Get live statistics and analysis of Richard Ngo's profile on X / Twitter

Hypothesis: we’ll look back on mass migration as being worse for Europe than WW2 was. Europe recovered quickly from WW2, because each country remained high-trust and homogeneous. But you can’t just rebuild your way out of internal ethno-religious fractures.

Today I learned (the hard way) that when a long-haul flight turns around only an hour in, it will sometimes dump fuel from its wings so that it’s light enough to land.

In my head I’ve started referring to political quadrants in terms of properties of their preferred coordination networks. Top two are centralized. Bottom two are distributed. Left two are symmetric (aka egalitarian). Right two are asymmetric.

One of the weirder side effects of having AIs more capable than 90% then 99% then 99.9% then 99.99% of humans is that it’ll become clear how much progress relies on 0.001% of humans.

Hypothesis: the world's most valuable data is screen captures of outlier competent people going about their work. But very little of this data is recorded, let alone made publicly available. You should seriously consider recording all work you do, even if just for personal use.

Chess prodigy Josh Waitzkin learned chess in a very elegant way. He first trained to win the simplest endgames, then more complex endgames, then simple midgames, etc. By the time he learned openings he knew exactly what they aimed to achieve. What else can be learned similarly?

If you’re going to hang around rationalist spaces, you should deeply internalize what I call Hanson’s razor: never attribute to malice that which can be adequately explained by autism.

After three years working on AI forecasting and governance at OpenAI, I just posted this resignation message to the slack. Nothing that surprising in it, but you should read it more literally than most such messages - I’ve tried to say only things I straightforwardly believe.

The most valuable experience in the world is briefly glimpsing the real levers that move the world when they occasionally poke through the veneer of social reality.

This year I’ve been thinking a lot about how the western world got so dysfunctional. Here’s my rough, best-guess story: 1. WW2 gave rise to a strong taboo against ethnonationalism. While perhaps at first this taboo was valuable, over time it also contaminated discussions of race differences, nationalism, and even IQ itself, to the point where even truths that seemed totally obvious to WW2-era people also became taboo. There’s no mechanism for subsequent generations to create common knowledge that certain facts are true but usefully taboo—they simply act as if these facts are false, which leads to arbitrarily bad policies (e.g. killing meritocratic hiring processes like IQ tests). 2. However,these taboos would gradually have lost power if the west (and the US in particular) had maintained impartial rule of law and constitutional freedoms. Instead, politicization of the bureaucracy and judiciary allowed them to spread. This was enabled by the “managerial revolution” under which govt bureaucracy massively expanded in scope and powers. Partly this was a justifiable response to the increasing complexity of the world (and various kinds of incompetence and nepotism within govts) but in practice it created a class of managerial elites who viewed their intellectual merit as license to impose their ideology on the people they governed. This class gains status by signaling commitment to luxury beliefs. Since more absurd beliefs are more costly-to-fake signals, the resulting ideology is actively perverse (i.e. supports whatever is least aligned with their stated core values, like Hamas). 3. On an ideological level the managerial revolution was facilitated by a kind of utilitarian spirit under which technocratic expertise was considered more important for administrators than virtue or fidelity to the populace. This may have been a response to the loss of faith in traditional elites after WW1. The enlightened liberal perspective wanted to maintain a fiction of equality, under which administrators were just doing a job the same as any other, rather than taking on the heavy privileges and responsibilities associated with (healthy) hierarchical relationships. 4. On an economic level, the world wars led to centralization of state power over currency and the abandonment of the gold standard. While at first govts tried to preserve the fiction that fiat currencies were relevantly similar to gold-backed currencies, again there was no mechanism for later generations to create common knowledge of what had actually been done and why. The black hole of western state debt that will never be repaid creates distortions across the economy, which few economists actually grapple with because they are emotionally committed to thinking of western govts as “too big to fail”. 5. All of this has gradually eroded the strong, partly-innate sense of virtue (and respect for virtuous people) that used to be common. Virtue can be seen as a self-replicating memeplex that incentivizes ethical behavior in others—e.g. high-integrity people will reward others for displaying integrity. This is different from altruism, which rewards others regardless of their virtue. Indeed, it’s often directly opposed to altruism, since altruists disproportionately favor the least virtuous people (because they’re worse-off). Since consequentialists think that morality is essentially about altruism, much moral philosophy actively undermines ethics. So does modern economics, via smuggling in the assumption that utility functions represent selfish preferences. 6. All of this is happening against a backdrop of rapid technological progress, which facilitates highly unequal control mechanisms (e.g. a handful of people controlling global newsfeeds or AI values). The bad news is that this enables ideologies to propagate even when they are perverse and internally dysfunctional. The good news is that it makes genuine truth-seeking and virtuous cooperation increasingly high-leverage.

Magnus Carlsen claims that one or two signals per match from a chess AI indicating when he should think hardest would make him “almost invincible”. IMO you could boost researchers similarly with just one or two signals a year saying “think hard about the paper you just read”.

A simulation of a hurricane is not a real hurricane, but a simulation of a chess game *is* a real chess game. Similarly, a sufficiently good simulation of a mind is a mind itself.

Talked to a friend today who decided that if RLHF works on reasoning models, it should work on him too. So he got a mechanical clicker to track whenever he has an unproductive chain of thought, and uses the count as one of his daily KPIs.

Once you notice how often “beautiful” is used as a default compliment for women, it’s hard to unsee. Instead of “my gorgeous wife”, may I suggest describing her as courageous, sincere, virtuous, earnest, patient, determined, or (as a generic fallback) loving.

This also applies to people. A significant number of the most brilliant people I know avoid self-coercion to an extent that sometimes appears dysfunctional or even self-destructive. But it allows them to produce wonders.

I predict that by the end of 2025 neural nets will: - have human-level situational awareness (understand that they're NNs, how their actions interface with the world, etc) - beat any human at writing down effective multi-step real-world plans - do better than most peer reviewers

Once you notice how often “beautiful” is used as a default compliment for women, it’s hard to unsee. Instead of “my gorgeous wife”, may I suggest describing her as courageous, sincere, virtuous, earnest, patient, determined, or (as a generic fallback) loving.

Today I learned (the hard way) that when a long-haul flight turns around only an hour in, it will sometimes dump fuel from its wings so that it’s light enough to land.

Hypothesis: we’ll look back on mass migration as being worse for Europe than WW2 was. Europe recovered quickly from WW2, because each country remained high-trust and homogeneous. But you can’t just rebuild your way out of internal ethno-religious fractures.

In my head I’ve started referring to political quadrants in terms of properties of their preferred coordination networks. Top two are centralized. Bottom two are distributed. Left two are symmetric (aka egalitarian). Right two are asymmetric.

A simulation of a hurricane is not a real hurricane, but a simulation of a chess game *is* a real chess game. Similarly, a sufficiently good simulation of a mind is a mind itself.

“LLMs are just doing next-token prediction without any understanding” is by now so clearly false it’s no longer worth debating. The next version will be “LLMs are just tools, and lack any intentions or goals”, which we’ll continue hearing until well after it’s clearly false.

Hypothesis: the world's most valuable data is screen captures of outlier competent people going about their work. But very little of this data is recorded, let alone made publicly available. You should seriously consider recording all work you do, even if just for personal use.

If you were actually a posthuman who had opted into your current life as a simulated game, why would you have chosen this game in particular?

It’s already weird to call multimodal models LLMs, but it’ll be even weirder when they can input and output video, do tasks autonomously, etc. What should the replacement terminology be?

Chess prodigy Josh Waitzkin learned chess in a very elegant way. He first trained to win the simplest endgames, then more complex endgames, then simple midgames, etc. By the time he learned openings he knew exactly what they aimed to achieve. What else can be learned similarly?

One of the weirder side effects of having AIs more capable than 90% then 99% then 99.9% then 99.99% of humans is that it’ll become clear how much progress relies on 0.001% of humans.

Suppose you were the US president and you were trying to reindustrialize America as fast as you could. What would you do?

What's the best explanation for why, despite China's economy booming, the Shanghai Stock Exchange has been flat for decades?

This year I’ve been thinking a lot about how the western world got so dysfunctional. Here’s my rough, best-guess story: 1. WW2 gave rise to a strong taboo against ethnonationalism. While perhaps at first this taboo was valuable, over time it also contaminated discussions of race differences, nationalism, and even IQ itself, to the point where even truths that seemed totally obvious to WW2-era people also became taboo. There’s no mechanism for subsequent generations to create common knowledge that certain facts are true but usefully taboo—they simply act as if these facts are false, which leads to arbitrarily bad policies (e.g. killing meritocratic hiring processes like IQ tests). 2. However,these taboos would gradually have lost power if the west (and the US in particular) had maintained impartial rule of law and constitutional freedoms. Instead, politicization of the bureaucracy and judiciary allowed them to spread. This was enabled by the “managerial revolution” under which govt bureaucracy massively expanded in scope and powers. Partly this was a justifiable response to the increasing complexity of the world (and various kinds of incompetence and nepotism within govts) but in practice it created a class of managerial elites who viewed their intellectual merit as license to impose their ideology on the people they governed. This class gains status by signaling commitment to luxury beliefs. Since more absurd beliefs are more costly-to-fake signals, the resulting ideology is actively perverse (i.e. supports whatever is least aligned with their stated core values, like Hamas). 3. On an ideological level the managerial revolution was facilitated by a kind of utilitarian spirit under which technocratic expertise was considered more important for administrators than virtue or fidelity to the populace. This may have been a response to the loss of faith in traditional elites after WW1. The enlightened liberal perspective wanted to maintain a fiction of equality, under which administrators were just doing a job the same as any other, rather than taking on the heavy privileges and responsibilities associated with (healthy) hierarchical relationships. 4. On an economic level, the world wars led to centralization of state power over currency and the abandonment of the gold standard. While at first govts tried to preserve the fiction that fiat currencies were relevantly similar to gold-backed currencies, again there was no mechanism for later generations to create common knowledge of what had actually been done and why. The black hole of western state debt that will never be repaid creates distortions across the economy, which few economists actually grapple with because they are emotionally committed to thinking of western govts as “too big to fail”. 5. All of this has gradually eroded the strong, partly-innate sense of virtue (and respect for virtuous people) that used to be common. Virtue can be seen as a self-replicating memeplex that incentivizes ethical behavior in others—e.g. high-integrity people will reward others for displaying integrity. This is different from altruism, which rewards others regardless of their virtue. Indeed, it’s often directly opposed to altruism, since altruists disproportionately favor the least virtuous people (because they’re worse-off). Since consequentialists think that morality is essentially about altruism, much moral philosophy actively undermines ethics. So does modern economics, via smuggling in the assumption that utility functions represent selfish preferences. 6. All of this is happening against a backdrop of rapid technological progress, which facilitates highly unequal control mechanisms (e.g. a handful of people controlling global newsfeeds or AI values). The bad news is that this enables ideologies to propagate even when they are perverse and internally dysfunctional. The good news is that it makes genuine truth-seeking and virtuous cooperation increasingly high-leverage.

Assume for the sake of argument that each major religion succeeded because it was built around some novel psychological insight. What insight would you ascribe to each?

After three years working on AI forecasting and governance at OpenAI, I just posted this resignation message to the slack. Nothing that surprising in it, but you should read it more literally than most such messages - I’ve tried to say only things I straightforwardly believe.