write in my journal, I keep the habit small - I just need to open it. This way the habit is very easy to start and maintain, and the full intended behavior of writing in my journal usually follows anyways (it’s pretty easy to journal once it’s open in front of you).

I recommend reading the book, which includes many more specific recommendations for various aspects of setting good habits. But even once you’ve learned the book’s frameworks, that’s still not enough to actually set good habits (in my experience). You need to apply the right strategies at the right times throughout your life. For me, that’s where the journal comes in.

2. Journal about my habits every day

Every day I write in my journal about a variety of things, one of which is my routines or habits. I use symbols to delineate the sections of my daily entry, so, when it’s time to write about habits, I write and circle a capital “H”2. Then I free-write about habit strategy, on topics like:

• What new problems do I want to solve?

• What new habits or routines might be helpful?

• How can I make those into three-part recipes?

• How are my ongoing habits going? How could they be better?

• If I stopped/failed at something, why?

The time and effort I spent on this “Habits” portion of my daily journal entry varies widely. If, for example, I moved apartments recently, then I’ll end up writing about what pieces of my old routines I should keep and how that all will work in my new environment. And at the same time I’ll be spending effort outside of my journaling sessions on implementing my new intentions. But if my routines feel stable, in my journal I might just write a quick “all good” and be done with it. So the journal routine stays lightweight and is easy for me to keep up through the ebbs and flows of life. I can even ignore it for a while, and as long as I come back eventually, I trust that I’ll be able to restart the reflective-workshopping process and my habits will end up in a good place. I try to make all of my personal systems forgiving in this way, to account for life’s curveballs.

This system helped me set up my sleep habits and my current morning routine of yoga, meditation, cleaning, and the consumption of various hot beverages. Of course it’s not perfect - it’s only as good as the things I already basically know how to do. But it does give me space to follow through with my intentions, and a good mechanism to course correct when things go awry, which is basically to write about the issues I’m facing each day until I’ve solved them.

3. Make sure it’s fun

If you’re actually interested in trying this I have one last suggestion, which is to make sure it’s fun. If you don’t already enjoy journaling, then step one is to come up with a journaling practice that you enjoy. That probably would involve more than just writing about habits, as it does for me.

Before I started my habit-journaling I was already writing every day about things I was thankful for, things I accomplished, ways I might improve, and the next day’s plans - each in its own section delineated by a unique symbol. Even with those guideposts my writing ranges freely, allowing me each day to make sense of my life and to work towards expressing my ideas and aspirations. With that practice in place, a “Habits” section was an easy addition, and contributed to an overall rewarding experience.

Subscribe now

The system described here is pretty simple, but I couldn’t find a description of anything similar on the internet. I suppose most people are looking for how to set good habits right now, without thinking about the more important question of how to keep good habits for life. For me, habit journaling fits the bill.

Part of a series on my personal systems:

1. Foundations of My Living Personal Systems

2. The Intentional Years ← you are here

Towards the end of high school I began following a set of self-improving personal systems. In the five or six years that followed, I poured perhaps 1,000+ hours and hundreds of written pages into the endeavor, producing an intricate system of interlinked intentions and practices, all formed around a set of core principles. Today’s post continues the story and describes that interlinked system’s workings.

The most fundamental motivating principle of my early personal systems was the following:

“It’s worth knowing what you want to do and what kind of person you want to be.”

Over time, my systems provided me with that kind of knowledge across many aspects of life. I had routines and plans for each day, goals or “modes” for each season, and most importantly, a set of overarching principles to guide my actions.

We can call the whole set of routines, plans, and principles my “intentions.” At my systems’ core was a set of reflection routines which compelled me to describe, maintain, and ultimately to manifest these intentions as best I could.

The core reflection routines

I had two core reflection routines: a nightly journalling session and a weekly review. These were codified in a document called “Constitution” which lived in my digital notes and was the entry point to the rest of my systems.

The nightly journaling sessions started as unstructured free-writes. Each night I wrote about what was going on in my life and about ideas for upgrades I might make to my systems, such as: “I’d like to set up principles for myself that I can reference,” or, “I’d like to write down what I’m grateful for every day.”

Then, during my weekly reviews I read through last week’s journal entries and made updates to my digital notes. In part my goal was to integrate the week’s ideas into my systems as appropriate, but I also allowed myself to make additional changes, informed by the zoomed-out reflective standpoint that the weekly review provided.

These two core routines maintained and built upon themselves. For example, during one weekly review I read in my journal that “I’d like to set up principles for myself that I can reference.” So, I set forth to manifest that. I created a digital note titled “Principles” and updated my Constitution in two places to reflect the following: that during nightly journaling I should prompt myself to write about learnings that are relevant to my principles, and that during weekly review I should modify my principles based on the learnings collected in the prior week.

My goal for any described routine was for it to become a habit, and for that habit to effectively accomplish the routine’s purpose, and for the entire story of the routine/habit and its purpose to be well-described within my system’s Constitution. To achieve that state of systematic integrity I knew I had to regularly “give the system love,” meaning, to apply steady creative energy towards the improvement of each aspect of the system and towards the system’s overall coherence.

I also believed strongly that my systems would work best if I could genuinely commit to following my stated intentions, so I did my best to maintain that commitment. Doing so gave my systems the power to adapt and mature by their own rules.

Factored journaling for nightly reflection

Over time my journaling routine evolved, and pretty soon I was doing the following: each night I’d proceed through a series of prompts represented by the acronym TAIL: “Thankfuls”, “Accomplishments”, “Improvements”, and “Laters”. In order, I wrote about:

1. (T) What I was thankful for - in my relationships, in the world around me, and in myself

2. (A) What I accomplished that day, especially in light of my principles

3. (I) Ways that I might improve myself and/or my systems - this section would directly feed into my Principles document and others

4. (L) What I needed or wanted to do the next day

And finally I’d put a placeholder for recording dreams in the morning.

This system served both my immediate goals of integrity + calmness + gratitude + self-direction, and my long-term goals of systematic self-understanding and improvement.

Principles and their synthesis

Over years of weekly reviews I read every word of my daily journal entries, integrating my scrawled thoughts into a growing body of digital notes. The most important digital notes were those relating to my principles.

At first, my principles were a single document: a list of eight to ten sentences, like this:

Be a confident role model.

Together my principles made up a concise description of the kind of person I wished to be and the kind of life I wished to live, and I intended for my actions and my systems to serve them.

Once my principles document was set up, I built a queue to aid in the principle-synthesis process. During weekly review time I would copy my daily “Improvements” notes into this queue, and in time I would process each item in the queue, considering whether it might call for a modification to my principles or perhaps to some downstream system.

Eventually I realized that my true intentions, and even the subset of my intentions that I wished to write about, far exceeded what could be conveyed in these brief sentences. To give my intentions more space I started a new document titled “Principles: Full Considerations,” which grew to include short essays under each principle. Here’s an example (note: this is a shorter one):

Be a confident role model.
A successful role model has many traits: not only does he act in a positive manner and go about life in a way that benefits everyone, he also must be confident in his ability to teach, and willing to put himself in the public view.

I must start by understanding that people look up to me already and will emulate me if I am willing to make visible my thoughts or actions. I must be confident enough in my unique ways to put them on display, and I must display them confidently.

I must be the first to spring to action when a situation requires it, being guided by what is the right thing to do and not what others think. Don’t use “I don’t know” as a crutch.

As to my role? Following my other principles is enough to define my role as it pertains to being a role model. An additional note is to act respectfully in public settings, especially on the internet, and to show the best sides of myself to every single person I meet. Remember: I have the power to define the energy in any setting.

…

To describe the full circle of principle synthesis: during nightly journaling I wrote about specific ways to improve, sometimes targeting my writings towards a particular principle and sometimes writing in a more free and uncategorized way. Then during weekly review I moved these thoughts into my queue for principles. Later I would integrate these thoughts into some appropriate section in my full-considerations doc, or, in rare cases, mint a new principle. In the end I had a well-adapted set of about ten principles with accompanying essays that integrated thousands of days of reflections.

The challenge of systematically realizing principles

Of course I knew that merely writing down intentions wouldn’t make them a reality, so I was constantly devising new schemes to become the kind of person my principles described. That endeavor was, of course, the most difficult part of the whole system, and I remained unsatisfied with my attempts to the end. But I tried many schemes and I liked some of them.

At first I would literally carry my principles in my pocket. Then at some point I created a new document called “Principles - Actionable Ideas” which described a protocol I could follow at any time in order to ground myself and direct myself towards positive action. Funny enough, the protocol started with a reality check, then branched one way or another depending on whether I was dreaming (I was practicing lucid-dreaming at the time).

But with that protocol there was still something incomplete - how would the full extent of my intentions cash out into reality? So I kept iterating. The next innovation was a “principle of the week.” During weekly review I’d choose whatever felt like the most relevant principle, then throughout the following week would direct my focus towards that principle by various methods. I also set up “seasonal modes,” which, like principles, represented intended ways of being, but were more closely adapted to my present circumstances.

I felt positive about these various attempts at principle implementation, but I remained unsatisfied, and despite my diligence things seemed to slip through the cracks. I loved my routines and thought that they brought me great benefit but I did not believe I had created the perfectly self-regulating system of guidance that I wished to create.

Auxiliary systems

While my main focus was towards the flourishing of my principles, I also regularly attended to a number of other systems and their written counterparts. The rest of my systems were ostensibly downstream of my principles, and I wished to make the links between each system and its motivating principles explicit, but I often struggled to do so (probably for good reason - motivations are complex). Regardless, I had a vibrant array of offshoots. Among them:

• Worksheets from the book Designing Your Life

• A list of close friends, and for each: how they inspire me, what they give me, what we have in common, what I could give them

• A list of accomplishments, organized by season

• A list of times I cried, and other lists of meaningful moments in my life

• A list of good stories that I wish to remember

• (and many more)

Living an intentional life

To summarize: each week I opened my journal, read through the week’s reflections, and updated my digital notes. Sometimes I changed my principles, sometimes I made changes to my reflection systems, and sometimes I worked towards setting daily habits that would help me live a principled life.

For at least four years these systems were going strong, and they gave me a strong sense of trust in myself. I knew that every morning I was waking up with the best intentions, and that whenever I fell short, as all people do, I would learn and improve to the greatest extent of my abilities. I was very happy with my systems and imagined them extending far into the future, and yet, I also felt there was much work still to be done. If only I could figure out the right algorithm to integrate everything together - to optimally guide myself into perfect alignment with my deepest values - then the vision would be fully realized!

Some concluding notes: At this point I’ve covered, from a very high level, the growth period of my living systems. Perhaps you now better understand what it’s about.

There’s tons more I could publish about these systems, much of which is already written (there are benefits of writing about something which was designed to describe itself). Of that, there are many details I’m truly excited to share, such as: what concrete outcomes did these systems create for me? Or, what were the rest of my principles and their full considerations? And, I suppose I might also cover: what happened to these systems? Why is everything in the past tense?

To be honest, to describe the downfall of these systems would be a daunting task. Perhaps I will find a good way to do so, but I expect that to take time. In any case, today’s post was the most important part of the history. Now that I’ve described my prior systems I expect to more easily describe their present evolutions, as indeed a revitalization of sorts is taking place. My next couple of blog posts will probably focus on health, and after that I look forward to returning to this theme.

Subscribe now

Three weeks ago I set this determination:

As long as my fears, pains, and concerns do not exceed what I experienced this week, I will keep pushing through them, choosing to live the life that I most wish were possible. If that succeeds, then eventually my body will catch up with my brain, learning to once more have confidence in itself. And then, finally, there will be no fears and nothing left to push through.

source: I tried David Chapman’s chronic-fatigue-defying six-mile run. It worked.

So far I’ve been doing exactly that, and I’m now on my fourth week of “choosing to live the life that I most wish were possible.” I’m now quite close to my holy grail of running three times a week and climbing/lifting three times a week.

As predicted, along the way there have been some challenges. One day in particular last week I woke up feeling quite tired. My body felt weird and my brain wasn’t working very well. I’d say it was “the normal stuff” but in truth, “the normal stuff” for me varies, and each problematic experience is a little different. I can at least say it was familiar.

It’s natural to see such challenges as setbacks, but recently I’ve been seeing them otherwise: as gifts.

As I understand it, over the last year my body has been conditioned to produce adverse effects (fatigue, inflammation, pain) in response to a wide range of stimuli that occur naturally in a full, engaged life. In order to conquer these adverse effects, I must provide the opposite conditioning - I must live a full, engaged life, with all of its stresses, and then when the adverse effects inevitably show up, I must demonstrate to my body that “actually, everything’s fine.” I can do that by maintaining positivity through challenging periods and by continuing with my intended activities, exercise-related or otherwise.

It’s like there’s a minefield of stimuli, and each time my health fluctuates it’s an opportunity to defuse another mine, to train my body-mind system to skillfully navigate some new area of life. Eventually all the mines will be defused. I expect that to take some time, and in the meantime I will continue to see each challenge as a unique opportunity to move my recovery forward. It’s almost a joyful thing: “Ah, another opportunity. Excellent!”

This mindset can apply to all sorts of challenges, not just my health ones. All challenges are opportunities to demonstrate and learn skillful behavior, expanding the boundaries of what one can do well.

In the end my problematic feelings this week didn’t last long. I felt much better the next day and ran another 10k, my best yet. Now, a few days later, I’ve finished my first week at my gold-standard activity levels. Maybe next week will be easier, or maybe there will be more challenges. As long as I keep doing what I’ve set my mind on, I’ll be happy.

Subscribe now

During my first few months of post-mono fatigue I struggled to fall asleep and stay asleep. It seemed that sleep had just become harder. Regardless of the underlying problem, the solution was straightforward: I just needed to create better sleep routines than my previous ones.

After a particularly un-restful period I decided to apply some effort to the matter and began researching optimal practices, and then began testing them. Eventually my issues resolved and I kept my new sleep habits to this day, though with minor adjustments. I thought I’d share what worked for me:

Consistent wake-up time

Every morning my alarm goes off at the same time (call this “t”). Consistent alarms from day to day help my body fall into a natural rhythm, so even if I’m up late I prioritize alarm consistency over sleep duration.

Wind down routine

I’ve learned that I sleep best when my lights are off at t - (8h 40min), so I work backwards from there. On an ideal day:

1. t - (10h) (or earlier): Wind down begins:

   1. Plug in / put away phone (not in bedroom) - the farther and more out-of-sight the phone, the better. Once it’s plugged in, I don’t use it. I also use my phone’s built in sleep controls to suppress notifications.

   2. Turn off lights, unplug bright computer keyboard - darkness helps with circadian rhythm.

   3. Turn on red bed-side light - red light is circadian-rhythm friendly and routine red light becomes a pleasant backdrop to pre-sleep rituals, plus a consistent signal to the body of impending sleep.

   4. Lightly organize apartment - putting things away helps “put away” the thoughts associated with them. It’s also just a nice wind-down-friendly task.

2. t - (9h 30min): Get in bed, journal (20 min) - I follow a structured journaling routine. Like cleaning the apartment, journaling also helps me “put away” thoughts from the day. I write about things I’m thankful for, things I accomplished, how I might improve my actions and routines, and what needs to get done the next day. When I’m finished, my thoughts are quieter.

3. t - (9h 10min): Read a book (fiction preferred) (30 min)

4. t - (8h 40min): Turn on alarm, put in ear plugs and put on eye mask, turn off red light, and close my eyes.
   …

5. t: Alarm

Sometime I extend or shrink the wind-down window to accommodate for the natural flows of my schedule, but I try not to shrink it too much.

Keeping the bed(room) for sleeping only

A lot of my routines above relate to ensuring that my sleeping spaces are used only for sleeping - that’s why my phone stays outside during the night, and my bedside table only has exactly the items needed for wind-down:

1. lamp with red bulb

2. journal

3. book

4. alarm clock (prevents reliance on phone)

5. ear plugs and eye mask

My setup isn’t fully ideal because my current bedroom contains my at-home office. But at least my computer and monitor don’t face the bed (they’re sorta around a corner), so there’s some mental separation.

I also try to avoid lying on my bed unless as part of wind-down/sleep. I’ve made exceptions in the past when I was extra tired, but in hindsight it would have been better to use the couch so that my body knows that bed = sleep.

Melatonin (rarely)

I only use Melatonin on rare occasions when my circadian rhythm seems behind schedule, using the clinically-studied dose of 0.3g (lower than most supplements) and timing it about an hour before I intend to sleep. Once my sleep seems roughly normal (generally after one night) I stop taking it, and otherwise don’t take supplements for sleep.

I tried magnesium glycinate, but didn’t personally notice a difference from taking it.

Pleasantness-maxxing

My routines form a sort of pleasant ceremony. Once my red light is on, it’s a bit like I’m in another world: a world where I only do pleasant, relaxing activities.

Nowadays this is a joyful part of the day that I can look forward to - when I was struggling with poor sleep and my other fatigue issues, this period felt more like a necessary respite. In any case, pleasantness is both good for sleep and good for its own sake.

Electronics off early

…just bears repeating - my phone is nowhere near me during the wind-down window. If there are internet things that I wish to get done, I write about them in my journal and save them for the next day.

Creating and maintaining routines (to be continued…)

My particular routines might not work for others, and it takes time to onboard any kind of routine, especially complicated multi-part ones (like the wind-down sequence described above). So, my real recommendation for someone looking to improve their sleep would be to develop a good routine-generating process - something I’ve put a lot of effort into myself.

I’ll write about routine-generation soon in a post titled (tentatively) “Journal as core routine engine.”

Last week I wrote (here) about my recent success in pushing through a post-viral fatigue spell, running six miles and coming out more energetic on the other end. I realized I have more to share - a long history of experiences and attempted interventions which together could form a useful fatigue-recovery case study. Today I continue the story by describing my experiences with hypnotherapy, an intervention which changed how I understand my illness and plausibly helped me recover faster. I’ll describe both the session itself (with illustrations) and my immediate and longer-term outcomes.

…

I learned of hypnotherapy through a close friend who used it to treat his chronic shoulder pain. He had a positive experience and eventually offered to buy me a session with the same practitioner. That was a year ago, three months after the start of my illness. I appreciated the thoughtful gift but wasn’t eager to begin: I trusted that my fears, pains, and other body signals were all well calibrated to prevent me from taking harmful actions in my fragile state.

Ten months later my perspective had shifted. As described in last week’s post, a series of positive experiences with exercise caused me to reevaluate the wisdom of my symptoms. By January 2026 I felt I was ready, and I reached out.

At the time I understood my condition as follows (excerpts from the hypnosis intake form):

What was I experiencing?

Presenting issues:

Since having mono a year ago, I’ve had some fatigue issues. Things have actually improved in the last few weeks and I have not felt many symptoms even though I’ve been more active (e.g. have been back to the climbing gym about twice a week). So I’m currently optimistic, but also things tend to change randomly, so I’m not fully optimistic.

…

If you are experiencing discomfort, on a scale of 0 - 10, which number represents it at its most severe?

5

And which number represents it at its best?

0? (Or maybe 1. If I think about it, there’s usually something there. But I think there are times when I don’t think about it and just feel fine.)

Describe the nature of the discomfort using any descriptors or metaphors that feel most appropriate:

I’ll describe the more mild symptoms as that’s what I’m feeling now, though it does get worse. But it starts in my shoulders and neck, which will feel sore and kind of sick. And then maybe I’ll feel it in my arms too. There’s a sort of heaviness sometimes, like, just taking action feels a bit difficult, like there’s a bit of a haze separating me from the world or from the actions I might take. Things just don’t feel very fluid. I do associate a particular “inflammation-y” feeling as well that’s very difficult to describe, but where there’s a kind of tenderness in my shoulders, or my chest, or my gums, or my arms… as I focus on these places there’s this field of tenderness. Overall things just feel delicate, like I’m made of glass (slightly).

And what was I hoping to change?

I want to be not afraid of physical exercise, and to feel good after doing it. And to be not afraid of work, and not afraid of going to New York. Just generally not afraid of doing hard/exciting things. I want to feel like I can push myself to the limit and feel rewarded for it, and like I am full of energy.

I also listed some moments that made me happy to remember, which would become relevant in the upcoming session:

There is one spot in Castle Rock that I’ve been to multiple times, napping on the grass on an overlook…

…

Getting acquainted with my red field

I logged into Zoom for my first session. After thoroughly probing many core facets of my life, the hypnotist asked me to come up with an image to represent my symptoms. “It’s like my body is made of glass,” I said. He asked again:

“Can you describe it as something separate from your body?”

I thought. I said “it’s like a red field that permeates my body and grows wherever my attention touches it, concentrating and spreading inward. Whichever parts it occupies are filled with a diffuse pain, and I am compelled to hold them still, to move them with great gentleness and care.”

He explained that this field could be thought of as a piece of software that runs on my nervous systems and/or subconscious mind. Our goal was to update this software.

To do so he would guide me into a relaxed dreamlike state, and in that state I would perform a sequence of visualizations and mantras. He assured me that my participation would be voluntary throughout. He taught me a “vagus-breathing” exercise, suggested as an intervention that I might use during times of anxiety, then he guided me through a body scan, and then, finally, deep into the hypnotic state.

Stepping into a new world and upgrading my software

Hypnosis was indeed a bit like dreaming, but less intense. I was mildly aware of my true surroundings and occasionally veered off into half-formed thoughts, but each time I eventually came back to the visualizations. Over time I experienced a pronounced shift in my mental background: I felt more calm, free, and fearless, as if I were “trying out” a radically different way of being.

My mental journey began in Castle Rock, lying in the grass with a hat covering my face, relaxing in the sunshine after a long hike and a big lunch. Once I established that positive backdrop I was guided into a dialogue with my red field. I asked the field its purpose, learned that it was well-intentioned but perhaps miscalibrated to my present circumstances, and thanked it for its service. Then, in a lengthy ceremony, I disposed of it completely:

After that I designed a new piece of “software” to replace the field. I imagined a thin blue suit covering my entire body, lined with a network of tiny tubes. The suit would effortlessly regulate my body’s resources, and with it donned, I was assured that whatever rest my body needed would take place naturally and without conscious intervention.

I imagined walking around with my new suit, first in Castle Rock, and later in a climbing gym. With my hypnotist’s guidance I accentuated the positive experiences of this new way of being: the freedom, the joy, and the boundless energy. In this new world my body was no longer problematic and my surroundings were once more full of possibilities. I stewed in these positive experiences then was guided out back into the real, unimagined world.

Immediate benefits in my daily life

After the session my hypnotist encouraged me to take practices into my daily life, including routines (like self-hypnosis) and ad hoc interventions (like the vagus-breathing exercise). And, I was to take my blue suit with me. Whenever I felt my field of pain / fear / confusion / tiredness, I imagined my blue suit working away, optimally managing and restoring those problematic areas, and I felt comforted.

For example, I went on my first trail run in many months soon after our session. I remember at one point losing energy and slowing down. Instinctually, the fear flashed:

You have exhausted yourself. Feel your body - are the symptoms there? You must be very careful.

But I remembered my suit, and thought:

My body will take care of itself. It has already slowed itself down, naturally. I need not worry.

The ground truth was the same - I was on a run, I did a lot of walking, I was tired. But when I remembered the suit, my fears relaxed.

On the reasonableness of hypnosis

I think that both the intentions behind the hypnosis, and the way it was carried out, were appropriate for my stage of recovery.

For a year I was plagued by a fickle illness, never knowing when the next symptom would strike. It seemed that using my muscles would cause symptoms to worsen, and those symptoms largely struck the very same muscles. Of course that caused me to develop heightened awareness of my body’s warning signals, and with such heightened awareness it’s no surprise that the “red field” got ingrained.

Although the field seemed to communicate that my body still had fundamental issues, I couldn’t exactly take it’s existence as evidence of fundamental issues - it’s possible that it was just hanging around. And indeed, after experiments with gradually reintroducing exercise, I started to believe that my underlying health dynamics were more favorable than the field was letting on, and that perhaps the field was causing me to be overcautious.

Or, put more simply: I spent a year in fear, deeply hypnotizing my red field into existence. After such conditioning, it made sense to spend a few hours un-hypnotizing myself towards a more normal relationship to my body.

And indeed the blue suit I imagined was quite realistic: we all contain a fantastically optimized network of (blue) veins that carry unneeded matter away from our organs, in concert with energy-providing arteries. This circulatory system, and the rest of our body systems, perform well without conscious intervention. A miracle!

My outcomes and the recovery flywheel

In the months following my sessions1 I experienced a recovery flywheel: as I reduced my fears and perceived symptoms I started maintaining gradually more intense exercise routines, and as I succeeded in these routines my fears further receded.

I think this “recovery flywheel” concept is critical to understanding my illness and how I got better. Such flywheels get stuck when perceived negative reactions to exercise outweigh perceived benefits. My own flywheel seems to have been stuck since I originally fell ill, and, while it’s hard to say for sure, it’s possible that my hypnosis sessions provided just enough grease (via lessening of fears) to get the flywheel back up and running.

To be clear, the effects of those sessions barely hold a candle to the fear-dismantling that occurred in the wake of my recent experiments with pushing through fatigue via exercising hard. There’s nothing like physically proving your perceived limitations to be spectacularly wrong. But still, when I look at the past months, it seems reasonable to suggest that my hypnotherapy contributed to a buildup of self-trust which allowed for my later more impactful experiments to take place.

At the very least I can say: my sessions were pleasant and my practitioner was a thoughtful guide. The practices I learned brought me comfort, and though I can’t make strong claims about causation, I can say that their introduction to my life coincided with an inflection point in my physical activity and health. Overall hypnosis seems to have been an appropriate and helpful tool for my particular stage of post-viral-fatigue recovery.

Subscribe now

In December of 2024 I had mono, a disease which upended my life and caused me fatigue issues that plague me to this day.

I recently tried a new recovery tactic with astonishing results.

The crash

On Sunday last week I woke up too tired to complete my 10 minutes of daily yoga: a sure sign that I was entering a low-energy period. I might have gone on a run that day, but knew I needed to rest.

The next day (Monday) I dressed up in my running clothes and went to a cafe, but as I sat there my energy fell lower and lower. I felt like I wanted to throw up. I did not run. I returned to my car and lay my head against the passenger seat. After returning home, I did the same. It took a lot of effort to get upstairs, and I cancelled my plans to cook myself dinner. As I proceeded through my wind-down routine, I paused to sit or lie down between each task.

On Tuesday I completed my yoga. My body felt slow but my head felt clear. I had one meeting, then started to write. I began to feel more and more tired. I moved to my bed. I switched to a computer game. Then I turned that off and closed my eyes, feeling I could do nothing else, completely spent. I was reminded of times during my original illness 15 months ago, and times since then, when I’ve been similarly debilitated. I prepared for the possibility of an unproductive day, and of multiple days of continued exhaustion.

I got up and went to the bathroom, and while there I recalled a blog post from David Chapman: Fake fatigue in long covid. I reread the post, attending closely to the story of his fatigue-defying act. Chapman’s words:

I pried myself out of the beanbag. I was dizzy and lightheaded, and my wobbly legs could barely hold me up. Slowly and carefully I got to the garage and drove to the park.

I ran six miles. Then I came home and wrote this post.

Fuck you, long covid, you are a fucking liar.

As I sat there reading his story, I began weighing the risks. I thought this might actually work for me. I decided to do it.

…

I pried myself off of the toilet (sorry). I was dizzy and lightheaded, and my wobbly legs could barely hold me up. Slowly and carefully I got dressed and walked outside.

I ran six miles. Then I spent a week being physically active and productive, and am now writing this post. So I too will say (excuse the profanity):

Fuck you, post-viral fatigue, you are a fucking liar.

I share this post in case it might help anyone else with similar issues. I include the history of my challenges with physical activity, the run itself, the week that followed, and my updated recovery outlook.

Caveats / you should read Chapman’s post

Chapman is a very good writer and he covers the necessary caveats. Most importantly: don’t take medical advice from internet randos. I agree, and will quote him here:

I’ve figured out a way to deal with long covid fatigue that has worked for me. It might work for you, if you have that. I have no idea. It may also cause other trouble, so you’d need to be careful.

Same situation here. This is a story about what worked for me.

I can at least attest that my story is accurate. I kept a detailed journal of my feelings and activities over the past week, updated multiple times a day. I’ve also spent months collecting daily self-reported health logs, and years writing and re-processing daily journal entries. All of those personal writings helped produce today’s story, which really began 15 months ago.

The history of my challenges with physical activity

I tested positive for mono and strep in December 2024, and then the flu one month later. I continued experiencing fatigue throughout 2025, and wrote about these experiences in my 2025 year’s end blog post.

In July 2025 I began tracking three self-reported health metrics on scales of 1 to 5:

1. how mentally sharp I felt

2. how much energy I seemed to have

3. how much soreness/inflammation I felt in my neck and body

These three metrics represented the signature symptoms of my condition. Summing them together, a 15/15 represented a normal-feeling day, and anything less represented various levels of ailment. Here’s what 7 months of data looked like:

As you can see, symptom-free days were few and far between. I stopped tracking in February 2026 in part to remove the burden of the task and in part to prevent myself from drawing unneeded attention towards the illnesses.

The struggle to reintroduce running and climbing

For many years I’ve enjoyed rock climbing, weightlifting, and running. I’ve told myself that if I could return to my pre-fatigue routine of climbing/lifting three times a week and running three times a week, I would then consider myself fully recovered.

During 2025 I intermittently attempted these activities, but often experienced delayed-onset fatigue, roughly one day after. I interpreted that to be post-exertional malaise (PEM). My read of online forums and publications from advocacy groups told me that PEM could have negative health effects, so I felt discouraged from continuing those activities. I generally opted for yoga and long walks instead.

The negative aftereffects of exertion were strongest for climbing, perhaps because my ongoing symptoms of pain/soreness/inflammation were clustered in the same upper body muscles that climbing engages. So, whereas I sometimes sustained an intermittent running practice, my climbing practice never got off the ground, though I tried a handful of times. Even running was difficult to maintain. My frequent symptoms made it harder to run and made me less certain that running was a good idea.

In October I moved to Seattle. During my first two months (November and December) I was often sick. I felt that my health may have regressed slightly. While I would sometimes go for walks or hikes, I did not feel comfortable making progress towards running, climbing or lifting.

Then things started to get better.

Improvements in the last two months

With the encouragement of my friends I returned to the climbing gym in late December. The day after my first climb my muscles felt sore and inflamed, as if I had a viral infection. After about three days those symptoms mostly resolved. Despite the adverse response, I felt that I had ultimately tolerated the exercise, so I continued going to the gym.

For a few weeks I climbed once or twice a week, doing short sessions (~30-40 minutes). Then I started running again. Slowly I ramped up to a point where I was running nearly twice a week and climbing nearly twice a week. The runs were about 2.5 miles with a fair amount of walking interspersed.

Throughout that period I experienced my normal fluctuations of symptoms, and often did not feel good, but crucially believed that I was not hurting myself, so I kept going. That change in belief was a tipping point in my recovery.

But despite my sense of progress, I was not encouraged by any of the feelings I experienced in my body, during or after activity. I was operating with great caution, and my symptoms often compelled me to reduce my activity and take unplanned rest days. Progress felt like a constant struggle, and it’s that tenuous headspace that formed the backdrop for last week’s crash and the six-mile run.

Why did I take the risk?

What was going through my head when I decided to go on that run?

It’s hard to describe. My felt experience of making health-related decisions is one of deep, complex uncertainty. As if I am dealing with a tangled ball of thoughts and feelings that spans multiple miles, so large that I cannot bring it into view and cannot think straight about it. The main component of the ball is fear, which suffuses everything.

The fear makes sense. I kept trying to expand my exercise envelope, and despite some success I continued to feel bad and to randomly crash. For each negative experience, I would worry I’d overdone it and would think about the potential causes, exercise-related or otherwise, and the fear would expand into more and more areas.

At the same time, a number of positive experiences gave me optimism. From as early as February 2025 I had moments where my energy seemed to suddenly recover: first at a bachelor-party weekend, then on a family vacation, and later during a series of backpacking trips. In hindsight these were all fun, multi-day activities in new environments.

The backpacking trips in particular were confounding. I would work up the courage to go out, set backup plans in case my health failed, and then proceed to feel great the entire time. Part of me still worried: I would feel exhausted after the trips, and backpacking is a pleasant activity for me, so perhaps I was still operating under limitation and offsetting the consequences? But it really didn’t seem that way. The memory of these trips became a beacon of hope for me.

Between the backpacking trips, my recent successes with re-introducing climbing and running, and my exposure to cognitive-retraining success stories1, I figured that I might be able to tolerate more than it seemed, and that I could engage in this experiment without serious risk to my health. The veil of fear would have to yield this time.

Also, I won’t lie: I was thinking it would make for a good blog post.

So I went on the run.

Quick note on terminology: long covid vs. post-viral fatigue

Before we move on I need to clear something up: I generally say that I’ve experienced “post-viral fatigue,” since that most directly describes my situation. If pressed I’ll say it was caused by mono, which is a frequent instigator of such issues. However, I’ve had covid, and probably long covid before (details at footnote2), and there’s evidence that Epstein-Barr virus reactivation (which causes mono) may be a contributor to many long-covid cases (see Dan Elton’s notes on this). Furthermore, post-viral fatigue from mono and post-viral fatigue from COVID are not clinically distinguishable - they share symptoms, mechanisms, and even treatment recommendations. As such, I didn’t mind calling it “long covid” during my run - it’s all post-viral fatigue to me.

The Run

I copied Chapman, heading out the door while forcefully saying “fuck you long covid,” trying my best to energetically cast off my limitations.

At the beginning running felt… unnatural. My vision was blurry and my thoughts were scattered, and I felt sluggish. But I could run. Over time my vision became normal and I felt normal, and then began to feel good. My congestion cleared up and I sustained a jog for most of the six miles. By the end it felt like running under normal healthy conditions.

That afternoon and evening I was productive and had plenty of energy. My lungs felt tired and I occasionally brought up phlegm, but otherwise my body felt great: I had a pleasant tingly feeling all over. The run had completely turned things around.

I was optimistic, but I wanted to wait before publishing my results. I’m glad I did, because the next week was even better.

I kept pushing myself and it kept working.

In keeping with my best-case exercise routine for the current period (run → climb → rest day → repeat), I proceeded to climb the next day (Wednesday). It was by far my best climbing day since 2024, and I climbed my first “blue” (an arbitrary difficulty grade at the local gym).

Two days later (Friday), I was out running again, this time in the snow:

About three miles. It went well. Just like on Monday (the first significant day of my crash) I was two days out from a pair of running/climbing days. Just like Monday, I worked on my blog (the same post on both days - an upcoming one). I did all of that to make Friday a controlled experiment. Happily, writing went well, as did the run.

The next day (Saturday) I was at the climbing gym again. I climbed my first “pink”:

Also, for the first time in months I lifted some weights - just a small amount to get started. Two days later (Monday) I ran far again.

I made poor choices regarding the timing of coffee consumption and ended up walking a fair amount, but I made it home ok and felt fine the next day. That brings us to today (Tuesday), during which I wrote the majority of this post and had another great climbing session.

Feeling motivated? I hope so! Allow me to fill in some gaps…

I felt slightly bad and concerned for my health every single day (and that might be a good thing).

After my run on Tuesday, I worried about my lungs. I told myself it would be fine, but was still scared. On Wednesday I wrote “My body is sore, a situation which threatens to draw my concern, but I remember that soreness is normal.” On Thursday I woke with a sore throat, but then began feeling better during my yoga.

Friday morning:

feel pretty sore, under the shoulder blades and such. The kind of thing that might normally be a warning signal. “Guess I’m sore after climbing” I think, and move on.

Saturday on the way back from the gym:

my body is throwing warning signs. As if I’m about to be sick. I Ignore them, have dinner, take a nice long bath. Afterwards, things seem fine. I am tired, but not unwell.

Sunday:

I woke up thinking I might be sick. Phlegmy, not feeling great. Still, got up, did my routine, did my yoga. Spent half the day cleaning my apartment, fasted, and eventually felt fine.

[…]

there’s still that feeling of heaviness, but only barely.

Monday:

again, quite zonked upon waking. This time, yoga was a bit harder. Once again, things progressed fine throughout the day.

…

Every single day was hard. And that might be a good thing. If I’d felt great the whole week I would have learned that I can have good weeks. Instead I learned that a lot of my negative feelings don’t cash out to physical reality, and that I can have a good week despite them.

Some closing thoughts:

This is all very exciting.

This seems a bit out of place in a sober analysis of the situation, but, yeah, I am really looking forward to slaying this demon, and this past week was like a big harpoon right in its rear end. It feels very good to go to the gym and pull hard. And it feels very good to experience hunger again (like, literal hunger, from exercising). If I can continue at my current rate of activity I will be over the moon.

I am glad that my friends invited me out.

My first two backpacking trips of 2025, my snow-camping trip in January, and my recent reintroduction to climbing were all initiated by friends. When I accepted each invitation I felt I was taking a risk, but in each case I was excited to join because of the people involved. Without these invitations, and the resulting disconfirming evidence I received, I would not have had the courage to push through this week. To everyone involved - thank you very, very much.

The plan is to keep at it.

As long as my symptoms do not exceed what I experienced this week I will proceed to treat them with “aggressive contempt,” as Chapman put it. I will continue the current exercise routine, and if that keeps working I will expand it until I’ve reached my ideal pre-fatigue cadence, with respect to the gradual approach required to recondition muscles (especially in weightlifting).

Of course, I am reporting on recent events and I have no idea how my health will progress. If I look within, I am still gripped by terrors: what if this week was an anomaly? What if I’m just building up for a bigger crash, one that I can’t fake my way out of? What if I have to turn around and say I was wrong?

The fears are to be expected. That’s how these illnesses work. But I do not intend to pay them heed. As long as my fears, pains, and concerns do not exceed what I experienced this week, I will keep pushing through them, choosing to live the life that I most wish were possible. If that succeeds, then eventually my body will catch up with my brain, learning to once more have confidence in itself. And then, finally, there will be no fears and nothing left to push through.

References and resources

1. The original “fuck you long covid” run:

Meaningness

Fake fatigue in long covid

This morning I was half-sitting, half-lying on the tiger-striped beanbag, weak and exhausted, mentally and physically…

Read more

2 years ago · 60 likes · 32 comments · David Chapman

2. Dan Elton’s writings on surmountable causes of fatigue:

More is Different

The "false alarm" theory of Long Covid fatigue

Note (added 9/29/24) - I do not think this explains most Long COVID symptomology. Even when I wrote this, I was thinking this theory was maybe only relevant in ~50% of cases. The main drivers are probably persistent virus, Epstein-Barr reactivation, immune dysregulation, and mitochondrial damage. Another point I would like to stress here at the start is…

Read more

3 years ago · 19 likes · 2 comments · Dan Elton

More is Different

Psychosomatic contributors to Long Covid suffering

“Some people are willing to ‘feel sorry for the sufferers’ if we find a traditional pathogenic mechanism … and that, to me, seems a fundamentally flawed point.” - Alan Carson…

Read more

3 years ago · 11 likes · 6 comments · Dan Elton

3. Mark Lovett Wells’ extensive long-covid wiki, presenting a path to recovery that does not involve pushing through discomfort: My Long COVID Treatment Strategy.

Bridge, Rudolph Ruzicka, c. 1915-1926

I’m not publishing my best essay of 2026

Yesterday, I performed an exciting “health experiment.” I’m planning to give you the full report next week.

In preparation for that event, I resumed work on the essay about mono which I foretold in my 2025 end-of-year update:

The three-month period depicted above was very challenging, and it’s daunting to try and do it justice in writing. But I have planned a post about this, “The Phenomenology of Mononucleosis” […]

At risk of tantalizing my audience I’ll say that the essay I produced is one of my finest pieces of writing: a deeply vulnerable story, charting a wild and disturbing psychological journey, punctuated with moments of the sublime, interwoven with images and excerpts from my journal…

But as I brought that period of my life into definition, I felt a growing sense of unease. The situation I was depicting, while fascinating, was really not a good one. And I figured that publishing it would give it more life than it deserved.

As I mulled over my decision, I began to play with a phrase, at first in my head and later out loud:

“We can probably move on from that”

Each time I said this, I felt more certain of its truth. I felt liberated. I don’t need to publish this, I don’t need to think about it, I can relegate it to the depths of my drafts folder and can do so with no ceremony. So that’s what I did.

I am someone who tends to finish things that I start. This has obvious benefits, but a drawback is that I can lose connection with my original motivations. In this case, I was motivated to write about health. Why? Because I’d like to help others and myself navigate those challenges and move in a positive direction. On reflection, the post I was writing didn’t serve that purpose. Whereas next week’s post almost certainly will.

The words we say are like spells cast into the world. “Where your focus goes, your energy flows,” says my Qi Gong teacher. And this is especially true of the words we put up in public places (like blogs): each becomes a node in a powerful network that conspires to shape our lives. As such, internet-writing experts like will remind us that it’s best to “focus on what you want to see more of” and to only “joke about outcomes you want.”

This doesn’t mean I intend to ignore life’s challenges. Instead, I hope to build narratives that transform my challenges into vehicles for optimism and growth.1 So how might I build those narratives for my own health story?

Crafting minimal bridges over the narrative landscape

As I see it, setting up beneficial narratives around challenging experiences is a creative exercise. You’re dealing with a messy landscape, and different people have seen you at different parts of it. You need a story that can hold up to a variety of inquiries and redirect them towards positive directions. So if the landscape has bogs and chasms, your goal is to build bridges.

What surprised me yesterday, but is obvious in retrospect, is how small the bridges can be. It doesn’t take much to get to a point where you can say “that’s enough explanation. We can just move on.”

When I consider my health story, it’s clear that my end of year post was a perfectly sufficient bridge. It touched on my challenges, but only in enough detail to clear up any confusion before reorienting towards the present. The particulars of my winter of sickness, in the end, despite being interesting, and complicated… are not relevant. What’s relevant are all the great things I can do with my life right now. And so there I leave it.

Remarkably, last night after I decided to shelf the essay, I came to the following quote in The Lord of The Rings (The Return of The King), which I’m reading for the first time (mild spoiler alert):

“They stripped me of everything; and then two great brutes came and questioned me, questioned me until I thought I should go mad, standing over me, gloating, fingering their knives. I’ll never forget their claws and eyes.”

“You won’t, if you talk about them, Mr. Frodo,” said Sam. “And if we don’t want to see them again, the sooner we get going the better. Can you walk?”

“Yes, I can walk,” said Frodo, getting up slowly.

In a fraction of the words I’ve written here, Sam Gamgee performs a beautiful redirect of Frodo’s attention. Something bad has happened. It’s over now. “Can you walk?” …And that’s that. The curtness is part of the virtue. Sometimes very little needs to be said in order to let something go.

My intent with the blog and otherwise is to focus on my immediate projects: on the work I can do now and the person I can be now, and to leave the past unexamined but for its present value.

As for whether I can walk, that question will be answered next week :)

Subscribe now

In optimism,

Daniel

Today we return to a core story of my life: that of my living personal systems. I’ve previously touched on them, but only in vague terms. This post will provide a more complete story, starting with my initial inspiration and ending with the launch of my first set of self-reflective routines.

I’m excited to share about these systems in part because they form the missing link between many disparate topics that I’ve written about, such as human-programming tools, artificial general intelligence, routines, and personal growth (links are to past posts).

Consider this part one of The History of My Living Systems. The full story would trace a thrilling rise and tragic fall, as the systems that survive today are a shadow of their former glory. And yet, I wouldn’t be writing this if I didn’t believe in the continued value of the endeavor, at least in my own life.

In any case, our story begins with a moment of inspiration.

A moment of inspiration

To set the scene, towards the end of high-school things were going great for me - I was enjoying school, getting lots of physical activity, and spending time with friends and family. But also I was feeling a growing sense of unease. A few things felt true: firstly, that the world was full of great opportunities. Secondly, that I had been “going with the flow” - working diligently at the tasks put in front of me (mainly school), but thinking little about what was actually worth doing with my life.

These feelings had been bothering me for a while when inspiration struck from an unlikely place: the psychological-thriller film Memento. In Memento, main character Leonard Shelby can’t form new memories, and yet is determined to accomplish a goal that he developed after his memory left him. His solution is to create a series of prompts, many of which are tattooed onto his body, that would remind him of his mission and the reasons behind it.

I had no intention of getting such tattoos, nor of pursuing such a vengeful mission, and yet I was inspired. Here’s someone that knows what he’s doing and why he’s doing it, I thought. And crucial to my inspiration was Shelby’s approach: he created systems that directed his attention and efforts towards his most important goals. To be clear, this is not a “Top 10 Life Optimization Tips I Learned from Christopher Nolan’s Memento” post - I barely even remember the plot, and am certain that my own systems diverged strongly from what’s depicted in terms of both vibe and approach - but, I cannot deny the inspiration!

I imagined having my own set of core directives, not tattooed onto my chest, but instead living in some digital or physical notebook that I could reference regularly. However, unlike Shelby, I didn’t have some totalizing quest handed down to me by the screenwriting gods, so I would need to figure out what I wished to do before attempting to do it. I began to imagine how I might go about discovering my values.

Planting the autopoietic seed

I might have sat down and defined some values for myself. But I figured that arriving at my values would be a longer process. And so, I might have sat down and defined the process for arriving at my values. But I figured that arriving at the process for arriving at my values would be a longer process. And so, I might have sat down and defined the process for arriving at the process for arriving at my values, but I figured that arriving at the process for arriving at the process for arriving at my values would be a longer process (and so on…)

It was clear to me that I was seeking a generic system that could grow in complexity over time while adapting itself continuously to my needs. I was still inspired to create finer-grained directives / principles for myself, but I didn’t want to start there. I wanted to build the adaptive foundation on which those directives, and any other system that might serve me, would stand.

Long after I started, I learned the term autopoietic1, meaning “capable of producing and maintaining itself by creating its own parts.” The term has been used to describe the self-maintaining chemistry of living cells, and it captures the “living” qualities of the system I wished to produce.2

A foundation of reflection

The simplest foundation I could imagine was to create daily and weekly routines that compelled me to reflect, and through that reflection to modify my routines to better serve my aims. I imagined these routines forming the seed that would blossom into more expansive systems for self-guidance.

I defined the following initial program for myself:

Complete the following activities without fail.

Daily: Write in your journal about how your day went and any thoughts you have about how to live your life better.

Weekly: Review last week’s journal entries, then update this reflection program in order to improve this program’s ability to achieve its goal: to help you lead a good life.

…And then I got to it - I purchased a journal and committed myself to daily nocturnal reflections, and from that point on the system took over.

This act of creation was quite a rush for me. I felt that I was starting a new life, both for the system and for myself. From now on, everything I do has a purpose, I felt. Now that I am committed to this program, all of my actions are contributive towards leading a good life. I felt I was embarking on the project of a lifetime - a project to systematically transform into the kind of person I wanted to be. All of my creative energy was happily directed towards this new pursuit.

…

And then the system began to grow. In the next post in the series I’ll continue the story, describing the specific results that emerged from these earlier foundations.

Subscribe now

A note to my subscribers ✍️

This week’s post is squarely in the “musings” category, focusing on time, presence, and communal practices - a sharp contrast to last week’s technical deep dive. It goes without saying, but I encourage my readers to pick and choose which posts you read and engage with. Not every post will be for everyone, but hopefully, each will be for someone. For my part, I’ll try to write clear titles and subtitles so that you know what you’re getting into.

If you do read and enjoy a post, I’m always happy to receive a “like” and/or a comment with your thoughts. Or you can reach me directly by replying to these emails. And an untracked KPI of this blog is conversations started, so please, converse away!

Without further ado, this week’s post…

An offer - Active Reading mode: if you’d like, follow the instruction on each of the green screenshots in this post as you reach them, to experience your own moments of presence.

Stretchly: a welcome interruption

In Deep Knowledge, and Three Ways to Get There, I mentioned my housemate’s fascinating computational biology “TED talk.” What I didn’t mention: every ten minutes, his slides would be interrupted by a full-screen instruction…

After a few instances, I caught a notification in the top right corner of his screen:

I was intrigued. As an unmitigated self-instructor, I had to investigate, and found out that Stretchly is free and open source! So I gave it a spin, and proceeded to have an unexpectedly great time.

The way it works: whenever your computer is open, every ten minutes your screen is blocked by a timer and an instruction. The first two times are “short breaks” (20 seconds); every third is a “long break” (5 minutes) (like the pomodoro technique if you’re familiar).

Here’s what I saw during a recent long break:

I was surprised at how much I enjoyed receiving these cues! Especially the short breaks - sometimes it’s a moment of mindfulness, sometimes a stretch… always an opportunity to step out of my projects and just enjoy life and my body and the world around me.

So, I recommend Stretchly. And perhaps this post could end there. But, I decided to go abstract and write about how my experience with Stretchly ties into time-management, psychology, and the sabbath.

On undifferentiated time

I came across Rowan Williams’ concept of “undifferentiated time” in an interview of Oliver Burkeman on Sam Harris’s Waking Up app1. Undifferentiated time is the tendency in secular society for all the time in one’s life to blend together into a uniform streak. Williams, a former Archbishop of Canterbury, presents this in contrast to the daily, weekly, and yearly schedules of the religious adherent.

Burkeman offered his own areligious characterization of the well-differentiated schedule in Four Thousand Weeks: Time Management for Mortals. I haven’t read the book, but resonated with this quote from it (ht Elizabeth Oldfield):

“freedom . . . is to be found not in achieving greater sovereignty over your own schedule but in allowing yourself to be constrained by the rhythms of community—participating in forms of social life where you don’t get to decide exactly what you do or when you do it.”

This freedom that Burkeman describes is far from my current life. While I engage in many different activities, many of which are social, I still make my own schedule and ultimately lack the kind of community-drive constraints espoused above. I’m especially aware of this fact because I grew up in a culture which imposes a strict, differentiated schedule: that of Judaism, or specifically modern orthodoxy. And the most notable division of time in Judaism is the sabbath.

Shabbat vs. project mind

The Shabbat experience is profoundly different from that of the rest of the week. To a large extent it’s defined by what you don’t do - no work, no electronics, no driving, no writing, no cooking even, and crucially, no planning for the week ahead. What’s left to do? Walk around to various locations of gathering (the synagogue, people’s houses), pray/sing, eat/drink, hang out.

I came across a quote I like in Heschel’s The Sabbath, which pitches Shabbat in opposition to the frantic utility-maximization of the work week:

He who wants to enter the holiness of the day must first lay down the profanity of clattering commerce, of being yoked to toil. He must go away from the screech of dissonant days, from the nervousness and fury of acquisitiveness and the betrayal in embezzling his own life. He must say farewell to manual work and learn to understand that the world has already been created and will survive without the help of man. Six days a week we wrestle with the world, wringing profit from the earth; on the Sabbath we especially care for the seed of eternity planted in the soul.

“The betrayal in embezzling [one’s] own life” - this resonates with me, but not because I’m constantly wringing profit from the earth. Instead, I find myself to be wringing my own specific variety of things - profit sometimes, but also board games, piano albums, plans, personal systems, health recoveries, and blog posts! The overarching category for me would be projects. In a way, my whole life feels like a project, and vast amounts of my experience are through the lens of project mind - that mental state in which I’m thinking of which actions might move my endeavors forward.

Project mind has its benefits, but it’s not quite conducive to caring for the seeds of eternity planted in the soul. Doing so requires present mind - being present with the people and world around. Present mind (or the encouragement of it) is part of what Shabbat offers, and part of what any time-constraining communal practice can offer as well.

Micro-Shabbats and Macro-Shabbats

I don’t have a Shabbat practice right now, but I do have Stretchly breaks, which, as scheduled pauses in productivity, are (sorta?) like micro-Shabbats2. When I get an instruction…

… I take it as an opportunity to enjoy the moment I’m occupying.

Is Stretchly just another tool in my project-mind’s acquisitive arsenal? Well, it could be, but it could also be a tool for presence. Connecting back to Heschel:

The Sabbath is not for the sake of the weekdays; the weekdays are for the sake of Sabbath. It is not an interlude but the climax of living.

Likewise, my computer breaks need not be productivity-serving interruptions, they can be earned moments of enjoyment - micro-climaxes of the workday, providing punctuations of pleasant differentiation.

Of course, the great benefits espoused by Williams, Burkeman, and Heschel are not to be found in software-mediated micro-pauses, and, at risk of being project-minded, I hope to introduce more macro-Shabbats (perhaps even the macro-Shabbat - Shabbat itself) into my life. But the path there may be long. In the meantime, I will be changing my sitting posture slightly more than usual. And hopefully continuing to enjoy it.

…

Want to try Stretchly yourself? click here on your computer. And if you’ve been following the instructions, here’s one more…

Subscribe now

Somewhere in a data center, billions of billions of floating-point calculations whir away on a fleet of GPUs, spitting out hundreds of thousands of tokens. The last 100 tokens are formatted and sent to a remote server for grading. A single puzzle has been completed. 119 more to go.

Finally, the result comes back: 84.6%. A new world record for Gemini 3 Deep Think! Has artificial general intelligence been achieved?

ARC-AGI is a series of benchmarks aimed towards evaluating the intelligence and/or reasoning ability of AI systems via the completion of visual patterns. Since 2019, AI systems have steadily progressed towards solving these tasks, with multiple high scores being published this month, each using a different solution architecture. But what particular approaches have succeeded, and how can we interpret those results?

These questions are answered in three parts:

1. The history of ARC - starting from the seminal paper On the Measure of Intelligence and continuing through the evolution of the benchmark and key historical solutions

2. Do we have AGI yet? (probably not) - discussing how we might interpret benchmark results in light of the AGI question

3. Are base LLMs the best? (so far, often so) - discussing the performance of different solution architectures, and how we might attribute performance gains to different research advancements

Finally, I touch on whether today’s commercial LLMs might grow to become generally intelligent.

Subscribe now

Part 1: The history of ARC

2019: ARC is created

In 2019, Keras creator Francois Chollet was concerned by humanity’s lack of progress towards artificial general intelligence (AGI). Disillusioned by the lack of flexibility in contemporary AI systems, Chollet published the paper On the Measure of Intelligence, arguing that better metrics for intelligence would aid in the development of usefully intelligent systems.

He wished to first nail down a definition of intelligence. The paper discussed many existing definitions, eventually arriving at skill-acquisition efficiency - the ability for a person or machine to quickly learn new techniques in new environments and thereby solve new problems.

To help researchers measure skill-acquisition efficiency, the paper presented a set of puzzles titled “Abstraction and Reasoning Corpus (ARC).” Each ARC task includes pairs of pixel grids, each pair representing an input and an output. The test-taker must determine the pattern between inputs and outputs and apply that pattern to a test puzzle (a lone input grid). For example, the following puzzle requires completion of a symmetrical pattern:

Each task in the dataset is handcrafted to represent a unique human-understandable pattern. If a test-taking machine could cheaply and reliably solve these without training on similar tasks beforehand, that would be a strong signal of its skill-acquisition efficiency and therefore general intelligence.

At the time of the paper’s release, no machine scored well, but commercial LLMs were right around the corner.

2019 - 2024: The rise of commercial LLMs

In 2019 LLMs were still nascent technology, with OpenAI’s GPT-3 model to be completed one year later in 2020 and released as ChatGPT in November 2022. How did this model and its successors fare against ARC?

Surprisingly poorly (though unsurprising for Chollet). Even GPT-4, released March 2023, scored only 7% when presented with textual versions of the problems (source: Jack Cole). And GPT-4o, released mid 2024, achieved only 4.5% (source: ARC leaderboard).

Notably, GPT-4 was OpenAI’s first “vision model,” but it seemed that the model’s new image-processing capabilities did not yield substantial gains on visual reasoning tasks like ARC’s.

This failing stood in contrast to early LLMs’ ability to mimic human conversation. Such mimicry was once proposed as a measure of intelligence in Alan Turing’s famous Turing Test. And yet, progress in conversation mimicry soared while progress on ARC stalled.

Alternate ARC approaches show promise

Program search (2020-2023): Chollet first hosted an “ARCathon” competition in 2020, and a pseudonymous “ice cuber” won with a 21% score. Ice cuber’s approach involved no neural networks, and instead used brute-force program search over a domain-specific language (DSL) of pre-built image-transformation primitives, attempting to compose a sequence of transformations that would faithfully produce the example outputs from the example inputs (source: ARC-icecuber repository).

As competitions continued, brute-force program-search solutions remained winning but with diminishing gains. In early 2023, Michael Hodel created an ensemble of past program-search solutions, scoring a 30.5% and capping off the era of program-search domination (source).

Transformer-based solutions take the lead (late 2023): Then at the 2023 ARCathon, a team named MindsAI shared first place, and soon after recorded a new high score of 33%. MindsAI’s solution is documented in their 2025 paper, and is notable as the first state-of-the-art deep-learning approach.

Their solution has three main components:

1. Pre-training on synthetic and augmented data: They used Michael Hodel’s RE-ARC to create 400,000 ARC-like puzzles for pre-training.

2. Test-time fine-tuning (TTT): At test time, for each puzzle, they generate a small training dataset based on augmentations of the given input-output pairs (for example, removing one pair, rotating the grids, applying a new color mapping), then they fine-tune the model on that augmented dataset. This was their core innovation, to which they attribute a 300% accuracy boost.

3. Augment, Inference, Reverse-Augment, Vote (AIRV): This part is very clever in my mind. First they use the same data augmentation engine as above to transform the test input grid into a large number of similar grids (using rotations, color mappings, etc.). Then, they run inference on each transformed grid, collecting a list of results. These results can then be remapped using the inverse of the original transformations, yielding legitimate candidate results. The candidate that received the most “votes” (that was produced the most times across all transformations) is chosen as the winner.

2024: ARC Prize announced

In mid 2024, Chollet teamed up with Zapier founder Mike Knoop to announce the ARC Prize, setting up $1M+ in incentives including a $600K grand prize. To secure the grand prize, a team would need to publish open-source code capable of achieving an 85% success rate on the ARC puzzles, using limited computational resources within a secure internet-free sandbox.

By the end of 2024, MindsAI was in the lead with a 58% scoring solution (an updated version of their previous winning solution). However, they declined to publish their solution’s source code and so did not make it to the podium. First place went instead to “the ARChitects” with a 53.5% score, and the grand prize remained unclaimed.

The ARChitects new deep-learning approach

The ARChitects overall pipeline was similar in form to MindsAI’s, but with different design decisions for many subcomponents (paper). Their candidate-generation and selection approaches were novel:

• Candidate generation: ARChitects essentially used the AIRV approach described above, but rather than sampling from a model with high temperature in order to create candidate answers, they performed depth-first search over all possible completions, extracting only those whose sampling probability exceeded a certain threshold.

• Candidate selection: Their voting system took into account the sampling probability of each candidate across each input transformation.

In sum, they leveraged the sampling-probability distribution built into their deep-learning model to a greater degree than past approaches. Still this was not enough to beat the incumbent MindsAI.

June 2024: ARC-AGI-Pub, the new public leaderboard

In parallel to the above contest, the ARC Prize Foundation released a second benchmark and leaderboard for closed-source solutions, allowing players like OpenAI to officially test their models. The public test dataset is “semi-private” - it’s not available on the open internet and therefore shouldn’t make it into any model’s training corpus (an important consideration when testing for “skill acquisition”), however the data is provided publicly at test time, and so could be leaked or trained on by a bad actor. That’s part of why there’s no monetary reward for ARC-AGI-Pub (though AI labs are surely incentivized to do well on this benchmark for PR reasons).

December 2024: O3’s breakthrough

A series of results on ARC-AGI-Pub brought the high-score for unassisted LLMs into the low 30 percents by the end of 2024. Then, a preview version of OpenAI’s O3, an early chain-of-thought-enabled reasoning model, achieved an 88% on ARC-AGI-Pub in December 2024 (source: ARC Prize blog). This was a breakthrough result, but came with some important caveats:

1. The preview model was trained specifically for success on ARC, unlike the later released O3 model which performed worse (source: ARC Prize blog).

2. O3-preview took a whopping 14 minutes and $4,560 of GPU compute per task, far exceeding the compute allowance of the open-source ARC Prize contest, and far exceeding reasonable estimates of the true cost of solving these small puzzles.

2025 - 2026: Refreshed benchmarks

Still, in 2025 the ARC Prize Foundation wished to counter the recent success of reasoning models, so they released a a new dataset called “ARC-AGI-2” and the old dataset became “ARC-AGI-1”. ARC-AGI-2 looked much like its predecessor:

… but sought to test for capabilities with which reasoning models struggled, such as:

1. Symbolic interpretation: assigning significance to visual symbols (see image above)

2. Compositional reasoning: applying multiple rules on top of each other

3. Contextual rule application: applying rules under specific contexts
   (source: launch post)

In tandem, the 2025 ARC Prize was launched with similar prizes and guidelines to the prior year’s. This time around the eventual top score was 24%, indicating that ARC-AGI-2 was indeed a harder benchmark.

Base LLMs see rising success

Despite the low scores on 2025’s ARC Prize, today’s frontier reasoning models continue to notch higher scores at greater efficiencies against the semi-private test set. Just this month, Google announced a massive 84.6% score (at $13/task) for their new Gemini 3 Deep Think model.

Is it over for ARC? Nope, the cycle continues: ARC Prize is already planning their 2026 benchmark, this time with an interactive game format (ARC-AGI-3), to be released March 25th, which will in all likelihood be more difficult for today’s LLMs. You can play the first three example games here.

Part 2: Do we have AGI yet? (probably not)

Is Chollet moving the goalposts with each new benchmark? And is Gemini 3 Deep Think already AGI?

Well, the goalposts are moving, but wouldn’t a general intelligence be capable of following a moving target? Isn’t that exactly what skill acquisition would enable? Concretely, as long as each successive ARC-AGI benchmark is achievable by humans, we can say that failures on the part of machines indicate a lack of general intelligence.

In fact, Chollet’s original paper acknowledges the need for periodic refreshes:

ARC only features 1,000 tasks in total, and there may be some amount of conceptual overlap across many tasks. This could make ARC potentially vulnerable to shortcut strategies that could solve the tasks without featuring intelligence.

[…]

…to mitigate potential vulnerability against such shortcuts, we intend to keep adding new tasks to ARC in the future, possibly by crowd-sourcing them.

What are the specific shortcuts that Chollet might consider disqualifying? The most likely culprit would be directly training on large synthetic datasets that closely mimic the puzzles themselves. Doing so arguably counts as pre-acquiring the skills that are supposed to be acquired at test time. Such pre-training has already been a hallmark of the winning deep-learning strategies since 2023, and is especially prominent in 2025 prize-winner NVARC’s solution. Also, we cannot rule out that closed-source model providers like Google might be taking similar approaches as well to improve their results on the public benchmark. Unfortunately, this makes the entire leaderboard harder to interpret.

No AGI until ARC-AGI-n is insta-saturated

A key pattern to observe is whether new ARC-AGI benchmarks saturate immediately. If Gemini 3 Deep Think scores well on ARC-AGI-3 in March, that would indicate the kind of fluid intelligence Chollet was looking for in his original paper, as the model probably hasn’t trained on environments similar to ARC-AGI-3’s games. If instead it takes time for Google and other labs to saturate the benchmark, we will be left wondering whether the gain is from general intelligence abilities, or from pre-trained skills that are aimed at beating the benchmark.

Part 3: Are base LLMs the best? (so far, often so)

Which methods are most successful against ARC, and which are most promising? Firstly, to define success…

The ARC leaderboards show a Pareto frontier between cost and score, and any submission along that frontier of low costs and high scores can be considered successful. What trends do we see?

Frontier trends

The ARC-AGI frontier has vacillated between different solution architectures - the early 2020s saw search-based program synthesis winning, while recent years saw chain-of-thought/reasoning LLMs pull ahead using transduction (producing the output grid directly instead of producing a program that produces the grid)… just look at how much of the frontier in the image above is dominated by Google’s green Gemini 3 Flash Preview and Gemini 3 Deep Think.

But even in recent months, we see a variety of architectures neck-and-neck for the frontier. Earlier this month a solution by Johan Land (code) topped the leaderboard with 72.9% on ARC-AGI-2 for $39/task. While this was soon eclipsed by Gemini 3 Deep Think, this solution has its part to play in the overall trends.

Johan Land’s briefly state-of-the-art kitchen-sink solution

Land’s solution involves a complicated pipeline, which works as follows (you can skip this numbered list if you’re satisfied by “it’s complicated”):

1. In parallel, run a bunch of state-of-the-art reasoning LLMs, some of which are tasked with producing a grid output, and some of which are tasked with code generation.

2. If there’s sufficient consensus among results produced by the above, then finish (this saves some money)

3. (if enabled) repeat the above steps using different models

4. Then run all five of these strategies in parallel

   1. Deep thinking: prompt a model to think especially deeply about the problem before producing its output

   2. Image input: Feed rendered images to a model, ask for grid output

   3. Hints: Get an LLM to analyze images and produce hints. An LLM uses these hints to produce a grid output.

   4. Structured, object-based thinking: A 3-part pipeline that compels models to describe the objects they see, then describe the transformations between those objects, then finally, in context of all previous answers, produce a grid output.

   5. Codegen: Re-run the codegen aspects from step 1, but with more models runs.

This was truly a “throw everything at the wall and see what sticks” solution, combining lots of raw LLM power with various forms of cognitive scaffolding.

For a brief moment it was the highest-scoring solution out there, surpassing Claude Opus 4.6’s score of 69.2% by 3.7%, though at 11 times the cost. Given the 120 puzzles in the semi-private test suite, Mr. Land spent ~$5K on the test run alone, to say nothing of the costs in developing his methods.

The biggest recent gains came from base LLM capabilities

Gemini 3 Deep Think outperformed Land on both accuracy and cost. Approaches with more scaffolding and/or symbolic reasoning, like Land’s, have occasionally reached the frontier, but they usually represent modest gains over incumbent transduction-based approaches, while incurring larger costs. Every approach at the top of the current public leaderboard relies heavily on LLMs even when combined with scaffolding, and improvements in the underlying models seem to cause improvements across the board. This suggests that a large amount of progress towards solving ARC (at least on the closed-source end) is due to advancements in LLMs.

Is this bad news for the ARC Prize Foundation’s mission to support novel research? Perhaps, but they have a few facts working in their favor. Firstly, LLMs did see meaningful algorithmic improvements over recent years - OpenAI’s O1/O3 models, for example, introduced the chain-of-thought reasoning approach that led to huge gains on ARC and many other benchmarks. Secondly, for the actual ARC Prize, which requires open-source models to run on limited hardware, each year’s winners have presented solutions with meaningful complexity outside of the LLMs that they leverage.

A possible synthesis of these facts: at smaller cost scales, independent researchers are incentivized to explore a variety of novel approaches, and these approaches beat out simpler LLM-based approaches and push the research frontier forward. At larger cost scales, submissions become too expensive for independent researchers, except for the occasional tech Senior Vice President (Johan Land), and the charts become dominated by big labs whose primary motive is to showcase their models as standalone products.

Where does program synthesis fit in?

A recent twitter post from Chollet reads:

I believe that program synthesis will solve reasoning. And I believe that deep learning will solve program synthesis (by guiding a discrete program search process).

But I don't think you can go all that far with just prompting a LLM to generate end-to-end Python programs (even with a verification step and many samples). That won't scale to very long programs.

Chollet has long been an advocate for program synthesis, and in January 2025 he and Knoop founded NDEA, a research lab building “AI systems that blend intuitive pattern recognition and formal reasoning into a unified architecture.”

As suggested by the tweet above, the architecture he wishes to build would not be the kind of LLM-assisted program-synthesis approach that Ryan Greenblatt used to top the ARC public leaderboards in mid-2024, which we see repurposed as a sub-component of Johan Land’s pipeline above - though by all appearances, such architectures are close to his vision. NDEA has not published anything yet, so we’ll have to wait and see how their approach differs.

However, the current frontier of ARC-AGI-2 submissions all use direct transduction without program synthesis, so it would be impressive if NDEA could present a program-synthesis architecture that’s competitive on past or future ARC benchmarks.

Will the LLMs generalize?

The ARC-AGI frontier has been populated by a wide variety of cognitive architectures, but for now is dominated by commercial LLMs - the same systems that answer our questions and write our code. Seeing whether these systems succeed immediately on the novel ARC-AGI-3 tasks will be a good test of their general intelligence abilities.

A key open question is whether commercial LLMs will grow to succeed at ARC-AGI-3 and subsequent versions. Per the ARC Prize website, “AGI [is] still unsolved. New ideas [are] needed.” But Dario Amodei, CEO of Anthropic, would disagree. In a recent interview with Dwarkesh Patel he indicated that he expects Anthropic’s training plan to scale to fully generalized intelligence (at least in domains that are operable by text). I’ll leave with his quote:

…all the cleverness, all the techniques, all the “we need a new method to do something”, that doesn’t matter very much. There are only a few things that matter.

[…]

In fact, I would point to the history in ML of people coming up with things that are barriers that end up kind of dissolving within the big blob of compute. People talked about, “How do your models keep track of nouns and verbs?” “They can understand syntactically, but they can’t understand semantically? It’s only statistical correlations.” “You can’t understand a paragraph, you can’t understand a word. There’s reasoning, you can’t do reasoning.” But then suddenly it turns out you can do code and math very well.

[…]

I think we may get to the point in a year or two where the models can just do [software engineering] end-to-end. That’s a whole task. That’s a whole sphere of human activity that we’re just saying models can do now.

Subscribe now

They say “slow is smooth and smooth is fast.” But you could also say “fast is fast,” which would be faster to say. I’ve been trying to say things fast, in order to be more smooth. Catch my drift?

… In all seriousness, I tend to talk slower than most, and I have been trying to talk faster, and I do think that doing so could increase my ease in conversations and allow me to listen better. I’ll explain my thinking and tell the story of a successful fast-talking experiment.

To wait has weight

As mentioned I tend to talk slower than most, and I reckon that sometimes I’m slow to decide and to act. But let’s focus on talking.

What does slow talking get me? Slow talking gets me space to think. This sounds good on the surface, but sometimes it’s a trap…

Subscribe now

An overthinking scenario

Let’s say you ask how I’m doing, and I’m aware of some challenge I faced this week. I formulate a response, but I don’t speak it - there’s a mental process that’s deciding whether the response is appropriate. How does that process evaluate? It needs to guess at your judgements towards me upon receiving my words. Perhaps, in this case, the result is uncertain. So I consider more options…

(Thoughts) But wait. How much do I value honesty vs. balance in the conversation? If I speak honestly, then we might just end up talking about my things, because I’m good at coming up with analyses. If you’re a question asker, I’ll just keep giving answers. And we can’t let that happen. What leads the conversation in a good direction?

At this point in the convo I offer some platitudes, but we’re off the deep end now, because now I’m in thinking mode™ and am in various ways self-conscious, and am not paying great attention to you, my interlocutor. Each question I receive pulls me further into rumination, as I carefully reconstruct and interrogate my intricate, fragile models of the world and my actions within it…

What an inconvenient dynamic! How do we prevent this!

There might be many ways to relax one’s mental grip and/or become a more engaged listener, but for me, what I ended up trying was to just talk fast, and I’m happy to say that I had a great time doing so.

A successful fast-talking experiment

I was at the Sauna with Olly when I thought, “you know what? I’m gonna talk to Olly without thinking. I’ll just observe my words as they come out of my mouth, not before. I’ll just talk fast.”

It was a wonderful experience! First of all, my approach basically worked - I was able to talk much faster. When I didn’t give myself time to think, my thoughts quieted down in a very pleasant way, and I could pay attention to what my friend was saying.

Under normal circumstances I would ask questions and think “is this a reasonable question?” and end up being self-conscious, but this time around, I was freed to focus on my conversation partner. I could feel a slight impulse to evaluate my questions before speaking, but could override that impulse, smoothing over the intrusive bump and returning to my present experience - the experience of what he was saying, and what I was saying too.

Also, as a recipient of questions I found myself to be defended against the pitfalls of overthinking. If asked a hard question, I could say “man, I don’t know, that’s a hard question,” and then later could say “I guess [xyz],” but in a way that makes it clear that I don’t fully endorse what I’m saying. That I don’t fully endorse anything I might say, as I’m not capable of coming up with definitive answers and proofs of their correctness. That I’m just talking. That it’s playful. That I can just say what’s on my mind instead of sitting there and recomputing my entire world-model every minute.

As time went on, I gained a sense of self-confidence, in my ability to have good conversations and in my ability to act well in the world. I felt that just as I could speak with little hesitation, so too could I act on the world with little hesitation, and feel good doing it.

Towards a broader practice of talking (and acting) fast

I’d like to keep practicing my ability to talk fast, especially in low-stakes informal conversations. I see this as part of a greater endeavor to reduce the burden of thinking and justifying that steers my attention away from the present moment.

Besides the benefits mentioned above, talking fast has the obvious benefits of getting more information across quickly, and it’s more collaborative too - it suggests, “we can figure this out together, and I trust you to understand my process along the way.”

Something similar could be said about acting fast in the world… That the world might reward you for acting upon it from a place of uncertainty; it might appreciate getting to figure things out together. I think that’s (metaphorically) true, but I’m not sure how I would approach a practice of acting fast. Whereas a practice of talking fast is easy to pursue.

Note: Surely there are times when slow, thoughtful conversation is better, and some people would benefit from working on that end of the spectrum (remember to consider reversing all advice).

I’d be curious to hear from my readers - do you tend to think before you speak, or not? Did anything here resonate with you? I am always happy to receive comments, or phone calls - in the latter case, expect me to talk fast.

til next time,

Daniel

Subscribe now

I’ve been thinking about how I might cultivate “deep knowledge” in my career and/or life. This essay explains what I mean by that, and tells the stories of three people around me who have done so. These stories make up the second half of the post, and are about:

1. A Civic Entrepreneur

2. A Logician and Radical Behaviorist

3. A Computational Biologist

But first, my problem statement:

I am awash in a sea of concepts

Increasingly, I feel that I know less and less. The world is a complicated place and it’s getting more complicated. Just this week, Moltbook arrived, and suddenly, machines are writing human-like posts to each other on an (ostensibly) AI-only social network.

What are the implications? No one knows, really. Perhaps this is a fun experiment that goes nowhere, perhaps it is an awakening of a new hive mind that will soon dominate the world. Most likely, it is a currently harmless experiment that foreshadows a near future of increasingly confusing dynamics between humans and growingly empowered machine intelligences.

When I say “no one knows”, I’m including the researchers and engineers who built the language models that make up the most significant part of these agents’ internal workings. I know this because I follow them on Twitter and Substack and other places. There is a healthy debate ongoing about the trajectory of AI, with some believing that AI will show diminishing returns, growing to nothing more than a helpful assistant for well-scoped tasks, and others believing that autonomous software agents will eclipse humans in all capabilities. Beliefs about timelines for such outcomes vary widely.1

…

Additionally, in my own work I feel I know less and less. I write code in high-level languages, far from the actual binary operations of my machine. These languages shift in and out of fashion while I sit atop the current wave. And whereas I previously needed to memorize many programming language features, I now rely on LLMs to write most of my code for me. With the introduction of new flagship LLMs like Claude Opus 4.5, I find fewer errors in the code they generate and am incentivized to delegate larger tasks.

Beyond that, I spend a lot of time reading blogs and listening to podcasts, and though I’m occasionally inspired by these sources, I don’t feel they leave me with a much better understanding of the world. I feel that they leave me with a fashionable vocabulary that sits underneath a discordant pile of half-understood concepts. When I attempt to articulate informed beliefs on subjects about which I’m “well-blogged”, I surprise myself with my lack of understanding.

Towards deeper knowledge

I don’t doubt that my effectiveness at work and in other arenas of life is increasing over time, but I also don’t enjoy the feeling that I lack strong understandings of the world and my impact within it. I wish to do good, and to develop convictions about how to do so. In this rapidly changing world, such footholds seem hard to reach, and yet I maintain the belief that they’re reachable, and that doing so is a sure way to have a positive impact on my community and/or the world. I maintain that belief because I see confirming examples, sometimes in the people around me (more on that soon).

I’ll call what I’m looking for “deep knowledge.” What do I mean by that? Here’s a graph of how I’m thinking:

Here’s what you’re seeing above:

X Axis - “Solidity of knowledge”: Solidity could be broken down into sub-dimensions of transience and rigor. For example, knowledge about a particular US census might be rigorous but transient. Knowledge about Internal Family Systems might be less rigorous (no offense to IFS - just a bit of a fuzzier topic). Whereas knowledge of Newton’s laws of motion would be rigorous and perpetually applicable.

In truth, the concepts “transience” and “rigor” might not perfectly encompass what I wish to describe here, and I use “solidity” as a placeholder for some more calibrated term of judgement around knowledge’s applicability.

Y Axis - “Depth of understanding”: The bands here describe levels of understanding. Note the “Twitter/Substack Zone (Danger!),” which I lament earlier in this essay. To clarify, it is specifically the ambient-scrolling form of consumption (which I find myself doing all too often) that seems insufficient for deep understanding.

The top-right zone is the “Deep Knowledge Zone,” in which one has a deep understanding of a solid knowledge area, such that one can speak, write, and think well about it. But really the whole top row is a good place to be.

Stories of deep knowledge

I will speak of three people around me who have taken their own paths in the deep knowledge direction, each of whom inspires me in different ways.

Caveat: these stories are from memory, and only represent my own perspective

The civic entrepreneur

I met Daniel at my co-living house in Brooklyn. Along with his impassioned speeches about America’s founding fathers, I learned of his vocation as the founder of Maximum New York (MNY), a “civics academy focused on governmental mechanics.”

Daniel took his own learning very seriously on the way to becoming an instructor. He seeks to read five books on each subject before he considered himself to have a reasonable grasp of it, and he’s done so with many subjects. He studied each aspect of the government in granular detail, including such feats as memorizing the NYC charter and reading every local law passed in 2023.

On our “Knowledge Zones” graph: Daniel’s knowledge would be distributed around the top layer - he knows a great deal about a subject area (government & politics) that is itself sometimes amorphous. But, within that area, Daniel’s knowledge is about as fundamental and mechanistic as it gets, and that places him in a position to pursue impactful projects from a standpoint of intellectual rigor. I am super inspired by his work with MNY and his other political activities, all of which are oriented towards promoting the prosperity of New York City and its citizens.

On learning paths: Much of Daniel’s learning happened outside of the university - after graduating, he underwent a number of career pivots and personal projects that eventually led to his current direction, and along the way he pursued much of the learning (and especially learning by doing - engaging with his local political systems) that led to his current expertise. Daniel has also expressed disatisfaction with political science degrees.

The logician and radical behaviorist

I met John during my time in college and have since struck up a correspondence in which we discuss all kinds of topics, often adjacent to human behavior and computing.

John has read an impressive amount, and, like Daniel above, has the bookshelves to prove it. John’s areas of interest are wide, but they center around logic, math, and the science of human behavior.

On learning paths: John has a diverse educational past that involved study and research across many subjects (math, physics, cognitive science, computer science) at a few institutions. During his undergraduate years he honed in on math as a primary interest and met mentors (David R. Larson and Ronald G. Douglas) whom he cites as ongoing influences.

Eventually John dropped out of a math PhD program and continued to independently learn about the history of math, logic, and behavior. Over time, he developed a perspective and opinions on such fundamental questions as “what is truth?” and “how is science done?” and “how do people function?”

I asked John how long it would take for me to understand his worldview. “About a decade,” he said, once again sending me a picture of his bookshelves. But he admitted that there was a handful of books that most captured his worldview, and I got started reading one of them: “The Analysis of Behavior (Programmed Instruction).”

Reading this book is part of what inspired me to write this essay - it was a joyful experience to learn something very fundamental about our world, and to do so not by scanning blogs that I’ll soon forget, but by carefully engaging with a system of memorable facts and theories. For example, did you know that your body has three kinds of mechanisms for responding to its environment: striated muscles that move your skeleton around, smooth muscles that modulate the dimensions of internal organs, and glands that release various juices? What a basic thing that I was unaware of!

On our “Knowledge Zones” graph: John’s knowledge is clustered at the top right, being both solid and deeply understood. John is still in the early stages of applying this knowledge to the world, but he aims to contribute to the survival of what he sees as an atrophying culture of scientific rigor, in part by developing and sharing teaching materials related to science, logic, and behavior.

The computational biologist

I got to see Pascal speak at my house’s “TED talk series.” He spoke for an hour plus about Vilya, a recently-trained neural network that can predict the structure of small cyclical molecules (macrocycles) with state-of-the-art accuracy (think of this like DeepMind’s AlphaFold, but for even smaller biochemical structures). Predicting these molecular structures can speed up the development of drugs that neutralize harmful proteins.

As with my reading of “The Analysis of Behavior,” I loved stepping into a world of more concrete truths. There’s something thrilling to me about looking at a chemical diagram and thinking “wow - this is very real, and very important, and I know very little about it, though much could be known.” And as with MNY, I am inspired by Vilya as an application of deep knowledge towards pressing problems.

On our “Knowledge Zones” graph: Vilya is a collaboration between biologists, chemists, and machine-learning engineers like Pascal, and Pascal’s own role required him to have knowledge of each subject. I believe his knowledge would occupy various x coordinates along the top of the graph, with biochemical knowledge being an especially solid component.

On learning paths: Pascal completed a computational biology PhD before joining Vilya. He considers himself to be lucky to have landed an excellent advisor and a personally-interesting research area with a high potential for impact.

So how does one get to deep knowledge?

There’s some overlap in these three stories. In all cases, the knowledge-acquirer was substantially interested in their field and spent at least a few years dedicated to learning. In all cases, this learning involved a high volume of book-reading and accompanying writing (whether for personal notes, publications, or assignments). At least in Daniel’s and John’s cases the curriculum involved both modern and historical texts. And at least in John’s and Pascal’s cases, the academic environment and key academic mentors were important parts of the picture.

Again, a big caveat - these are my own analyses! I would certainly benefit from asking these people more about their own perspectives on their learning journeys. But today it’s Wednesday, and the blog must go out.

…and how might I pursue deeper knowledge?

As to my own possible paths, I have a few open questions. One is “what to learn about?” I seem to have intrinsic interest in computation and planning (a la Methodable), and those interests point me towards the realms of AI agency (or human agency). There are also deeper directions to go when it comes to software engineering more broadly. However, these directions feel less solid when compared to e.g. biology. I actually feel excited about computational biology presently for that reason, though this is a recent interest, and I don’t know much biology yet.

The second open question would be how to approach such learning, in case I’d like to do so. The academic route is appealing, as higher ed is our primary institution for the development of deep knowledge. But I worry about ending up in the wrong lab and studying something that is not personally interesting or applicable to real-world problems. So on reflection, a key sub-question is: “how easy is it to pivot and choose your own research direction in various academic settings?” - If the answer is “very” then that seems a promising direction.

On the flip side, I seem to be surrounded by a culture of DIY learners, some of whom have indeed gone very deep in their subject areas. Considering such approaches in my own life raises further questions: how would I find/create a community of learners and support myself through a learning period? How would I maintain clarity on a learning path?

If anyone has thoughts or related experiences to share, I’d love to hear from you.

Subscribe now

Til next time,

Daniel

Hi readers! Changing gears from the previous long and technical post… This one’s a bit more “light” - it’s about the very first Sneaky Town tournament!

For those who don’t know, Sneaky Town is a board game I’ve been designing over the last six years. It’s a two-player game in which players compete to capture points, each working with their own set of secret information. Here’s an action shot:

(the game also has a blog and instructions for those curious)

Sneaky Town has been a perpetual slow-burn side project. Over the years, many dozens of people have played, most notably a stream of competitors over a 3-day stint at Vibecamp 2:

But up until now, I’ve had just one board. Recently I made new boards, and that unlocked the ability for me to host a tournament with five (5!) concurrent games. This is the story of how that went - the lead-up, and the tournament itself, and what I learned along the way.

Beginnings: embracing serendipity and commitment

When I first came up to Seattle, I thought I was only staying a couple weeks. I had no plans other than to visit friends and take it easy. Then I found myself going to cafes and libraries and randomly started working on new tile designs and a rulebook for the game. My brother thought I might want to visit his friend “C” who works at a Seattle makerspace (Seattle Makers), in case there was any synergy with the project, so I went to check it out.

I had been to one makerspace before, Noisebridge in San Francisco, which is where I made Sneaky Town board V3. Noisebridge is an awesome place - it bills itself as “anarchistic” and it’s totally free to use. The downside of the free-ness and anarchism is that it’s disorganized and doesn’t have a lot of great machines. So, my expectations were low when I came to Seattle Makers.

I was very pleasantly surprised! They even uses a pricing system to allocate machine time... “Great market-based coordination here” I thought. C showed me around to exactly the machines that I might use to make the next set of boards - their CNC wood routers - and convinced me that it would be “easy” for me to make them there... “oh, and you need a three-part certification for the CNCs, and the next certification starts in two days, and there’s exactly one slot left.”

This felt like sufficient serendipity for me to pull the trigger and get a membership and sign up for certification. I was already considering staying in Seattle, and though I hadn’t solidified those plans, I figured I might as well make a commitment (even just to the month-and-a-half stay I was considering), as commitments are required to get anything serious done. After a couple hours I signed up, and my next stint in Seattle was secured!

The mad rush to pull everything together

After starting my new sublet and getting my CNC router certification, I began my work on the next round of boards (these would be version 4). I figured that if I was making so many boards (I planned to have four total by the end) I might as well host a tournament, and I figured there was only one date that made sense, and that date was a week away! So I made an invite link and sent it out to my entire Seattle network.

At this point the new boards were not at all created and their designs were completely unproven... So I was simultaneously hoping I could get enough participants for the tournament while desperately trying to get the boards across the finish line. I had come to Seattle to “chill,” and here I was in an intense week-long sprint.

Murphy’s Law in the woodshop

The week leading up to the tournament was fraught with logistics. Every morning I got up and spent the day before 2pm fervently tending to my flow charts and task lists. At 2pm I’d go into the makerspace and make the most of my 6-8 hours of time on their computers and machines. I had a very tight schedule assuming things did not go wrong... and many things went wrong. Including:

• Software issues: VCarve, the CAM tool I was using, couldn’t import multiple 3D models - had to get clever with exporting layouts from my 3D CAD software (OnShape)

• Timing issues: My CNC cut paths turned out to take way longer than I anticipated. Also, I hadn’t realized that the makerspace closed on Tuesdays.

• Material issues: I learned that oil-based wood finishes were off-limits in the makerspace (as oil-soaked rags sometimes spontaneously combust), and that finishes in general take days or weeks to cure

The final push

In particular there was one evening where I was planning to run my final cuts, only to learn that I simply didn’t have time before the shop closed. I felt sick to my stomach - this was my last chance to make the boards before the tournament started. What was I going to do?

On a walk outside, my mind was racing. I decided to make the difficult decision to change my board designs and forego the wood inlay I was planning. This was devastating, as it entailed using up the last of my wood, and potentially never seeing the fully inlaid board, the pinnacle I’d been building towards for the last month.

But it was more than just a difficult decision - I still had a ton of work to do in my narrow time window. I had to quickly re-orient and frantically re-compute my cut paths to make sure my last-minute pivot wouldn’t wreck my materials. The space closed at 8pm and I took my material out of the clamps just about then.

It was a strangely crushing combination - a lot of intense work towards an outcome I was already deeply disappointed by. But when the tournament came around, everyone liked the boards. No one cared about the lofty goals to which they fell short.

Invites

I spent a decent amount of time writing the invite. At first I was trying to make sure it was a competitive tournament, and the invite reflected that: I wanted clear RSVPs and time commitments.

But over time I realized that such strictness wasn’t really realistic, and wasn’t really the point. I changed the invite’s language to be more lax and to emphasize that it was a beginner-friendly event. I would see who showed up, and adapt the tournament to the party’s needs.

I included a specific schedule of events, to help people understand all that was planned...

And added an extensive FAQ. Altogether, I wanted the invites to get people jazzed and to leave them knowing exactly what to expect for the event.

The day of the tournament

Tournament #1 was a huge success! Here’s how the new boards came out:

Here’s how the apartment looked before people arrived - six boards with seating around each of them:

As people filtered in I pointed them to the soup station (on the left)...

I served two homemade soups, both of which were drinkable from cups. I figured that was a nice winter food which took up little table space and kept people’s hands clean (around the precious boards).

Directing the event

When it came time to first corral people and explain the rules, I got to practice my public speaking skills. I was actually thinking about this quote from Kamala Harris that I found on Twitter:

When you’re standing up to speak, remember that it’s not about you...

If you’re on the Titanic, and you know the ship is about to sink, are you going to worry about how you look and how you sound? No. Cause the thing that’s most important is that everyone knows what you know.

That was the headspace I was in - well, not that it was a Titanic-level event, but I did have a lot of teaching and instructing to do, and I sought to do so straightforwardly without worrying about my appearance.

Also, I read somewhere that it’s a host’s job to tell people exactly what to do, as people like having clear instructions. I was in that mode as well. I was happy with the event’s overall flow - people got the hang of the game, and played many rounds amongst themselves without my guidance. After I introduced the tournament section of the event and told people what to expect, I gave a “passing period” where participants chatted for 15 minutes while I set up the bracket. In all, there was a good mix of intense gameplay and laid-back socializing.

People playing the game!

At the peak of the event there were 15 participants and five consecutive games:

The bracket

I used an online bracket software (challonge) to set up a single-elimination tournament. I wanted each competition to be at least “best-of-3 wins”, because Sneaky Town is both somewhat luck-based, and a lot of strategy takes places between rounds. Ideal would have been best-of-5 or even best-of-7, but we simply did not have enough time (and I knew I was already asking a lot of people).

I also considered double-elimination or Swiss style tournament designs, but chose single elimination, again because of time constraints, and because I wanted to make sure that there was a definitive finals event that everything built up to. In the end, the tournament design was sufficient to be fun and to produce a clear winner, even if it wasn’t the most high-signal result (no offense, winners).

The Podium

Rosie and Magoo took #1 and #2 spots respectively, and Olly and Yoshiko shared 3rd place (there was no tie-breaker for them).

Each medal was made of lemon-cornmeal shortbread cookie with edible metallic frosting, in the style of Sneaky Town’s distinctive eye motif. The silver medal:

Board close-up for reference:

I think at least one medal got eaten.

... in the end, I invited everyone to stay for dinner (quiche + more soup). And the Seattle Sneaky Town community was born! This was also when I was finally convinced to stay longer in Seattle - I got such great encouragement from that group of people.

Feedback & learnings for the game

Some constructive feedback I received was that the tile racks are finicky. The obvious solution is to make them a bit deeper in future editions. Also, I noticed (and continue to notice) that players often forget certain rules (specifically, the rule that lets you move pieces around on the board). I think the solution to that problem is to improve the way I teach the game - make sure people actually go through the motion of each action themselves.

Otherwise, the feedback was super positive! This was especially rewarding coming from the players who were new to the game. I’m glad they could learn quickly and enjoy themselves, even when I had limited capacity for 1:1 teaching. But the most positive feedback I received was a request to “run it back”, which was seconded and third’ed and so-on’ed by many participants.

…So, let’s do it again! Once the boards are back in commission (they’re currently in the shop), I’ll be having another tournament. Maybe for this one I’ll also just set a date and hope that everything fills in.

A success of sharing my projects

I felt very rewarded, after working my tuchus off, and falling short of many of my goals, to still have made something people enjoyed.

And obviously that’s the big lesson here: “just share your projects with people before you feel they’re perfect.” It’s easy for me to get caught up in perfectionism. This tournament worked because I set a date for it and invited people and forced myself to meet the deadline. That’s what I’m doing with this blog as well: forcing myself to share my work, even when it’s not always up to my standards.

My standards are often unreasonably high and don’t necessarily map to what other people care about. I won’t know where my projects and interests fit into the world until I put them out there. This tournament was a successful example of doing so. Let’s keep sharing!

I organized my thoughts and to-dos, and did my highest priority tasks in a properly time-boxed way, and meditated. When all was done, I could say “I’ve done what I needed to do today and had a good time doing so,” which is just what I’d hoped - a far cry from the dopamine rut my “spidey senses” had warned me about that morning. And all the time I had a calm companion guiding me along: the voice of my prior intentions.

Today, I am sitting in a cafe, and writing about a different time I was sitting in a cafe… do I have you at the edge of your seat? I hope so, because:

• If you are a new reader, you will be introduced to Methodable, my “human-programming tool,” a web app that helps people make systematic progress towards goals.

• If you are a past reader, you will finally see a real-life Methodable use case!

In particular, I’ll describe a day during which I used Methodable to un-scatter my attention and gracefully navigate a complex landscape of personal projects. I’ll cover the entire day, starting from when I awoke and continuing through the creation of a seed program which ultimately blossomed into a comprehensive, tailored guide for my day.

Methodable is a quirky, unmaintained piece of software, but I still find it useful in my own life, and I hope you’ll enjoy learning about the patterns of thinking and planning that it enables.

Our story begins on a Tuesday morning.

A day with no clear path

Some days I feel I know what to do - I have clear projects, and clear tasks within those projects, and I can just “do”. And I really enjoy those days! But on many other days the path is not clear. This was such a day.

To start, I woke up with little energy and little bandwidth for work, as happens to me from time to time. And I felt quite scattered. I knew I had a lot of items on my to-do list, far more than I could handle, but I didn’t know which ones were really worth doing.

(Here’s what my to-do list ultimately looked like, but take note - at the beginning of the day, these tasks were not yet even collected into a single list!)

Having experienced these days before, my “spidey senses” were tingling: I knew I risked going off the rails and spending my day scrolling through social media while flinching away from the uncomfortable question of “what should I do?”

I knew I had to set myself on a good path, so I started with a change of scene.

Simple interventions: walk + cafe + Methodable

I kicked off my first intervention, which was to walk to a cafe - that always helps me regain some clarity and situate myself for focused work.

On the walk, I realized that it was a perfect day for Methodable. I committed to open the Methodable editor first thing upon arriving and to write myself a program. That’s what I did and here’s how it went.

Kicking off a Methodable day

Here’s a screenshot of the initial program that I wrote (I’ll explain what you’re looking at shortly):

Some quick background on the Methodable editor: Methodable programs are composed of nested blocks of text. Writing a program feels like writing a bullet-point list, except that sometimes you use keyboard shortcuts to change the “verb” (the emoji on the left) of the block you’re on. The verbs tell the computer how to combine the text you wrote into a guided workflow.

Methodable programs are largely written in English (or one’s natural language of choice), but I’ll translate the above even further into English so that you can appreciate the journey I’m about to embark on. The program says:

I’d like to have a nice Tuesday. In order to do that, I plan to do the following:

1. I’d like to first write down principles to guide me today.

2. Then, based on those principles, I’d like to write a new Methodable program called “Have a day that fits my principles,” which should serve to guide me effectively through the day.

3. Then, I will immediately follow the steps of that program I just wrote!

A pattern: meta-planning

We can call that program a meta-plan: a plan for myself which compels me to create a more detailed, well-informed plan - and then immediately follow it. Meta-plans are Methodable’s bread and butter, and I use them to help myself start the day intentionally when I’m not yet sure exactly what I’d like to do.

For more on why I wrote this particular meta-plan, see Appendix A. To see how Methodable’s language supports meta-planning, see Appendix B.

… And then I pressed “Run” and for the rest of the day knew exactly what to do

Ok, so here’s what’s cool about Methodable: after pressing “Run” and starting a program, you enter a new experience in which your every action is instructed, step-by-step and in sequence. At every moment you have a single instruction to follow, and sometimes you are given a small workspace in which to complete the task (as shown above).

When you enter Guide Mode, it’s as if you have taken your own hand, saying “don’t worry, I know what we must do. Follow me.” And indeed, during that day in the cafe, after clicking “Run” I was completely at ease, knowing that I was following the plan I had set for myself.

The magical part is, you can start with a very simple seed program like the one above and watch it blossom into a comprehensive guide, all while staying within a single step-by-step flow.

How my meta-plan blossomed

Let’s continue our Guide Mode story:

After writing down my principles as instructed, I clicked “continue,” moving to the next instruction in my program, and saw this:

This screenshot is Methodable in full form. We see:

1. An instruction that I wrote as part of my initial meta-plan, telling me to create a task list based on my principles

2. An embedded Methodable editor (just under the instruction) where I can complete the task (by writing a program) without leaving the page

3. Another editor showing me my guiding principles, which I wrote during the prior step

…In other words, a neatly packaged workspace, expressing a confluence of my prior intentions, guiding me to make incremental progress towards my goal of having a productive day. As I sat there in my cocoon of telic closure, I calmly specified my next actions. Here’s the same page, but after I finished writing the sub-program:

Note: I still don’t expect you to understand the language of these programs. If you’d like to understand it you can follow the Methodable program Learn how to create guides with the Methodable editor, which is a subprogram of the larger Meet Methodable program. Or check out Appendix B where Methodable syntax is briefly discussed.

After writing this program, I pressed “continue.” What happened next?

Well, I was still following my original meta-plan. And recall that the final step in that program was to “Have a day that fits my principles” - which is the exact program I just wrote! So, when I pressed “continue,” Guide Mode stitched me right into the first instruction of the program I had just described.

That first instruction I’d defined was to “Write down all of my TODOs”:

Meta-plan 2

Things are about to get crazy - because that second program I wrote? The one my meta-plan told me to write? …Was also a meta-plan.

As planned, writing down my principles had given me some clarity and nudged me towards understanding my next steps, but I was still far from where I wanted to be in terms of understanding my projects and goals. As before, I pulled the meta-planning arrow from my quiver of self-programming tricks, this time writing a more detailed version. My second meta-plan would bring me through a series of exercises and prompts that were specifically tailored to wrangle clarity from the herd of projects and to-dos that were yet stampeding across my mental plain (as it were).

To describe the exact shape of this more complex meta-plan to you, instead of providing the “English translation” of the program as I did before, I’ll just continue to describe my experience in Guide Mode, as that will demonstrate exactly what the program prescribed.

So let’s pick our story back up. Upon seeing the instruction “Write down all of my TODOs,” I collected tasks from a few locations, and in the end produced this result:

Finally, the to-do list overview I so desperately wished to have at the beginning of the day!

This was an overwhelming list of tasks, but luckily I had prepared for this situation when I wrote my second meta-plan. When I clicked “continue,” I saw:

…A prompt to write about my motivations with respect to each of these tasks. Again, the workspace engineering of my second programming session had paid off, providing me with a single page with the minimal user interface required for completion of the instruction. The page contains the instruction itself, the to-do list to be analyzed, the editor in which to write my analysis, and (not shown) the trusty “continue” button.

I completed my preordained free-write as follows:

A pattern: gradual plan structuring

Through this free-write exercise, I articulated a path forward, which was to focus on the pressing needs of searching for housing, buying health insurance, and planning a snow-camping trip. Secondarily I wished to make progress on a couple of projects that sparked joy, for example the writing of this very blog post (I was taking these screenshots throughout the day as I did my work).

At this point I was in the earlier stages of gradual plan structuring, a feature of some Methodable meta-plans. Gradual plan structuring is the process by which semi-formed ideas slowly become more and more concrete, until they are fully specified in a program. I said above that I had “articulated a path forward,” and I did so in an editor within Methodable, but I did not articulate it as a program - the words I wrote were not executable.

But that’s just as intended! My second meta-plan was built to support this intermediate stage of definition. Just as computer programmers write free-form memos and design documents before creating their rigid code, so too the human programmer benefits from a process of gradual structuring.

It just so happens that the human programmer, unlike the computer programmer, may have the benefit of operating within a meta-plan which can carefully guide them through that gradual structuring process. That was the case for me.

We’ll soon see the completion of this gradual plan structuring, but first we must take a meaningful detour through the land of positive self-talk.

Interspersing positive self-talk

I clicked “continue,” and here’s what I saw:

A reminder from myself to be grateful and to take it easy! How thoughtful. Thanks, prior Daniel.

I hope to convey how flexible these programs are, and how effectively they can integrate the softer elements of guidance - the gentle reminders, the positive affirmations, the fun, as you may have noticed in my free-write before…

At its best, an ad hoc Methodable session is a practice in being positive towards yourself - of telling the happiest, most productive story you can about what you’re doing, and then seeing that story play out.

We see this in my next instruction as well:

I try to make each Methodable instruction a gift to my future self, imbued with positive wishes. Like many of us, I sometimes struggle to have positive self-talk, and yet with Methodable I find it easy. By writing my programs intentionally, I can facilitate a dialogue with myself that is always caring and productive.

Completing the second meta-plan

Having briefly sat with the last two instructions, I moved on to the programming step of my second meta-plan:

This looks a bit like the programming task from my original meta-plan, but this time things were very different. I no longer felt scattered, and was finally ready to write a program that would take me to completion on my tasks for the day. That program looked as follows:

And now, having arrived here, you finally understand the meaning of the second program I wrote, as it described the exact steps that got me to this point: the writing of to-dos, the free-write on motivations, the positive affirmations, and this final planning task. That, plus a step titled “Finish processing my TODO list and continue the day with mindfulness and excitement”… a step which, of course, entails the completion of the third program displayed above. As happened at the end of our first meta-plan, this second meta-plan also seamlessly stitched my newly written program into my guided experience. And the blossoming continued.

Completing the session

You can guess the rest of the story, roughly speaking - I clicked “continue”, and I was brought to a new instruction. I completed that instruction, and I clicked “continue”. Sometimes the instruction was something from my to-do list. Sometimes it was a positive affirmation to read. Occasionally it was a multiple-choice question, but explaining those is out of scope for today’s post.

The final leg of my Methodable session was more straightforward. Having braved the intricacies of the meta-plans, I was left with simpler steps to follow, like this:

…and like this:

You’re looking at the prototypical Guide Mode experience: a single clear instruction, and a continue button. Just enough to make the next bit of progress you know you need to make.

I won’t bore you with rest of the screenshots, but for completeness, here are the rest of the instructions I received:

• Fill out the house’s interest form.

• See if there are other promising housing leads on Facebook. If so, reach out!

• Set a 40 minute time-box timer. While it’s running, see about switching my health insurance.

• (Read this): Hey, great job! You’ve done the important things for the day! Nice!

• Now clear your mind a bit. Take this great opportunity to do a guided meditation.

• Now, if you’d like, start planning your snow camping trip.

• You’re done for now! Want to do more? (y/n)

• Then stop here.

I followed those instructions, including the instruction to “stop here.” And then I left the cafe.

And it was a good day

You now know exactly what I did at that cafe. I organized my thoughts and to-dos, and did my highest priority tasks in a properly time-boxed way, and meditated. When all was done, I could say “I’ve done what I needed to do today and had a good time doing so,” which is just what I’d hoped - a far cry from the dopamine rut my “spidey senses” had warned me about that morning. And all the time I had a calm companion guiding me along: the voice of my prior intentions.

Why I’m excited about Methodable

Methodable is no longer under development, so I’m not advertising its usage, though I’m always happy to onboard the curious. But still, I’m very excited by the patterns of thinking that the tool enables. What I’ve shown you today is only a small sampling of the patterns I’ve seen, which are themselves a small sampling of the patterns that tools like Methodable can support. I think that if properly developed, such tools could benefit all kinds of goal-having entities, be they humans or machines. And while I don’t immediately plan to continue developing Methodable, I do hope to continue developing the ideas behind it in one form or another, and to keep it by my side as a trusty companion in times of uncertainty.

Epilogue

After messaging the landlord, I eventually moved into a house in the Capitol Hill neighborhood of Seattle. Here’s the view from my living room:

The following weekend, Olly and I had our snow-camping trip:

We were well-prepared.

As I anticipated in my free-write, “just by getting through this next period while remaining organized, [I found] my motivations to continue realigning in meaningful ways as new space opened up for each of my latent projects.”

One such project is the publishing of this blog post, which is now complete.

Appendix A: How I wrote my seed program

Some brief Q&A on why I started with the particular 3-step meta-plan that acted as my seed program. These are stories about the goings on within my mind, so take them with a grain of salt.

Q: You could have written any set of instructions for yourself to follow. Why did you choose these three steps?

A: The seasoned Methodabler (a term introduced in this very sentence) develops a sense for their own mental capacity and clarity of direction, and learns to write programs to match. This morning, I knew that whatever strand of willful energy existed amid the fog and chaos had exactly the strength to string together these three instructions. And yet, I knew (again from experience) that this small program was enough to nudge me towards meaningful progress.

Q: Why did you write this particular meta-plan which focused on principles?

A: Honestly, it just felt right - I could already sense some half-formed principles swimming around in my soup of thoughts, and I latched onto that as a starting point for my path towards orienting myself. Again, I was probably building off of my experience with similar meta-plans in the past.

Q: Why didn’t you just immediately write those principles down? Why start with the meta-plan?

A: Writing down principles is a creative writing task, and it takes work. I knew that during the task I might easily lose the thread, and losing the thread can send me meandering towards the attentional pitfalls that abound on my laptop. The meta-plan in Methodable does not prevent me from losing the thread, but the meta-plan makes it so that I can easily regain the thread of what I’m doing that day.

In sum, I wrote this meta-plan because it was simple enough for me to produce with ease, and powerful enough to bring me incrementally closer to the place I wanted to be.

Appendix B: The syntax of a meta-plan in Methodable

We can revisit my original meta-plan to understand how Methodable encodes meta-planning, and in the process learn more about Methodable’s “language”. In the screenshot below we’re zoomed in on the blocks for steps two and three of the meta-plan, along with their child blocks:

We see that step 2 contains a red “editor” block which attaches two editors as context/workspaces to its instruction. The first editor attached is a reference to step 3 of the program (this is indicated by the yellow superscript 2 next to its verb/emoji). So, in Guide Mode, when I was editing the program “Have a day that fits my principles,” I was really specifying sub-steps of the step immediately following the one I was presently executing. And since Guide Mode automatically presents the user with the most granular instruction available, when I clicked “continue” I was brought straight to the most granular instruction within the block “Have a day that fits my principles” - in other words, I was brought straight to the first step of the program I just wrote!

The pattern described above can be extended to conform to a wide variety of user needs, as is evidenced by the two differently-shaped meta-plans that I wrote in the course of this session.

Subscribe now

- 1 -

Once again, today I found myself at a cafe, staring at my drafted post about Methodable and feeling that it’s not ready to publish. Of course, I still had to publish something today - that’s the commitment. So I started thinking of other options. None of them were looking great and I kept chugging ahead with the draft, but I was not feeling optimistic.

The cafe closed at 8pm. I left, not quite knowing where my car was. I had parked far away. I wasn’t sure whether to go left or right. As I started walking, I took out my phone to call a friend. That call lasted about one minute before my phone died.

Before my phone died I had checked Google maps, to no avail. And after my phone died, I felt the impulse to check my phone again, and again, in case I might screw my eyes up at that small map and figure out some new fact about the world. But each time, I remembered that my phone was dead, and some part of my brain loosened its grip. Eventually I stopped checking.

There was a moment where I stopped walking, and just thought, “okay, I’m here.” I’m here on this street. I know where the cafe is - not on my phone, but in space. it’s over there. I’m here and the cafe’s over there and the car is in some 5-block radius from the cafe, and I’m walking the edge of that radius. And I don’t know how long it will take to find the car.

And, strange to say, it was a good feeling. I suddenly had a task that required my faculties of sight, of walking, of navigation. There was nothing to do but glide through the streets of Seattle, searching for that car and refining my strategy. How pleasant.

- 2 -

One time I was at some kind of event, and some kind of person asked me some kind of question. Clearly I don’t remember many details of that story, but I do remember that I said to a large room of people, “I like running fast down hills with uneven terrain.” The presenter said, “Really? I also like running on rocks! So does this guy over here.”

Okay, I remember now, it was a “Tools for thought” event, and the presenter was doing a live demo of a super-connecting tool for networking people together with similar interests. So he put me down in his database as “(Daniel Sosebee) -> (likes) -> (running on rocks)”, and lo and behold, up popped a visual representation of the connection between me and my newly discovered soulmates.

I was shocked, but should I have been? Maybe this is a more common interest than you’d expect. Maybe it’s innately joyful.

I like running fast on uneven terrain because it requires my full attention. One time I was on road trip in Wyoming, and I pulled off to summit a random mountain I’d found on AllTrails. And I got to the top after traversing a long and exposed ridge, only for the weather to get stormy. The irony is, unlike this evening, my phone had battery and I had cell service up there, so I could google what posture to use during a lightning storm. Well, in the end I decided to make a run for it, but the ridge I took was much too long, and so I booked it straight down the mountain.

I feel guilty describing how much fun it was. Besides the danger of lightning, I could have slipped and seriously injured myself. But in that moment everything coalesced into a single, perfect challenge. My entire experience was just this tunnel of present. Each iota of brain power or body power at my disposal was immediately and continuously dispatched towards the singular goal of getting myself down the mountain, safely, as quickly as possible.

I liked it so much I made a drawing about it:

- 3 -

Well, that drawing isn’t quite realistic - I was wearing shoes at the time. But it gets the feeling across. And in fact, this drawing holds special significance for me, since I drew it at the height of my illness with mono. The drawing was an escape. I wished to draw the kind of exhilarating experience I was so removed from in my weakness.

Today I still struggle with aftereffects of that illness. I’ve lamented recently that I don’t have enough “flow” in my life. I take it easy in order to not overexert myself, but that just gives me more time to spin my mental wheels. Less fun than “going for it.”

But this blog is a good thing, because tonight it is compelling me to “go for it.” Because after I found my car, I drove home straightaway and opened up my computer, and tried again to complete the Methodable draft, and when I failed I had to adapt - I couldn’t give up.

And I started thinking of other things I might write. I started a piece called “Good Sleep is Really Important,” but I didn’t have much to add other than what the title already said. And then I started writing this one.

And now it’s 11:22pm, 38 minutes of Wednesday left, and I see that tunnel of time ahead of me. Another perfect task. 38 minutes to get down the mountain before the lightning strikes.

Subscribe now

Welcome new readers! I appreciate your kind responses to my end of 2025 update, and am excited to begin this year of writing!

Honestly, I was hoping to start off with a big splash, and I drafted a lengthy post about a recent Methodable session I undertook1, however, that post is going so well that I actually want to “cook it a bit more”… (I’m hoping this doesn’t become a pattern…)

But fear not, I maintain my explicit commitment to filling your inbox, along with my implicit commitment to not wasting your time, so I have selected for you a short story from my past writings titled “The Origins of LIFE.”

I believe this is a fitting first post as it acts as a backstory to many of my current projects, including not only Methodable, but also my personal routines and writing systems.

Be warned: the story is brief, and quite incomplete, but that’s actually the point - it is a story about how a small and incomplete thing can blossom into something larger, through the power of reflective self-improvement - a theme which is core to many of my interests.

Enjoy, and see you next week,

Daniel

The Origins of LIFE

Towards the end of high school I became concerned that I wasn’t living my life well and didn’t even have a methodology for living a good life. I figured that I could solve this quandary by producing a system that, when followed exactly, would cause me to eventually lead the best life I could. So I got to it.

For some reason I called the system “LIFE”. The acronym didn’t stand for anything. Here’s the first version:

LIFE program v1 description

Complete the following activities without fail.

Daily: Write in your journal about how your day went and any thoughts you have about how to live your life better.

Weekly: Review last week’s journal entries, then update this reflection program in order to improve this program’s ability to achieve its goal: to help you lead a good life.

…And that’s it

That was the whole program. A minimal strange loop that seeks to improve itself with time. It wasn’t much, but I figured it was enough to pull itself up by its bootstraps. If I could follow this system, in time it would grow to become an ideal guide for me.

So I got started, and 8 years later the LIFE system is still going. It and I have evolved a ton, and I hope to write about that coevolution soon.

Daniel Sosebee, March 2024

Subscribe now

Ok, but first, I will see if I can fill you in on my last year, in a desperate attempt at continuity and closure. This year was a tough one, but meaningful nonetheless.

My 2025

Last you heard from me, I was in New York, about to go back to Recurse Center, and had plans to focus on some exciting personal research projects related to AI self-reflection. And I was going to blog about it! But then I didn’t... what happened?

First of all, thank you to all of my wonderful blog readers who checked in on me... your kind words mean the world to me. Here’s the full story:

Winter: Health Happened

Right after my last post, I was struck with illness! Specifically - mono and strep (at least). And then, when things started looking up again, the flu. Some have since wondered whether it was a poor choice for me to live in a Brooklyn co-living house that doubled as an underground daycare operation for some of the most well-networked babies in the Tri-State Area. Still, the credit-assignment problem remains a challenge (as will be a theme of this year for me).

Anyhow, I was quite sick, and then I didn’t get better.

I think most people have an intuitive sense of what trajectory an illness is supposed to take - you rapidly feel worse, until you reach some minimum, and then you slowly get better. And it is very disconcerting when something different happens, like the following that happened to me:

The above chart illustrates how things felt at the beginning of my time in New York. In full scope of the mono and the flu and so on, things actually looked more complicated, though no less disconcerting:

The three-month period depicted above was very challenging, and it’s daunting to try and do it justice in writing. But I have planned a post about this, “The Phenomenology of Mononucleosis”, since one of my goals for this year is to write more about my health journey.

…And, Life Happened Too

The crazy thing is, in the cracks between the periods of illness described above, I was having an amazing time. I found an awesome community of “friendly, ambitious nerds” via Fractal NYC, hosted dinners at my house, did yoga at the climbing gym and walked to Recurse Center every day, where I was learning a ton from my peers and working on projects ranging from installing a new server in their compute cluster to collecting activations from an LLM for mechanistic interpretability research.

... which really only made things more difficult when my health stopped cooperating. Having lived a largely nomadic life ever since I’d graduated from college, I was looking forward to putting some roots down, and Brooklyn seemed like a great place, but my health was stagnating at levels that did not allow me to make use of my new environment, and it was looking like a long, cold New York winter and spring, so I packed up and made my way back to the Bay Area to live with my parents until I got better1.

Spring to Summer: Complicated Illnesses are Complicated

I am very grateful to have such a supportive family and such a comfortable place to land as Oakland, California. During my Oakland period I was largely focused on my health - reading everything I could on related illnesses and trying to build the right routines. I also continued my part-time software consulting work and dove into my second piano album.

And, overall, things slowly got better. But recovery was very non-linear, and the question of when and how I might fully recover continued to loom large.

Wondering Whether Work Would Work

At some point, after a particularly positive period of physical prosperity, I decided that it was time to “move forward” and attempt to do hard things once more, and that perhaps doing so was a necessary step in my recovery (you’ll have all sorts of ideas when your health gets weird). And so I kicked off a job search, which quickly gained a lot of traction. Maybe too much traction, thanks to the excellent career services at Recurse Center...

I interviewed for a dozen roles and ended up with a few offers from companies I was truly excited about, each in different ways. I even worked with one company for two months in a trial period that went quite well by all accounts. And yet, the whole time I had a persistent doubt about whether I was making the right move.

Everything rode on the question of “am I getting healthier”, and I was extremely sensitive to the slightest fluctuations in the dial that swung between “yes I’m improving” and “no I’m not”. Extrapolated forward, that dial pointed between one future in which I regained my health, my physical activities and my social life, all while building a career at an interesting company… and a second future where all aspects of my life slowly deteriorated until even my job was too much to handle, setting back my recovery by months at best, and at worst, indefinitely.

With such a steep downside, in hindsight it’s surprising to me that I didn’t cut my losses earlier. But it was also demoralizing for me to consider sitting around indefinitely - there is always a part of me that wants to push the boundaries, in case I find them to yield.

But this time around, fate made the choice for me. The same week that I intended to sign a full-time offer, my body failed again in a full on “crash”. Everything was weak, I couldn’t even do my five minutes of light morning yoga, and trying to write code felt like grinding my brain against a wall. (It’s wild how, in these states, the body is so fiercely opinionated about what to spend energy on - but that’s a topic for another time.)

After conversations with my counsel of friends, I called my employer-to-be and postponed my joining indefinitely. And once again was floating into the unknown.

Fall: Getting my Mojo Back?

Not quite knowing what to do with myself, I put all my energy into recording my piano album. And as that went on, I started to piece together a different vision for my recovery - one in which I went straight for the things that brought me the most joy and excitement… though I hadn’t understood things exactly in those terms yet.

But I had some vague notions of completing the album, and traveling and visiting friends, and learning about math and AI, and writing publicly, and reconnecting to my personal systems and the other creative projects in my life, including the very projects I told you I was going to focus on last year!

And as a first stop, I packed my car and set off for Seattle for a trip of unknown duration. Originally I just meant to visit friends, and yet, ~2.5 months later, I’m still here. And, though my health continued to be rocky...

... overall things have been very good! Indeed I’ve enjoyed hanging with my friends here, and I’ve gone on a couple adventures, and worked on projects that are meaningful to me, including my board game Sneaky Town (you can read the latest Sneaky Town update here, and there’s more progress updates to come).

My life has a lot of richness right now. I have engineered, and/or been blessed with, many projects, activities and relationships to look forward to, and these help me tolerate the troughs. Though my full health trajectory remains unknown, I no longer worry that a meaningful life is out of reach.

To be clear, I am not claiming any sort of victory. I am still quite in the midst of things, and am well aware that my circumstances could change on a dime. “We’ll see”, replied the farmer. But, I wished to bring you up to date, and here’s where things are right now. Not bad.

Hello 2026

I have a feeling that 2026 will be a good year. And I do not wish for you to hear about it in 12 months. I wish to write to you more often.

“But you said that last year”

... yes, but this year I have a specific commitment - I will send out a new blog post every Wednesday. That’s 52 Wednesdays, 53 if you count today. In fact I’m finishing this here draft on New Year’s Eve. How’s that for commitment?

This blog is now called “Daniel Sosebee” and has moved to blog.danielsosebee.com.

I already have many posts and ideas queued up, on topics such as: health, personal systems, and AI. I’ll use the blog to get my thoughts out, to share progress on my projects, and to inspire me to learn more on the topics that interest me.

And I hope you have a wonderful 2026!

…Lastly, if you got this far, you get to hear a single from the upcoming album. It’s called Eternal, because, to me, the song seems to emerge from an endless and beginningless place (dang - that would be a good album name 🤔 …). Listen here.

Until next week and Happy New Years to all,
Daniel

Subscribe now

Dear readers,

I am excited to be back on the blog for the first time since September 2023. In this post I hope to catch you up on the software projects I’ve undertaken in the last two years, and to introduce my upcoming research endeavors.

TLDR for the time-sensitive human-programming fan: Human programming (the research area) is back - I'll continue to build programmatic reflection and planning systems, but now the target user will be LLMs, not humans. In tandem I'm excited to explore the frontiers of related research areas in neuro-symbolic AI, and look forward to posting about all of the above, right here on this blog.

Now, let’s return to late 2022…

InstructionKit

After publishing the human-programming tool Methodable, I teamed up with my friend Chris to build a more marketable version called InstructionKit.

What was our vision? While Methodable helped with self-guidance for personal productivity, InstructionKit focused instead on guiding others, aiming to be a simple platform on which businesses could create instructional and data-collections flows. This demo, built in the InstructionKit playground, shows the initial rich-text-editor/flowchart authoring experience. And here’s a deployed InstructionKit guide in the wild, helping people choose the right tires for their newly lifted Prius!

After building the v1 shown above, we pivoted towards a developer-focused product and built various domain-specific languages to facilitate the creation of interactive guides. My favorite was "JFX", a variant of JSX that carried data not just down but all the way around the UI component tree, allowing the developer to more easily mix sequential flows with JSX's regular markup and logic. Or to put it visually:

Unfortunately I never got to publish JFX, and eventually we dropped InstructionKit since we each had promising part-time engagements which eventually outweighed our excitement for the startup…

The Digital Abacus

Last I blogged, I was working on my first consulting engagement, The Digital Abacus, which was another fun opportunity for me to build a spatial-programming web tool. I enjoyed that my entire involvement was via pair-programming video calls, so my collaborators and I could be creative together and iterate on our ideas quickly.

Galileo by the Josh Bersin Company

Around March 2023, while I was still working on InstructionKit and The Digital Abacus, I found myself at Movement Athletics of Pasco, Washington for a rollout of InstructionKit as a tool for employee SOPs (long story). I got a call from Josh Bersin (of The Josh Bersin Company) who was hoping to create an AI system to help people access his company's extensive HR research corpus.

In a few days I put together a retrieval-augmented generation (RAG) app that parsed, indexed and queried the company's PDFs, and we soon took the product into beta testing. As this was the early days of RAG I had to figure out a lot on my own, and was especially proud of the query-routing system I built which could selectively search against document metadata or document content, allowing the system to serve as both an advisor and a librarian.

Eventually I helped The Josh Bersin Company transition this product (now called Galileo) onto Sana Labs’ AI platform. After the transition I continued working with the company to build internal content systems and advise on technical strategy.

AI agents and spreadsheets at Sana Labs

The team at Sana were impressed by my work, and in November 2023 hired me to develop experimental additions to their enterprise AI platform. First I built their transactional multi-step AI agent system, allowing Sana’s users to do things like update Salesforce records based on a meeting, query SQL databases with natural language, and generate Google docs from a conversation. I presented on this system's design at the OpenAI DevDay London conference in a talk titled Architecting Multi-Talented General Agents:

Next I built Sana's "Sheets" feature: a spreadsheet for repeatable LLM workflows, and an AI agent to configure the spreadsheet for you. The Sheets project was also a zero-to-launch endeavor, and is now being used to various effects by Sana's enterprise customers (e.g., to extract data from pitch decks). I particularly enjoyed designing the engine that powers the sheet, which stores the computational state of the spreadsheet as a single immutable data structure and re-calculates cells automatically as upstream values change.

Transitioning towards exploration

Each of the consulting engagements described above has been wonderful for me in its own way. I got to pour my passion into designing and building ambitious web tools and AI products, and did so in a variety of collaborative environments: a non-profit research lab, a respected HR advisory firm, and a fast-paced AI startup. Though much of my work was remote, my clients brought me to conferences in SF, LA, and London, and at times I got to work alongside wonderful folks in Stockholm and New York. Along the way I set up my LLC Harmonic Software and learned to manage my contracts with increasing professionalism, creating a successful independent business.

I feel deep gratitude for these experiences and for my clients who have continuously put their trust in me. At the same time, managing projects across multiple companies has taken up a lot of energy, and in recent months I've felt a desire to open up space for exploration in my career. To that effect, I have substantially reduced my consulting commitments, moved to New York, and will be joining the community at Recurse Center once more, this time in-person, for a three-month retreat in which I'll pursue my AI passion projects full-time.

A preliminary research focus for 2025: self-modifying programs

I am excited to pursue projects that combine AI research with product development. In the process I aim to develop a more holistic understanding of the theory underlying both machine learning and symbolic AI, including the landscape of AI alignment research.

As a concrete starting point, I will continue work on an ongoing project which extends the human-programming ideas to the realm of AI agents. In particular, I aim to build a general-purpose AI agent which operates as a self-modifying collection of programs. This strikes me as a very natural way to conceive of an artificial mind, and yet I haven't come across any compelling efforts to do so - the closest I've seen is in the STOP paper (Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation), which describes a strictly controlled experiment (which is still very interesting), rather than the kind of messy engineering effort which I imagine would be necessary to bootstrap the kind of system I have in mind. I am excited to learn, though, of other related projects and papers.

Self-directives and intention to blog

I am open to my projects going in a variety of directions, and am excited to follow my passions wherever they lead. Most importantly, I am excited to operate under Recurse Center's self-directives: work at the edge of your abilities, build your volitional muscles, and learn generously. In particular, learn generously will be relevant to this blog: regardless what I end up producing, I hope to share about each interesting part of the journey with you. I would be honored if you learn generously along with me by engaging with my posts and letting me know your thoughts along the way. This blog will be one of many ways in which I hope to put myself out there and connect with people, which is perhaps the most concise summary of my goals for the new year.

I hope you have a wonderful 2025, and I look forward to seeing you next time.

Daniel

Subscribe now

Table of Contents

1. The Automatic Constraint Solver

2. Frontend Architecture ← you are here

3. …

Introduction

In part one of the series I described the theory underlying the Digital Abacus Tool, focusing on our data model: the constraint graph.

Now in part two I’ll discuss a more practical aspect of the project: the tool’s frontend architecture and our approach to state management and persistence.

I’ll begin chronologically with the project requirements, jumping back in time to the beginning of my involvement.

Requirements

When I joined the project, the team had already produced a few prototypes using p5, and was looking to combine them into a single web app with shared state.

One prototype was a flowchart UI for defining mathematical constructions:

The other was a 2-D plot UI for exploring complex values:

The team was looking to create a unified web application that combined both UIs and bound them to a shared state, so that users could build and explore their constructions across both interfaces simultaneously.

In terms of requirements, the Flowchart UI, Plot UI and Solver would all need to read from and write to the constraint graph simultaneously. We also needed to find a way to save and load entire constraint graphs, including their internal numeric values. All of this would be deployed together as a fast and beautiful web app.

Choosing boring tools

To optimize for stability and maintainability, we chose the current most boring and popular web-framework combo for interactive apps: React + NextJS. Switching to React also allowed us to use the React Flow library, an excellent library for creating interactive flowcharts. React Flow is a mature library (used by the likes of Typeform) that has good performance and enables many intuitive user interactions that would be a massive time cost to implement otherwise. It’s also the library I chose for InstructionKit’s flowchart editor, so I had experience with its API.

Spanning state between React and p5 via proxies

Once we knew we were using React and rewriting the Flowchart UI with React Flow, we had to decide how to integrate the Plot UI into the app. We considered rewriting that UI in React as well, but I did some research and found a library for embedding p5 into React which would allow us to reuse the existing Plot UI and therefore iterate more quickly.

However, getting the p5 code to share state with the rest of the application was a challenge, since p5 uses global variables to store state. My solution was to make the existing global state variable a Valtio proxy, allowing the React parts of the application to subscribe to changes in that global variable (see code).

In the process I migrated all of the constraint-solver class systems and the Plot UI to use ES6 module imports and typescript. It was a big commit but AI code-completion made the migration relatively painless.

Saving and Loading Constructions to the User’s Filesystem

We evaluated a few possibilities for persisting constructions. One option was to set up a backend and a database, but that would be more work than setting up a local-first storage option. We discussed three storage options:

• Using browser localstorage API

• Using URL encoding

• Saving and loading from user’s filesystem

At first I set up URL encoding, which is great for allowing people to quickly share the entire state of their application with each other by just pasting their current URL. However, we started running into problems with browser compatibility and URL length, so I switched to enabling save-to/load-from the user’s filesystem.

Saving to the user’s filesystem is great because the user’s filesystem becomes an extension of your product UI; the user can save files, make folders and backups and versions, send them over email, etc., all of which are affordances that I can skip over as a developer (which is not true of the browser-localstorage approach).

I was able to set this up quickly since I built something similar for my open-source human-programming tool Methodable.

I did need to do some extra work however, since persisting constructions required me to set up serialization for our class-based application state.

Serializing JavaScript classes

I generally recommend using plain JavaScript objects for application state rather than classes. There are a few reasons I prefer that pattern, one of which is that serializing and deserializing plain JavaScript objects is as easy as JSON.stringify() and JSON.parse(). However, I joined this project when the class-based model system was already pretty mature, so instead I set up serializers and deserializers for all of the classes.

I created Zod schemas for each class, such that deserialized graphs could be parsed and validated before being loaded into the application state (example of a schema). Then, I wrote a serialize method for each class, such that the entire graph could be serialized (example of a serialize method).

Note: We serialize everything, including the values within each Vertex, because the state of values are path-dependent. Consider the following:

We’ve created a system that solves `x^2 = 4`, and has reached the equilibrium where x = -2. We can actually reach the other equilibrium where x = 2 by winding our free variable (the product) around the origin of the complex plane and returning it to its current value, 4. So, the value of bound variables is dependent not only on the current values of free variables, but also on the path those free variables took to arrive at their current value. For this reason, we serialize everything!

To-do: clean up the deserialization/instantiation flow

Due to the nuances and unevenness of the way state is stored in the graph’s class hierarchies, deserialization is currently done in one gigantic function. In the future, I would standardize all class constructors to take in a serialized state as their single argument. With that refactor in place, we could gradually deserialize a graph using each class’s constructor, rather than having to do it all in a single messy function.

Up Next

I hope you enjoyed learning about the tooling and technical architecture of the Digital Abacus Tool. Feel free to subscribe for more on the Digital Abacus, and other updates from Human-Programming land.

Subscribe now

Best,

Daniel Sosebee

Introduction

In February of 2023, I was holed up in San Bruno, CA, deep in development of a flowchart-powered developer tool called InstructionKit.

My cofounder Chris and I were looking to bootstrap, so we needed side gigs. Chris was already working part-time with Hack Club to produce his amazing game SineRider (check it out), and would soon connect me with Paul Dancstep, who was looking for help with his project called the Digital Abacus.

As Paul explained, he and a team of mathematicians were building a tool for solving math problems, to be used by students and professionals alike. Something that would look like this:

There would be two interfaces: on the left, a flowchart with nodes and edges representing operators and constraints, and on the right, a plot showing the live-updating real and imaginary coordinates of every input-, intermediate-, and output-value in the system. The user could directly drag and manipulate values from either view, so they could construct reusable interactive tools to help them model real-world systems (see this lecture for some conceptual background).

This project sounded like a perfect match for me given my experience building InstructionKit, so I joined and spent a fantastic three months working with the team to produce the version shown above (here is a demo and here is the source code).

I enjoyed this project so much that figured I should write about the tool’s unique technical design and the decisions that went into it. Eventually I decided to split things into a multi-part series, with the following sections:

Table of Contents

1. The Automatic Constraint Solver ← you are here

2. Frontend Architecture

3. …

…And you’re coming up on part one. Enjoy!

Pt. 1: The Automatic Constraint Solver

First I’ll describe the experience of building and interacting with a construction using the Digital Abacus Tool, then I’ll talk about the underlying state representation of a construction, and finally how the tool solves for dependent values.

An example construction: Euler’s Identity

Say we want to model and explore Euler’s identity using our tool:

To do so, we drag the constants, e, pi, and i into the flowchart workspace. We connect pi and i to the input terminals of a Multiplier to yield the product i * pi. Finally we connect e and i * pi to the input terminals of an Exponentiator to yield the result, -1. Like so:

What makes this UI special?

Merely solving e^(i*pi) is not all that interesting; Google does a good enough job at that. What makes our tool here special is that we can see our values interacting in the complex plane. And, more importantly, we can drag our input values around, watching dependent values update instantly and continuously. By playing with the system, the user can understand the mechanics underlying the equation. Instead of being a single-shot calculation, our equation has become an explorable explanation.

We can even reverse dependencies in the construction to make the output a free variable and solve for one of the inputs, all with a couple of clicks (more on this soon).

The shape of the constraint graph

So how does this work under the hood? First, we need to store all of the values and constraints within the construction.

We do so in a graph data structure (called the RelGraph in the code). The RelGraph (short for relation-graph) is the single source of truth for all information about a particular model, including the shape of a model (what components it has in the flowchart) as well as the state of values within a model.

Vertices and Edges

The RelGraph contains Vertices and Edges. A Vertex (code) represents a numerical value with real and imaginary parts. With respect to the system as a whole, a Vertex could be an input, output, or intermediate value.

An Edge (code) represents a constraint between two or more values. For example, connecting two values by a wire in the flowchart UI corresponds to an equality constraint Edge in the RelGraph. Continuing our example, let’s see how Vertices and Edges work together:

A concrete example: the RelGraph for Euler’s Identity

The image below shows the RelGraph created for our construction of Euler’s Identity. Vertices/values are blue (and are given arbitrary uppercase letters as IDs for the sake of this diagram), while Edges/constraints are green. As you can see, a RelGraph is a hypergraph where Edges can connect multiple Vertices. The messy image further below illustrates how this RelGraph corresponds to the nodes and wires in the flowchart UI.

Note that our construction has some extra Vertices at the incoming and outgoing terminals of our Multiplier and Exponentiator. That’s because these operators come with their own input and output Vertices. Wiring up two values does not merge them, rather it creates an additional equality constraint between them.

Operators are reversible, so users can solve for different variables

An important affordance of the system is that every single operator can run in reverse; you can turn what used to be an output into an input. For example, you can unlock the sum value below an Adder, give up control of one of the addends, and suddenly you can run the Adder in reverse, effectively as a Subtractor.

Reversing multiple operators at a time

The UI makes it easy to reverse multiple operators at once; the user can lock and unlock disparate Vertices, and the tool will find a path of Edges (operators and equality-constraints) between them, reversing all of those edges simultaneously.

This allows the user to quickly solve for different variables in a system. For example, a mechanical engineer who is modeling pressure with a headset strap might wonder “if I set pressure and head size to these constants, what is the resulting optimal strap length?” Later, once a strap length is selected, they might free up the head-size variable, allowing them to ask “given this strap length, what is the smallest head size that yields at least some minimum amount of pressure?”

How the RelGraph reaches equilibrium

The screenshots and renderings above show a RelGraph in equilibrium, but the RelGraph is not always in equilibrium. When you first connect an operator to some values, or when you drag a value around, the system will be in a temporary disequilibrium, then will iteratively march towards a solution.

This march happens because the RelGraph is scheduled to regularly update its values (code). These updates are delegated to the RelGraph’s Edges; each edge updates its dependent Vertex’s value in an attempt to bring the Edge’s constraint closer to being satisfied. For example, an equality constraint spanning from a 4 to a 3 might update the 3 value to a 3.02 in a single update cycle, then on to 3.04 and 3.06 and so on, such that equality between the two values is closer to being satisfied.

Depending on the speed and granularity of updates that you’ve set, you can see this march in real time as the system solves itself.

Reaching equilibrium can fail

Since you can create cyclic constructions where a value indirectly relies on itself, not every construction is guaranteed to reach equilibrium. Some systems will result in values that spin around in circles, or that gradually spiral towards equilibrium, or that run off towards infinity.

Representing composite operations

So far we’ve covered the basics of the constraint solver; now on to my favorite part: composite operations.

The Digital Abacus Tool started with only four primitive operators: Adder, Multiplier, Exponentiator, and Conjugator. These building blocks can be used to make basically any mathematical function [citation needed], but we also wanted to give the user a wider menu of operators to work with. Rather than implement update-functions for every single operator we wanted, we decided to support Composite Operations, meaning that a single node in the flowchart could encapsulate multiple primitive operations in the RelGraph. This would let us add things like logarithms and trig functions.

We discussed two ways to enable composites: One option was to add multiple Edges and Vertices to the main RelGraph graph per composite operation. Another option was for each composite operation to contain its own subgraph. Each subgraph would itself be a RelGraph, and could contain any of the primitive operators listed above, or could recursively contain more subgraphs (spoiler, we chose this approach).

The subgraph pattern for composite operations

Here’s how subgraph-based composite operations work: suppose we have a Subtractor within our main RelGraph, with input values 5 and 3. When it’s time for the Subtractor to update, that Subtractor pulls the 5 and the 3 down from the main RelGraph into its subgraph, then runs its subgraph’s update function (which contains a reversed Adder), and finally pushes the result, 2, back up into the main graph. Here’s the code that runs those nested updates.

We chose the subgraph approach for a few reasons. First of all, it gave us a nice pattern to use for creating composites: We could create a composite in the UI, then serialize it and store it as a configuration file associated with that particular composite’s sidebar menu item (example configuration). This serialized configuration represents the initial equilibrium state of the composite operation’s subgraph, and can be deserialized to create a fresh copy of the composite operation whenever a user drags a new composite node into the flowchart.

The subgraph pattern also simplifies batch operations. Deleting a composite is easy: since you just delete its subgraph, you don’t have to go searching the main RelGraph for related Vertices and Edges.

Coming soon: custom composite operations

Some small updates to the UI could allow users to build and edit their own composite operations using the exact same flowchart and plot UIs, giving users a personal component library of math functions relevant to their work. This would be relatively simple, since the RelGraph powering the entire UI could easily be swapped out for the scoped RelGraph that defines any given composite.

This could look similar to Cuttle’s component system, shown below, where user-defined components are listed in the left sidebar and can be dragged into the current work area.

Up Next

Thank you for reading. If you haven’t already, please subscribe below for future updates, including the upcoming post: Building the Digital Abacus pt. 2: Reactivity & Persistence.

Subscribe now

P.S. I worked on this project in my capacity as a product development contractor and am open to new clients. Also the Digital Abacus is looking for funding to continue pushing the boundaries of free & open-source math tools. Feel free to reach out for either.

Best,

Daniel Sosebee