korrents

On the map

Tap a claim on the ring to put it at the centre.

← Training AIs on millions of verifiable tasks in diverse RL environments will lead to AGI.

17 connected korrents · 15 moments from 3 Oct 2012 to 13 Sept 2026. Nearly all of them are about reinforcement learning.

Everything filed under AGI AGI Everything filed under LLMs LLMs Everything filed under neural networks neural networks Everything filed under benchmarks benchmarks Everything filed under scaling laws scaling laws Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Training AIs on millions of verifiable tasks in diverse RL environments will lead to AGI. Training AIs on millions of verifiabletasks in diverse RL environments will leadto AGI. Last stated 4 months ago 26 Jun 2026 DP Dwarkesh Patel — holds since 2026-06-26 — tap for who they are Same subject: Scaling up GPT will never produce AGI, because a model trained on cross-entropy loss cannot get there; reinforcement learning in rich environments is required. — tap to centre the map on it Scaling up GPT will never produceAGI, because a model trained oncross-entropy loss cannot get there;reinforcement learning in richenvironments is required. Last stated 3 years ago 29 Jun 2023 GH George Hotz — holds since 2023-06-29 — tap for who they are Same subject: A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. — tap to centre the map on it A verifiable task can be optimisedby reinforcement learning until aneural network performs it extremelywell. Last stated 11 months ago 17 Nov 2025 AK Andrej Karpathy — holds since 2025-11-17 — tap for who they are Same subject: Aggressive data curation may be harmful for frontier models that are significantly overtrained relative to Chinchilla optimality. — tap to centre the map on it Aggressive data curation may beharmful for frontier models that aresignificantly overtrained relativeto Chinchilla optimality. Last stated 2 months ago 8 Sept 2026 DP Dwarkesh Patel — holds since 2026-09-08 — tap for who they are Same subject: Anything precise enough to benchmark is also precise enough to optimize for, and modern RL training increasingly resembles the shape of the benchmarks themselves. — tap to centre the map on it Anything precise enough to benchmarkis also precise enough to optimizefor, and modern RL trainingincreasingly resembles the shape ofthe benchmarks themselves. Last stated 6 months ago 16 Apr 2026 SK Sayash Kapoor — holds since 2026-04-16 — tap for who they are Same subject: Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. — tap to centre the map on it Capability does not generalise forfree: a model that will movemountains on an agentic task stilltells the same bad joke it told fiveyears ago. Last stated 7 months ago 20 Mar 2026 AK Andrej Karpathy — holds since 2026-03-20 — tap for who they are Same subject: Current models are unsafe because they are not smart enough, not because they are too smart. — tap to centre the map on it Current models are unsafe becausethey are not smart enough, notbecause they are too smart. Last stated a month ago 13 Sept 2026 FC François Chollet — holds since 2026-09-13 — tap for who they are Same subject: Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. — tap to centre the map on it Humans barely use reinforcementlearning for intelligence — what RLthey do use goes into motor tasks,not problem solving. Last stated a year ago 17 Oct 2025 AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one. — tap to centre the map on it Humans keep their place in AI asjudges rather than authors, becausetelling which of two answers isbetter is far easier than writing agood one. Last stated 2 years ago 3 Feb 2025 NL Nathan Lambert — holds since 2025-02-03 — tap for who they are Same subject: A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it A country outside the AI supplychain should just buy the index —which works only in the world whereAI ends up commoditised rather thanconcentrated. Last stated 5 months ago 4 Jun 2026 AI Alex Imas — holds since 2026-06-04 — tap for who they are Same subject: A poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that. — tap to centre the map on it A poor country should prioritiseowning a piece of AI over retrainingits workers, but it should not beteverything on that. Last stated 5 months ago 4 Jun 2026 PT Phil Trammell — holds since 2026-06-04 — tap for who they are Same subject: A slow takeoff is significantly more likely than a fast one: AI that is nearly as powerful will have transformed the world before the incredibly powerful kind arrives. — tap to centre the map on it A slow takeoff is significantly morelikely than a fast one: AI that isnearly as powerful will havetransformed the world before theincredibly powerful kind arrives. Last stated 9 years ago 24 Feb 2018 PC Paul Christiano — holds since 2018-02-24 — tap for who they are Same subject: A true artificial general intelligence cannot exist without being recognized as a moral subject. — tap to centre the map on it A true artificial generalintelligence cannot exist withoutbeing recognized as a moral subject. Last stated a year ago 10 Jun 2025 SH Samuel Hammond — holds since 2025-06-10 — tap for who they are Same subject: AGI research made no progress in its first six decades. — tap to centre the map on it AGI research made no progress in itsfirst six decades. Last stated 14 years ago 3 Oct 2012 DD David Deutsch — holds since 2012-10-03 — tap for who they are Same subject: An AI that cannot name the problems it can solve falls short of general intelligence — tap to centre the map on it An AI that cannot name the problemsit can solve falls short of generalintelligence Last stated a year ago 3 Oct 2025 SF Sadayuki Furuhashi — holds since 2025-10-03 — tap for who they are Same subject: The gap between chimps and humans is no evidence that a small increase in compute yields an explosion of capability, because evolution was not optimising chimps for technology. — tap to centre the map on it The gap between chimps and humans isno evidence that a small increase incompute yields an explosion ofcapability, because evolution wasnot optimising chimps fortechnology. Last stated 9 years ago 24 Feb 2018 PC Paul Christiano — holds since 2018-02-24 — tap for who they are Same subject: There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck. — tap to centre the map on it There will be no overnightintelligence explosion, because amodel's best work takes so muchtest-time compute that time itselfis the bottleneck. Last stated 4 months ago 26 Jun 2026 NB Noam Brown — holds since 2026-06-26 — tap for who they are Same subject: "Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next. — tap to centre the map on it "Scaling" was powerful because itwas one word: naming a researchdirection is what tells a wholefield what to do next. Last stated 11 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2012 to today (stretched back to the oldest claim here) — full is todaya face: someone who holds the claim — tap it for who they are

At the centre Training AIs on millions of verifiable tasks in diverse RL environments will lead to AGI. Last stated 26 Jun 2026 · 4 months ago Holds Dwarkesh Patel Read this korrent →