Personality Basins

Personality basins are the mental model that I use to reason about humans within their environment. They are an elucidating way to think about many concepts: from modelling why people are they way they are, how they change over time, how mental illnesses and addiction function along with how we should look for their cures, and how the attention economy optimizes itself to consume all of your free time.

What is personality?

Your personality is formed by a process conceptually similar to RLHF. You are first born with a set of traits in a given environment. After this, you perform many interactions with your environment. If an interaction goes well, you’re likely to do it more often, and if it goes poorly, you’ll probably do less of it.

See the learning agent? That’s You!
If your interaction with this post goes well, you’re likely to read more of them later.

If you were born tall and with a commanding voice you might find that you get what you want by confidently demanding it, and this will help to result in a confident personality. If you attempt this strategy as someone born small with a soft voice, it will probably have weaker results and encourage you to try something else out instead. Obviously some traits are more genetic, and thus inherent, than others, but that is not the scope of this post as even highly-heritable traits will result in a large distribution of outcomes.

Periods of high social and environmental entropy during adolescence are the most formative because you will learn the most information about which actions perform well in your environment and which don’t (of course, our meta-learning algorithm knows this, and this is why you have higher neuroplasticity and thus a higher learning rate and more energy during this period. It’s time to learn how to succeed in your newfound environment!)

Your personality basin

As you go about your life, you will continue to modify your personality in response to your environment, and eventually you will end up in something that resembles a basin. Maybe you were born tall and attractive and then this led you to engage in a lot of athletic activities and socialization, and at the end of all of the positive feedback you have ended up with a jock personality that goes on to become a professional football player.

This is a landscape of personalities. The black line is your personality over time, and the last point is the person you currently are. Just like in machine learning, the way that you’ve progressed as a person has been by trying out many things and then doing more of the things that worked well.

If instead you grew up scrawny yet intelligent you might have found things go well for you when you adopt a more quiet persona and focus on solving technical problems in programming or mathematics, perhaps eventually leading to a career as a software engineer or academic. Just like training a model in machine learning, the general gist is that you will try out a lot of things and then do more of the things that went well.

The above image is of a loss landscape in machine learning. Since we are discussing personality, all of the points on the landscape represent different personalities you could have, with the lower points being personalities which are more successful. The personality basin that you find yourself in solidifies over time as you find out who you are and choose your friend group, career path, social and aesthetic preferences, and more.

Most personality changes are unconscious

Most of your movement within personality-space happens outside of your conscious awareness. Although there are many times in life you’ll consciously decide to act in a certain way, this is the exception, not the norm. Your brain is always making millions of gradient updates a day based on what is and isn’t going well and often the most you can do is try to be as observant as possible. This is why techniques like nonviolent communication, dialectical behavior therapy, and mindfulness have observation and introspection as a core facet, because it’s something that you have to consciously practice to become good at rather than something you’re born with.

Most addictive behaviors start without us noticing what is happening until we are sufficiently addicted such that the habit is hard to break. Relatedly, if you introspect on many seemingly-innate preferences you will often notice some of the environmental and social gradients that have helped shape them. An interesting thought experiment you can perform on yourself is to pick a random personality trait that you have and try to answer the questions “why am I like this? could I imagine a version of myself that is not like this, and if so, what happened differently to them?”

Many people think their music and fashion preferences are innate to them and are solely based off of how the music sounds and how the outfits look. But if their most hated political party (or often in the case of adolescents, their parents) adopted the same aesthetic preferences, you can imagine they might start to literally like them less!

Your conscious experience of a stimuli is not dictated by a single-variable function f(stimuli), but rather f(stimuli, personality, environment), at least for broad definitions of ‘personality’ and ‘environment’. If you have a favorite song that your friend thinks sounds terrible, this is because they are literally experiencing it differently from you due to the latter two variables given to this function. They don’t think the thing that you hear sounds terrible, they think the thing that they hear sounds terrible, and it is probably very dissimilar from what you hear. For more information on this line of thought I’d suggest reading about signaling theory and checking out The Elephant in the Brain by Robin Hanson and Kevin Simler.

How do you know if you’re in the right basin?

If you’re reading this you probably have a vague idea of what type of personality basin you’re currently in which you can recall by asking yourself the question “What type of person am I?” But an important question remains: how can you find out if this is the right basin to be in?

A simple answer would be that you could try out other basins to see how they feel. Maybe you’re having a great life as a devops programmer, but you could try to become an artist or a woodworker or a stay-at home parent and see how that fares for you.

The reason why this is hard is that the optimal personality for this basin is not immediately accessible to you – to truly test optimality you will need to go through a full RLHF process. If you want to know how good of a life you’d have as a professional pianist, you will have to practice the instrument for a decade to find out.

You may wonder if you could simply try your hand at the piano for a month or two and see how it goes, and of course you can do this too. Your time (and your meta-learning algorithm’s number of epochs and learning rate) is limited, and it’s reasonable to make the trade-off of sacrificing depth-first search in favor of more breadth-first search.

As you progress in life, you will usually perform less exploration for new personalities and more exploiting with your developed personality

Usually this breadth-first search of trying out many different and creative strategies for life (prioritizing exploration over exploitation) automatically happens during your adolescence, but one of the magic things about the modern world is that there are so many societies, cultures, countries, and fields of work one can move into, and for each different environment could exist a slightly-different-you which finds their own distinct personality that maximizes success. Had you been born as a hunter gatherer or within the roman empire or in ancient china, you’d probably have ended up quite different as a person. Similarly, if you decide to move countries or communities or careers, the optimal-you-for-your-environment will change a lot too.

Personality-space is adversarial

One interesting thing to note about personality-space is that it is adversarial. Rather than a static training set to iterate through, your training data consists of other RL agents, many of which are other people, and all of whom want different things from you.

This is what leads to the concept of Personality Capture. Personality capture is when your environment RLHFs you into becoming a personality that benefits other agents rather than yourself.

If a school bully threatens to hurt you unless you do their homework for them, they are attempting to modify your RLHF process so that it results in an agent which is beneficial to them, hopefully resulting in someone who will always give in to their demands.

Those familiar with high school psychology will find high similarity with this concept and that of classical and operant conditioning as well as concept of a Skinner box. The attempted addition to these concepts here is that of modelling the personality as a reinforcement learning process and changes in personality as gradient updates, which then allow us to view personality-space as a high-dimensional area which will give us some interesting tools to think with. As the saying goes, all models are wrong, but some are useful.

Luckily for humans there exist many symbiotic equilibria where multiple parties can find mutually-beneficial feedback loops within the epochs of personality-space. A mother loves her child because it provides her with the reward of feeling good which encourages further love. In response the child gets food, shelter, and care, which further encourages them to continue the relationship.

Personality Capture

It’s easy to become susceptible to various forms of personality capture when your environment changes. When asked why he isn’t on Twitter, Dario Amodei, CEO of Anthropic, responds to Dwarkesh Patel with:

I’ve just seen cases with a number of people I’ve worked with, where attaching your incentives very strongly to the approval or cheering of a crowd can destroy your mind, and in some cases, it can destroy your soul.

I’ve deliberately tried to be a little bit low profile because I want to defend my ability to think about things intellectually in a way that’s different from other people and isn’t tinged by the approval of other people.

Illustration of a monkey being personality captured by excessive twitter usage

Most people around you want to personality-capture you in some way. Your boss might want you to work harder, your children might want you to give them more attention, and political parties want you to vote for them.

One interesting way to frame personality capture is by combining it with the concept of attention economics. All of the apps on your phone want to turn you into the type of person that uses them all day because that is beneficial for their revenue models. In many cases this is mutually beneficial, but it’s nonetheless clear that the cat and mouse game is starting to favor the felines more and more over the last two decades as they have learned to perfect the craft of user acquisition, the art of user retention, and the science of ARPU maximization.

As I discussed in where are the builders, the game becomes particularly skewed when there is a large difference in ability or judgement between counterparties, with one common example being children and adolescents. It’s easy to become personality-captured by minecraft or roblox at the age of 10 – the game is not only fun and addictive, but a child also has little understanding of the level of optimization their counterparty has put in to making sure that they remain a user for life.

How do I leave my personality basin?

Perhaps you have decided that you don’t like your personality basin. Maybe it used to be working out for you but no longer is, or maybe you’ve always been unhappy with it. Or maybe you just have reason to believe you’re trapped in a local maxima which is far inferior to the global one. What should you do?

The first thing you’ll want to do is to change your environment. If both you and your environment are a constant, you shouldn’t expect to end up in a different basin any time soon. For every new environment exists a new optimal-you, and the world offers many environments to choose from.

The second thing you’ll want to do is increase your learning rate. There are a lot of ways to do this. One interesting note is that your learning rate will automatically increase if your environment changes. This may be why so many people find they are able to be more thoughtful and creative while going on long walks in nature rather than sitting in a cubicle.

This is also a reason why it’s good to constantly be trying new things, because new things will likely involve new environments and new people. If you wonder why trying new things is hard, it is likely because this trait was more maladaptive in our ancestral environment than it is today, as we had less control over our surroundings in the past (If anything, we may have too many options in some cases of the present: our society is so large that defection from a group is less costly as you can simply find a new group to join afterwards. This seems to create challenging game-theoretic equilibria in match-making where commitment to a partner is devalued due to the ease of finding alternatives, the effects of which can be seen by how discontent much of the population is with dating apps).

Although you have a general learning rate curve for how quickly your personality adapts to a new environments, different stimuli will also be paired with differing gradient magnitudes. High-magnitude experiences which result in strong gradient updates can move you within personality space much more quickly.

Humans have many sets of learning rate curves which govern different parts of their brain. In addition to the baseline learning curve, our learning curves are heavily modified by our environment.

If someone uses a psychadelic drug which explicitly gives them high-magnitude gradients they will probably move a lot more in personality space than if they had stayed sober. Similarly if someone undergoes a highly traumatic event, it may push them a long distance within personality space as they quickly adapt to ensure that they don’t have to go through the same experience again. Both of these activities involve large gradient updates.

Common activities which seem to give the largest gradient updates to humans are meditation, drug usage, trauma, religious events, love, gambling, and sex.

Some of these concepts are more negatively-coded than others, for example trauma. But the intended purpose of trauma is obvious, which is to avoid really bad things from happening to you in the future. One of the reasons why overcoming trauma isn’t as hard-coded into us as strongly as we might hope for is because our present society is so much larger than that which we evolved in such that there’s more opportunity to change your environment as to remove the potential source of trauma. Trauma was likely more adaptive in our ancestral environment than it was today due to an inability to drastically change your surroundings and social group in the past.

This is why strong psychedelic drugs like ayahuasca can be dangerous: whatever happens to you during your experience will be fed to you via high-magnitude gradients. Because users may experience hallucinations and delusional thinking during usage of such drugs, it’s possible for their location in personality-space to be thrown far out-of-distribution and into an area which has little overlap with the rest of humanity.

This isn’t to say there can’t be high-magnitude positive outcomes as well, but just that there is a high potential for variance when large gradients are involved. Romantic love can be a similarly dangerous force and has pushed thousands to suicide, yet our society near-universally regards it as a good thing! While there are many other reasons for this, high-variance is not inherently bad and is likely necessary at the societal level in order to promote long-term antifragility (this is also the very reason I am so bullish on America).

Personality basins and mental illness

Personality basins are an interesting way to model many mental illnesses. Similar to attractor states or trapped priors, they allow us to have a simple model with which we can plan to manipulate in order to solve our problems. Just as your personality basin decides how introverted you are, how funny you are, and what type of music you enjoy, it also helps to curate which psychiatric conditions affect you.

One of the reasons why curing depression is so hard is because you need a very large gradient update to escape the basin you’re trapped in. This gradient update could come all at once via an excessively strong positive stimuli, for example a drug which explicitly increases your learning rate like ketamine. But this is often hard to reliably induce, and so the gradient updates instead usually have to be small and continual over a long period of time.

This is what most cognitive behavioral therapy techniques are: we find a simple way to make a small positive gradient update to push you ever-so-slightly out of the personality basin you’re trapped in, and then we keep doing it for months or years until we finally push you all the way out of the undesirable basin.

This is also a nice way to model something like drug addictions: drugs personality-capture you into a basin which feeds off of and depends on them, and this basin can become arbitrarily deep due to the high magnitude of gradients drugs can apply to you (and thus be very hard to escape from). The concept of relapsing on a drug is equivalent to falling back down to the bottom of the basin, and the concept of tapering off dosage over time is equivalent to providing small and continual gradient updates over time.

I have a lot of hot takes that society is collectively becoming so efficient at some forms of personality capture that we will end up inducing various psychiatric conditions in the majority of our population. Societies end up with their own hyperdimensional personality basins just as people do, and just like us, the two ways they can move out of their basin are either gradually via many slow updates (e.g. the industrial revolution), or all at once via a very strong update (e.g. the french revolution). It’s worth thinking about the effects that different types of memetic information may have on our society’s collective personality basins as we become more and more efficient at communication.

Can’t I be in multiple personality basins?

One thing you may notice from the above sections is that your personality appears much more malleable and dynamic than one described by a static point: you probably act differently around your family than you do around your friends or your co-workers.

To solve this discrepancy you can simply model personality space and your personality basin with additional dimensions, allowing you to model yourself not as a 1d point, but as a three-dimensional landscape.

I model my own personality basin with an extra dimension (i.e., 4d): at any given point in time there exists a “me” which implements a given personality landscape in a given personality basin, but I also have many sub-basins which implement my different moods. The set of actions I might perform when I’m angry is very different from that when I’m sad, and these are simply different sub-basins within the containing higher-dimensional basin. You could similarly increment the model’s dimensionality in order to model yourself using internal family systems or even dissociative identity disorder.

Further reading

This post was heavily inspired by other posts including Trapped Priors, Dynamical Systems, and Singing The Blues by Scott Alexander and Personality: The Body in Society by Kevin Simler.

I’d strongly suggest reading The Others Within Us, The Arctic Hysterias, Crazy Like Us, and Neurons Gone Wild as an addendum to this post. Other related topics to explore include signal theory, control theory, set point theory, game theory, reinforcement learning, and deep learning.

Although the concepts presented in this post are similar to pre-existing concepts, I find that applying the analogy of loss landscapes, basins, and basic RL and DL concepts to be useful tools for thought and encourage readers to do further exploration with this mental model in case they find other useful analogies (what might a linear transformation on the loss landscape of personality-space look like and compare to? how can we develop a more comprehensive model of learning rate in humans and how would we modify it? are there any mental illnesses we can use this model with to try to come up with novel types of cures? how can we integrate this with bayesian theories of learning and perception? which other ideas in LLMs, RL or ML might we find useful to further analogize with?)

The explicit goal of this post is to help RLHF you into a personality basin which more easily allows for both thoughtful analogies and practical tools for thought. If you liked this post consider checking out my home page or twitter. Feedback is welcome!

Where are the builders?

What are the brightest and most ambitious minds of our generation currently working on?

  • Here is a video from someone who spent 7 months building minecraft inside of minecraft by painstakingly constructing a redstone computer inside of it with its own graphics card and screen
  • Here is someone who spent 5 years constructing a 3D game within a 2D geometry game by building primitives and constructing 3D illusions from them
  • Here is a video from someone who spent 6 months building a factory inside factorio which recursively self-expands using a lua script
  • And here is someone who spent 4 months building a shader to let the linux kernel run inside of VRchat via writing a RISC-V CPU/SoC emulator in an HLSL pixel shader

I find the above examples fascinating from the meta perspective: while there’s nothing wrong with having fun building inside of games, these are the very same skillsets which tech companies would pay six figures to have on their side! (of course they may enjoy the games more – this is discussed later)

Sometimes people of this caliber even have trouble finding a job – they often don’t really know where to go besides apply online to boomer companies who reject them when they see a lack of credentials. They love building things and are very smart and hardworking, but their milieu is an environment which captured them from a young age (often a video game or social media) and sometimes also ensured that the value they produce is within a pre-existing platform (e.g. a video game).

“Why did you cherry-pick people playing video games instead of talking about, like, everyone currently enrolled in medical school or something?”

The US currently has 125,000 students enrolled in medical school (this seems low to me but I checked several sources). Minecraft has 140,000,000 (1120x) monthly active users. Roblox has 200,000,000 (1600x). This is obviously an unequal comparison, but the magnitude of the difference is still staggering.

Why are you building a graphics card inside minecraft instead of inside nvidia?

There’s several reasons why someone might build a graphics card inside of minecraft rather than being paid $300,000 a year to build one inside of nvidia:

  1. Minecraft is more enjoyable
  2. Minecraft is more addictive
  3. Minecraft found them first
  4. They don’t know the latter option exists, or how they would do it, or think they’d fail at it

The first reason (that minecraft is more enjoyable than working for nvidia) applies to most people who are playing games instead of working, and instead the latter three reasons will be the focus of the following sections.

Addiction & Adolescence

The world has a lot of addicting products. Most of them I’m able to avoid, but some of them just happen to hit my sweet spot: I had no problem avoiding smoking growing up, but world of warcraft consumed years of my adolescence.

Others don’t find world of warcraft addictive, instead procuring their poison elsewhere. Maybe it’s minecraft, or league of legends, or youtube shorts.

One of the reasons these apps out-compete the ‘real world’ is because they start competing for our attention at a very young age. Most kids will grow up inside of roblox, minecraft, discord, instagram, and tiktok. If a kid starts using their smartphone at 10, these platforms will have a full 8 years to solidify within their mind and modify their values and social network before they are even legally allowed to have a job. I refer to this concept as personality capture and have a post on personality capture and personality basins here.

Some comparisons to past historical figures:

I would have killed for a tech internship when I was 14. I had no idea how I could do that, so I studied independently for my CCNA instead and would hop straight into video games when I got home. In hindsight it’s really interesting thinking about past-me playing these games, because I was young and knew so little about the world, yet my counterparty was hundreds or thousands of well-educated adults optimizing for my addiction and spend. It certainly wasn’t a fair battle!

Products induce strong preference modification

When I was 12, the highest-status person in the world to me was zezima. For the ~85% of readers who don’t recognize this name, he was the highest ranked player in runescape and had an aura of infamy that I can only compare to someone like elon musk. What I wanted most in life at this age was a party hat, which was an immensely valuable item in the game which most players could never afford even after years of play.

Many of our values are locally-set by our environment and peers, and when we immerse ourselves into a different world, our preferences change alongside it. This is pretty obvious – the twitter addict is constantly thinking about how many followers and likes they get just as the league of legends player is ever-ruminating over their rank and win ratio.

This is a fully general force too – If my friends and I only had a forest to play in growing up, we’d probably have invented some status game of who can climb the highest tree and would eventually have our own local culture, lexicon, and so on. But the forest is actually much easier to escape from than video games and social media – literally speaking.

I tried to find some user retention numbers for world of warcraft which I was heavily addicted to as a teenager and found a monthly churn of ~5%. In other words, the typical world of warcraft subscriber played the game for over a full year. I wonder if they knew when they clicked the sign up button that, statistically speaking, they would spend hundreds of dollars and over a year of their life playing? I certainly didn’t when I clicked the button at 13. It’s worth noting that the linked paper is a decade old and points to a time when we used spreadsheets to optimize addictiveness rather than machine learning.

That your preferences are locally induced is why the simple heuristic that you become the average of your five closest friends is so useful. If you get to choose your friends, you also get to choose many of your preferences and goals. Although I had the freedom to choose my friends at the time, quitting a game I loved was hard because unless my friends quit too, I’d have to go find new friends. Before this statement appears obviously fallacious to many readers, I need to add the necessary context that most people I knew in MMOs would also play them for ~100% of their free time, easily reacing 8-16 hours a day (yes, there’s a strong selection effect here). Although I had a ton of fun in my years inside these games, I always wondered what I’d have ended up doing if they hadn’t existed.

Agency in the free market

I’m writing this blog post at 1AM right now. In order to do so I’ve had to block twitter, close messenger, and set my phone to night mode. Luckily I’m not battling any video game or youtube shorts addictions, or this post wouldn’t exist. I don’t think I’d be able to sit down and write for hours if I had spent my entire adolescence on tiktok.

As consumer markets become more efficient and we become more skilled at capturing and retaining the attention of the populace, we should expect the average agency of society to decrease.

This is obvious if you think about it for a bit (the goal of almost every app on your phone is to get you to do less of anything which pattern matches ‘not using their app’), but there are few who appreciate the magnitude of this effect as the masses of society engrossed in video games and social media at home alone in their bedrooms every night are well-hidden from us. You can walk to the park to see 50 people enjoying the outdoors, but the millions currently scrolling tiktok at home are hidden from you in every way except via a statistic.

I love how easy generative AI makes it to learn – I sometimes talk to Claude until I’m exhausted and have to sleep. But in the free market, Claude doesn’t stand a chance against Tiktok. This post isn’t about Tiktok either though, as Tiktok doesn’t stand a chance against SuperTiktok (soon).

Outlier Success

Many have wondered why there’s fewer entrepreneurs in their 20s on a path to outlier success than there were in previous decades. Facebook IPO’d at a valuation of $104 billion when Mark was 28. Stripe reached a valuation of $35 billion when John was 29. Snapchat IPO’d at $24 billion when Evan was 25. These are outlier examples, but that’s the entire point. Where are the current outlier examples from the next generation?

I offer several potential answers:

  1. They are currently busy playing video games (which likely become more important to them at a very young age)
  2. They watched so much tiktok as a adolescent that they no longer have the attention span to build things (that would involve not using tiktok)
  3. They have so little free time due to attention economics that they no longer have original ideas (time spent doing ‘nothing’ is very valuable for quality long-term life outcomes)

Many in the tech ecosystem call me a doomer when I suggest these explanations – they certainly aren’t addicted to video games, and their friends certainly don’t have reduced attention spans from tiktok. But they live in a bubble within a bubble (context: I work in AI in San Francisco), and from my point of view the data points to these hypotheses as strong contenders. Sometimes I talk about this with normal people and they think the above is so obvious that it doesn’t even interest them. Perhaps our future has always been that of bread and circuses?

To clarify – I don’t intend to say that consumption or video games are bad; I love both of them myself! But we may be getting too good at consumer app optimization, and when that is paired with adoption at a young enough age, the outcome is undesirable. Building minecraft inside of minecraft is cool, but when I see a toddler scrolling youtube shorts on an ipad alone I feel really bad.

As the agency of the average consumer decreases, the ceiling for the agency of outliers increases. Examples of inventions which drastically increased the ceiling of agency include venture capital, generative AI, programming, microchips, and trade and capitalism itself. Once AI agents start to actually work it seems like this will be another large driving force here. Many have wondered when the first one-person billion-dollar company will exist, and many predict it may be within just one or two decades. It will be an interesting time to be alive in, if nothing else.

If you enjoyed this post, you may also enjoy: Types Of Memetic Information and my Home Page.

LLMs are strangely-shaped tools

few hit AI apps exist because LLMs are what i’d call very “strangely-shaped” tools.

most tools are built with a specific purpose in mind like a screwdriver or a car.

but LLMs were something we stumbled upon by predicting text and playing with RL – we didn’t design the shape of them beforehand, we just let them naturally evolve into what the loss optimized for.

it’s clear they’re good at many things, but they are so strangely shaped that it’s easy to fall into traps when making products.

AI agents are a good example of a trap (for now), where it’s easy to spend months trying to perfect your scaffolding yet never quite reaching the level of reliability you’d hope for.

long-term memory implemented solely via RAG is another trap. it’s just tempting enough to try, but the results aren’t as good as they should be.

other common inadequacies include poor search, hallucinations, and high inference costs. but there’s a long list of subtle weaknesses which few tinkerers ever notice as well as many weaknesses (and strengths) which remain unfound.

much of the frontier of LLM posttraining is currently concerned with these inadequacies – wondering how we can mold these strangely-shaped LLMs we have grown into a slightly more suitable form for the problems we face.

this is hard, even for the major labs. as we slowly progress on it, i’d expect to continue to see most AI products attempt to solve the same problems via the same methods, further suffering from lack of distinctness both in performance and aesthetic, because they don’t have the right connection between research teams and product teams (or perhaps the right vision to begin with).

it’s telling that among the few recent consumer successes like midjourney or perplexity, competitors are hyper-focused on directly copying winners rather than exploring the vast new frontier of things which could be built instead. this makes sense because the frontier is strangely-shaped, as a result of the underlying catalyst itself being strangely-shaped.

it’s not uncommon for services to launch a feature literally called “AI” which is primarily composed of literal magic wands and glitter emoji simply because the product designer has no idea how to actually convey the intended experience to the user. 2024 is certainly not a year one would be fired for using too much AI.

I expect it to get more interesting later this year and especially in 2025, but it’s still been a surreal experience continually contrasting my day to day life in san francisco with that of the actual real world (note: SF is not real in this example).

the above is also relevant to some of the reasons i have longer agi timelines than i did a few years ago. agi is not a strangely-shaped tool. in fact, it is quite literally the opposite.

Originally posted via Twitter/X, but mirrored here for convenience.

If you liked this post you may be interested in the rest of my website too!


This page lists many of my favorite blog posts, organized by author. Much of my most-cherished knowledge is from blog posts or internet comments, so I hope to share some of that with others here. Last updated: Apr 17, 2024

Scott Alexander (Twitter): As the author behind SlateStarCodex (now AstralCodexTen) and many great LessWrong posts, Scott is among one of the best written content creators of the last decade. He writes about psychiatry, rationality, and meta-science. Here’s some writing of his that I love, with my favorites bolded:

Gwern Branwen (Twitter – currently private): Well-known for having quality deep dives in diverse areas such as statistics, technology, machine learning, genetics, psychology, and many others. Also often recognized as an amazingly aesthetic, verbose, and highly-usable website. Favorite posts:

  • About Gwern: About Gwern; who he is, what he has done, and links to other mediums
  • It Looks Like You’re Trying To Take Over The World: An eloquently-written and humorous short story about AI alignment and paperclipping, featuring our good friend Clippy alongside a multitude of entertaining references, both to Internet history and many arxiv machine learning papers
  • Generating Anime Faces: An overview of GANs in machine learning, with focus on Stylegan2 and anime art generation including ThisWaifuDoesNotExist and its follow-up ThisAnimeDoesNotExist, both trained from a large Danbooru dataset
  • Death Note Anonymity: Using information theory to quantify the magnitude of Light Yagami’s mistakes in Death Note (absolutely worth watching, even if you’re not into anime), offering insightful analysis and constructive criticism
  • The Scaling Hypothesis: Discussion of the scaling hypothesis in machine learning (essentially how much better models get with significantly more data+compute), with obligatory emphasis on GPT-2 and GPT-3
  • Melatonin: Detailed information on melatonin, a simple endogenous hormone that notably improves sleep in many individuals when supplemented just before bedtime
  • Nicotine: An analysis on the benefits of nicotine as a nootropic, with attention given to the fact that it is often incorrectly assumed to be a dangerous and addictive drug due to its inclusion in cigarettes and consequently significantly-confounded research claims
  • Modafinil: Discussion of modafinil, a prescription stimulant drug that appears to have a relatively favorable cost/benefit profile for productivity and alertness
  • Embryo Selection for Intelligence: A cost-benefit analysis of the marginal cost of IVF-based embryo selection for intelligence and other traits
  • Why Correlation Usually ≠ Causation: A meta-scientific discourse and analysis on the age-old adage that correlation does not imply causation
  • The Melancholy of Subculture Society: A brief analysis on the cultural effects of the Internet allowing niche subcultures to easily form
  • Newsletters: Links to Gwern’s past ~monthly newsletters
  • My Anime List: Gwern’s top-rated anime

Andrej Karpathy: (Twitter) A bright AI researcher who has spent time both at OpenAI and as the chief AI officer at Telsa. He has a popular Youtube channel with machiune learning content as well.

  • The Unreasonable Effectiveness of Recurrent Neural Networks: Back in 2015 Andrej trained a 10M-parameter RNN on some interesting text datasets like the source code for the Linux kernel and Shakespeare. Performance was surprisingly good!
  • Biohacking Lite: It’s always fun to read content from people from fields like computer science when they later deep dive into biology, often for their own personal health. This post has some high-SNR content on the basics of metabolism and energy in humans as well as some quantified-self demonstrations and simple dietary advice.

Scott Aaronson: A theoretical computer scientist with a focus on quantum computing and complexity theory. Although his posts on quantum computational complexity theory research go over my head, I’ve enjoyed some great content from him in other categories. Favorites:

Matt Levine (Twitter): An ex-Goldman Bloomberg opinion columnist with some wonderfully insightful and hilarious posts (offered as a free newsletter, generally ~4x a week) on the happenings in our modern yet often-insane financial world. Posts are generally centered around current events and are best read as they come out. Some examples:

Nintil (Twitter): A wonderful blog by Jose Luis Ricón with a focus on longevity, economics, and meta-science. Favorite posts:

Patrick Collison (Twitter): The CEO and co-founder of Stripe, often with focuses involving meta-science, individual and societal productivity, and economics

  • Fast: Examples of people quickly accomplishing ambitious things together
  • Questions: A short list of interesting questions
  • Advice: Advice, particularly for young and ambitious individuals
  • Book Recommendations: A well-sized list of suggested reading

Sam Altman (Twitter): The CEO of OpenAI and former president of Y Combinator, his posts often focus on startups, artificial intelligence, productivity, and science. Favorites:

  • How to be Successful: Thirteen thoughts on how to achieve long-term successful outcomes: learn a lot, compound yourself, work hard, and be ambitious
  • Productivity: Various productivity tips, such as ‘Picking the right thing to work on is the most important element of productivity and usually almost ignored. So think about it more!’
  • Advice for Ambitious 19 Year Olds: Advice for young and ambitious individuals, such as ‘The best people always seem to be building stuff and hanging around smart people’
  • How to Invest In Startups: Advice about being a good startup investor
  • Super successful companies: Notes some salient commonalities between many very successful companies
  • The Strength of Being Misunderstood: You should trade being short-term low-status for being long-term high-status

Paul Graham (Twitter): The founder of Y Combinator, with many posts focusing on startups, ideas and frameworks for everyday life, as well as advice and reflections for people that fit the founder/builder/nerd stereotype. Some favorites:

  • Do Things That Don’t Scale: An amazing tip on gaining initial traction and leverage by doing high-impact activities that won’t scale, but that will work effectively for the time being
  • What You Can’t Say: Reflections on that which exists outside of the Overton window
  • How to Make Wealth: An essay on effectively building wealth over time
  • Keep Your Identity Small: On why politics and religion yield such uniquely useless discussions due to excessive involvement with personal identity
  • Having Kids: Personal experiences and thoughts on having kids
  • It’s Charisma, Stupid: A 2004 essay arguing that charisma is the most important trait for elected politicians, using the US presidency as an example
  • What I worked on: A personal and emotional memoir on pg’s professional and personal history

Alexey Guzey (Twitter): Currently working on New Science, Alexey has some great blog posts with a focus on properly using the Internet for social leverage (reach out to people more, cold email people more, initiate conversations more, and create content more!), meta-science, productivity, biology, and more. Some favorites:

Melting Asphalt (Twitter): Written by Kevin Simler (along with Robin Hanson (Twitter), co-author of The Elephant in the Brain), Melting Asphalt has a wonderful collection of posts on evolutionary psychology, game theory, and novel and introspective takes on what makes us human. Favorites:

  • Neurons Gone Wild: A beautifully speculative post that suggests a recursively selfish model of biological neurons which enables selfish sub-agents and networks to co-exist in an evolutionary semi-competitive environment within our own minds. Probably my favorite post on this blog for several reasons. Also see Hallucinated Gods
  • Music in Human Evolution: A great book review of Why Do People Sing?: Music in Human Evolution by Joseph Jordania, involving predatory defense mechanisms, disposition of the dead, battle trances, and the audio-visual intimidation display
  • Crony Beliefs: On beliefs that stick around when they shouldn’t
  • Personality: The Body in Society:
    What is personality? ‘Nature and nurture work together to create a prototype, which then negotiates with the external world. The result is a strategy for getting along and getting ahead — a strategy we call “personality”, in other words, ‘Personality is a strategy for making the most of one’s particular lot in life.’ See also: part two and part three
  • Ads Don’t Work That Way: On ‘cultural imprinting’ and signaling in advertising
  • Doesn’t Matter, Warm Fuzzies: Discusses many interesting aspects of human ecology and society, with a focus on rituals, culture, confabulation, mimicry, and more
  • Social Status: Down the Rabbit Hole: On social status in humans, including an analysis of two proposed separate status systems: dominance/submission and prestige/admiration. See also: Social Status II: Cults and Loyalty
  • Border Stories: Borders are a necessary precondition for agency within a hostile ecosystem

Telescopic Turnip: Reads like type of cross-over between scott alexander and gwern, which means it’s good

Qualia Computing: With a subtitle of ‘revealing the computational properties of consciousness’, Qualia Computing is a great blog for anyone interested in the neurology, phenomenology, and interesting attempts at quantifications and explanations behind our own conscious experiences (qualia)

Patrick Mckenzie (Twitter): An entrepreneur and writer that lives in Japan and currently works at Stripe with a focus on startups and outreach, Patrick has many invaluable posts about finance, startups, marketing and professional communication, and highly-regarded SaaS and entrepreneurial advice. Favorite posts:

Nat Friedman (Twitter): Great personal website!

Fantastic Anachronism (Twitter): todo, see Recommended Reading

Applied Divinity Studies: todo

Peter Attia (Twitter): todo

Vitalik Buterin (Twitter): todo, see The bulldozer vs vetocracy political axis

Lesswrong: todo

Overcoming Bias: todo, ‘This is a blog on why we believe and do what we do, why we pretend otherwise, how we might do better, and what our descendants might do, if they don’t all die’, from Robin Hanson.

Tim Ferris: 11 Reasons Not to Become Famous

Dynomight (Twitter): todo, see Better air is the easiest way not to die by The impact of air pollution on health is often significantly underrepresented, and working on improving the quality of air in your dwelling can result in a very high ROI for your health

Marginal Revolution: todo