Tap a claim on the ring to put it at the centre.
← OpenAI's o1 does an online search over reasoning steps at test time,…
17 connected korrents · 17 moments from 25 Jul 2023 to 24 Oct 2026. Nearly all of them are about LLMs .
Everything filed under reinforcement learning
reinforcement learning
Everything filed under OpenAI
OpenAI
Everything filed under Anthropic
Anthropic
Everything filed under scaling laws
scaling laws
Everything filed under AI alignment
AI alignment Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: OpenAI's o1 does an online search over reasoning steps at test time, unlike a traditional autoregressive language model. OpenAI's o1 does an online search over reasoning steps at test time, unlike a traditional autoregressive language model. Last stated 2 years ago
4 Dec 2024
NL
Nathan Lambert — holds since 2024-09-16 — tap for who they are
NL
Nathan Lambert — no longer holds since 2024-12-04 — tap for who they are
Same subject: Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world. — tap to centre the map on it Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world. Last stated a year ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: Process supervision by an LLM judge cannot be run for long, because a judge with billions of parameters is gameable and RL will find its cracks. — tap to centre the map on it Process supervision by an LLM judge cannot be run for long, because a judge with billions of parameters is gameable and RL will find its cracks. Last stated a year ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling. — tap to centre the map on it Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling. Last stated today
24 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-24 — tap for who they are
Same subject: Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute. — tap to centre the map on it Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute. Last stated 2 months ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: Without an execution environment, LLMs cannot properly act on their understanding of how to forward evolve a system. — tap to centre the map on it Without an execution environment, LLMs cannot properly act on their understanding of how to forward evolve a system. Last stated a month ago
21 Sept 2026
TL
Tobias Lütke — holds since 2026-09-21 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. Last stated 8 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: Frontier AI models are consolidating into an oligopoly held by a small number of large players. — tap to centre the map on it Frontier AI models are consolidating into an oligopoly held by a small number of large players. Last stated 3 years ago
21 Feb 2024
EG
Elad Gil — holds since 2024-02-21 — tap for who they are
Same subject: LLM-based AI tools can solve many small, self-contained programming problems found in introductory classes. — tap to centre the map on it LLM-based AI tools can solve many small, self-contained programming problems found in introductory classes. Last stated 3 years ago
25 Jul 2023
PG
Philip Guo — holds since 2023-07-25 — tap for who they are
Same subject: "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. — tap to centre the map on it "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. Last stated 2 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A skill is a set of repeatable, specific instructions that augments what Claude Code can do. — tap to centre the map on it A skill is a set of repeatable, specific instructions that augments what Claude Code can do. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — 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 it was one word: naming a research direction is what tells a whole field 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: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. Last stated 4 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. — tap to centre the map on it A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from. Last stated 7 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
Same subject: A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. — tap to centre the map on it A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. Last stated a year ago
7 Oct 2025
MM
Mr. Money Mustache — holds since 2025-10-07 — tap for who they are
Same subject: A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. — tap to centre the map on it A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. Last stated 2 years ago
7 May 2024
BS
Buck Shlegeris — holds since 2024-05-07 — tap for who they are
Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. Last stated 11 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
At the centre
OpenAI's o1 does an online search over reasoning steps at test time, unlike a traditional autoregressive language model.
No longer holds Read this korrent →
Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world.
Holds
Process supervision by an LLM judge cannot be run for long, because a judge with billions of parameters is gameable and RL will find its cracks.
Holds
Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling.
Holds
Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute.
Holds
Without an execution environment, LLMs cannot properly act on their understanding of how to forward evolve a system.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
Frontier AI models are consolidating into an oligopoly held by a small number of large players.
Holds
LLM-based AI tools can solve many small, self-contained programming problems found in introductory classes.
Holds
"I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out.
Holds
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Holds
A skill is a set of repeatable, specific instructions that augments what Claude Code can do.
Holds
"Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next.
Holds
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Holds
A lab should spend most of its compute on research rather than on building the next model, because research is where the tenfold yearly efficiency gains come from.
Holds
A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad.
Holds
A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail.
Holds
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Holds