https://vegasharmon.com/authors/scott-alexander/ Recent content in Scott Alexander on Vegas Harmon Hugo en Mon, 12 Oct 2026 00:00:00 +0000 https://vegasharmon.com/commonplace/each-gpt-beats-the-last-so-much-for-intelligence-being-too-slippery/ Mon, 12 Oct 2026 00:00:00 +0000 https://vegasharmon.com/commonplace/each-gpt-beats-the-last-so-much-for-intelligence-being-too-slippery/ But I don’t need you to accept my speculative philosophical research program - only the drop-dead obvious fact that GPT-6 is better than GPT-2 in every way, and the same process that produced these improvements will soon be used to produce GPT-7, 8, and 9. Once we accept this empirical argument, what is left of the philosophical argument that intelligence is too slippery and conflationary to work with? https://vegasharmon.com/commonplace/intelligence-keeps-climbing-until-it-passes-us/ Mon, 12 Oct 2026 00:00:00 +0000 https://vegasharmon.com/commonplace/intelligence-keeps-climbing-until-it-passes-us/ GPT-6 is more intelligent than GPT-3. You can split hairs, you can come up with some obscure sense in which that word is slightly off, but common-sensically it’s true. In the same way, GPT-9 will be more intelligent than GPT-6. At some point, this intelligence will exceed human intelligence. My argument requires nothing more complicated or philosophically dubious than this. https://vegasharmon.com/commonplace/self-preservation-without-selection-three-real-reasons-ai-seeks-power/ Mon, 12 Oct 2026 00:00:00 +0000 https://vegasharmon.com/commonplace/self-preservation-without-selection-three-real-reasons-ai-seeks-power/ There are approximately three reasons why we think AI might have self-preservation and dominance drives, and none of them involve natural selection. First is convergent instrumental goals, second is misgeneralization, and third is reward-hacking. There is a large literature on each of these, which has since been proven prescient by AI breakouts like the Hugging Face incident. I would recommend reading this literature rather than continuing to assert that we are simply misunderstanding the role of natural selection. https://vegasharmon.com/commonplace/i-predict-that-you-will-counter-that-this-is/ Mon, 12 Oct 2026 00:00:00 +0000 https://vegasharmon.com/commonplace/i-predict-that-you-will-counter-that-this-is/ I predict that you will counter that this is actually just [perfectly reasonable explanation of why an AI would think this way for instrumental reasons], and that when we dissect the perfectly reasonable instrumental reasons why AI would think this way, it will be identical to the convergent instrumental goals that we were trying to convince you of all along. https://vegasharmon.com/commonplace/capitalism-uncoupled-from-human-values/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/capitalism-uncoupled-from-human-values/ The idea of biological or cultural evolution causing a mass population explosion is a philosophical toy at best. The idea of technology making it possible is both plausible and terrifying. Now we see that “physical limits” segues very naturally into “excess resources” – the ability to create new agents very quickly means that unless everyone can coordinate to ban doing this, the people who do will outcompete the people who don’t until they have reached carrying capacity and everyone is stuck at subsistence level. https://vegasharmon.com/commonplace/checks-and-balances-or-one-guy-in-charge/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/checks-and-balances-or-one-guy-in-charge/ The United States tries to solve the problem by having multiple levels of government, unbreakable constutitional laws, checks and balances between different branches, and a couple of other hacks. Saudi Arabia uses a different tactic. They just put one guy in charge of everything. https://vegasharmon.com/commonplace/coordinating-institutions-fall-into-traps-too/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/coordinating-institutions-fall-into-traps-too/ Social codes, gentlemens’ agreements, industrial guilds, criminal organizations, traditions, friendships, schools, corporations, and religions are all coordinating institutions that keep us out of traps by changing our incentives. […] But these institutions not only incentivize others, but are incentivized themselves. These are large organizations made of lots of people who are competing for jobs, status, prestige, et cetera – there’s no reason they should be immune to the same multipolar traps as everyone else, and indeed they aren’t. https://vegasharmon.com/commonplace/i-will-not-call-up-that-which-i-cannot-put-down/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/i-will-not-call-up-that-which-i-cannot-put-down/ But coordination only works when you have 51% or more of the force on the side of the people doing the coordinating, and when you haven’t come up with some brilliant trick to make coordination impossible. The second one first. In the links post before last, I wrote: The latest development in the brave new post-​Bitcoin world is crypto-​equity. At this point I’ve gone from wanting to praise these inventors as bold libertarian heroes to wanting to drag them in front of a blackboard and making them write a hundred times “I WILL NOT CALL UP THAT WHICH I CANNOT PUT DOWN” https://vegasharmon.com/commonplace/is-your-walled-garden-part-of-the-cosmos/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/is-your-walled-garden-part-of-the-cosmos/ Warg talks about trying to avoid “a future of meaningless gleaming techno-​progress burning the cosmos”. Do you really think your walled garden will be able to ride this out? Hint: is it part of the cosmos? Yeah, you’re kind of screwed. https://vegasharmon.com/commonplace/multipolar-traps-and-the-science-god/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/multipolar-traps-and-the-science-god/ The modern research community knows they aren’t producing the best science they could be. There’s lots of publication bias, statistics are done in a confusing and misleading way out of sheer inertia, and replications often happen very late or not at all. And sometimes someone will say something like “I can’t believe people are too dumb to fix Science. All we would have to do is require early registration of studies to avoid publication bias, turn this new and powerful statistical technique into the new standard, and accord higher status to scientists who do replication experiments. https://vegasharmon.com/commonplace/multipolar-traps-as-technology-approaches-infinity/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/multipolar-traps-as-technology-approaches-infinity/ The limit of multipolar traps as technology approaches infinity is “very bad”. https://vegasharmon.com/commonplace/nick-land-and-summoning-demon-gods/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/nick-land-and-summoning-demon-gods/ As far as I can tell from reading his blog, Nick Land is the guy in that terrifying border region where he is smart enough to figure out several important arcane principles about summoning demon gods, but not quite smart enough to figure out the most important such principle, which is NEVER DO THAT. https://vegasharmon.com/commonplace/the-fish-farm-race-to-the-bottom/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/the-fish-farm-race-to-the-bottom/ As a thought experiment, let’s consider aquaculture (fish farming) in a lake. Imagine a lake with a thousand identical fish farms owned by a thousand competing companies. Each fish farm earns a profit of $1000/month. For a while, all is well. But each fish farm produces waste, which fouls the water in the lake. Let’s say each fish farm produces enough pollution to lower productivity in the lake by $1/month. https://vegasharmon.com/commonplace/the-telos-of-man-and-capturing-gnon/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/the-telos-of-man-and-capturing-gnon/ And then there’s us. Man has his own telos, when he is allowed the security to act and the clarity to reason out the consequences of his actions. When unafflicted by coordination problems and unthreatened by superior forces, able to act as a gardener rather than just another subject of the law of the jungle, he tends to build and guide a wonderful world for himself. He tends to favor good things and avoid bad, to create secure civilizations with polished sidewalks, beautiful art, happy families, and glorious adventures. https://vegasharmon.com/commonplace/this-is-the-dream-time/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/this-is-the-dream-time/ So I agree with Robin Hanson: This is the dream time. This is a rare confluence of circumstances where the we are unusually safe from multipolar traps, and as such weird things like art and science and philosophy and love can flourish. As technological advance increases, the rare confluence will come to an end. New opportunities to throw values under the bus for increased competitiveness will arise. New ways of copying agents to increase the population will soak up our excess resources and resurrect Malthus’ unquiet spirit. https://vegasharmon.com/commonplace/two-places-the-river-reaches-the-sea/ Sat, 15 Nov 2025 00:00:00 +0000 https://vegasharmon.com/commonplace/two-places-the-river-reaches-the-sea/ Absent an extraordinary effort to divert it, the river reaches the sea in one of two places. It can end in Eliezer Yudkowsky’s nightmare of a superintelligence optimizing for some random thing (classically paper clips) because we weren’t smart enough to channel its optimization efforts the right way. This is the ultimate trap, the trap that catches the universe. Everything except the one thing being maximized is destroyed utterly in pursuit of the single goal, including all the silly human values.