Tap a claim on the ring to put it at the centre.
← Large language models mimic what people say to do rather than work out…
17 connected korrents · 14 moments on record from 22 Apr 2024 to 26 Aug 2026. Nearly all of them are about reinforcement learning .
Everything filed under LLMs
LLMs
Everything filed under scaling laws
scaling laws
Everything filed under formal proof
formal proof 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: 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. 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 11 months 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 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — 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 optimised by reinforcement learning until a neural network performs it extremely well. Last stated 10 months ago
17 Nov 2025
AK
Andrej Karpathy — holds since 2025-11-17 — 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 for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. Last stated 6 months ago
20 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-20 — 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 reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. Last stated 11 months 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 as judges rather than authors, because telling which of two answers is better is far easier than writing a good one. Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — tap for who they are
Same subject: Models look far better on evals than they are in the world because researchers, inadvertently, take inspiration from the evals when they build RL environments. — tap to centre the map on it Models look far better on evals than they are in the world because researchers, inadvertently, take inspiration from the evals when they build RL environments. Last stated 9 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training. — tap to centre the map on it Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training. Last stated 9 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: No person learns the way RL does: a human reviews which parts of an attempt were good instead of rewarding every step of a lucky one. — tap to centre the map on it No person learns the way RL does: a human reviews which parts of an attempt were good instead of rewarding every step of a lucky one. Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. — tap to centre the map on it A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted. Last stated a year ago
7 Jun 2025
GM
Gary Marcus — holds since 2025-06-07 — tap for who they are
Same subject: A language model is not using language at all, because language requires an intention to communicate. — tap to centre the map on it A language model is not using language at all, because language requires an intention to communicate. Last stated 2 years ago
31 Aug 2024
TC
Ted Chiang — holds since 2024-08-31 — tap for who they are
Same subject: A language model's apparent mind is mostly our own bias: it predicts text, and leverages our evolved habit of attributing intentionality to anything that acts human. — tap to centre the map on it A language model's apparent mind is mostly our own bias: it predicts text, and leverages our evolved habit of attributing intentionality to anything that acts human. Last stated 2 years ago
22 Apr 2024
SC
Sean Carroll — holds since 2024-04-22 — tap for who they are
Same subject: Large language models could still plateau, and that possibility should be held open even though no evidence of it has appeared. — tap to centre the map on it Large language models could still plateau, and that possibility should be held open even though no evidence of it has appeared. Last stated 2 weeks ago
26 Aug 2026
DH
David Heinemeier Hansson — holds since 2026-08-26 — tap for who they are
Same subject: The LLM line of research will reach a capability plateau. — tap to centre the map on it The LLM line of research will reach a capability plateau. Last stated a month ago
7 Aug 2026
FC
François Chollet — no longer holds since 2026-08-07 — tap for who they are
GM
Gary Marcus — holds since 2025-06-07 — 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 2 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck. — tap to centre the map on it AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck. Last stated 5 months ago
22 Apr 2026
MK
Martin Kleppmann — holds since 2026-04-22 — tap for who they are
Same subject: Formal verification is about to become economical, because models are getting good enough at writing the proofs that humans no longer have to. — tap to centre the map on it Formal verification is about to become economical, because models are getting good enough at writing the proofs that humans no longer have to. Last stated 5 months ago
22 Apr 2026
MK
Martin Kleppmann — holds since 2026-04-22 — tap for who they are
Same subject: Formalising a proof in Lean currently takes about ten times the effort of writing it out: doable, but annoying. — tap to centre the map on it Formalising a proof in Lean currently takes about ten times the effort of writing it out: doable, but annoying. Last stated a year ago
14 Jun 2025
TT
Terence Tao — holds since 2025-06-14 — tap for who they are
At the centre
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 RS Richard SuttonRead this korrent →
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
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
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.
Holds
Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving.
Holds
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.
Holds NL Nathan Lambert
Models look far better on evals than they are in the world because researchers, inadvertently, take inspiration from the evals when they build RL environments.
Holds IS Ilya Sutskever
Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training.
Holds IS Ilya Sutskever
No person learns the way RL does: a human reviews which parts of an attempt were good instead of rewarding every step of a lucky one.
Holds
A language model is no substitute for a well-specified conventional algorithm, so it cannot simply be dropped into a complex problem and trusted.
Holds GM Gary Marcus
A language model is not using language at all, because language requires an intention to communicate.
Holds TC Ted Chiang
A language model's apparent mind is mostly our own bias: it predicts text, and leverages our evolved habit of attributing intentionality to anything that acts human.
Holds SC Sean Carroll
Large language models could still plateau, and that possibility should be held open even though no evidence of it has appeared.
Holds
The LLM line of research will reach a capability plateau.
Holds GM Gary MarcusNo longer 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 NB Noam Brown
AI-written code makes formal proof necessary, because human review of all that generated code becomes the bottleneck.
Holds MK Martin Kleppmann
Formal verification is about to become economical, because models are getting good enough at writing the proofs that humans no longer have to.
Holds MK Martin Kleppmann
Formalising a proof in Lean currently takes about ten times the effort of writing it out: doable, but annoying.
Holds TT Terence Tao