Tap a claim on the ring to put it at the centre.
← Language models cannot be a prior for learning from experience,…
17 connected korrents · 12 moments on record from 21 Jan 2019 to 1 Apr 2026.
Everything filed under reinforcement learning
reinforcement learning
Everything filed under formal proof
formal proof
Everything filed under Google
Google
Everything filed under LLMs
LLMs
Everything filed under scaling laws
scaling laws
Everything filed under design
design 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: Language models cannot be a prior for learning from experience, because a prior needs a ground truth to be a prior about and they have none. Language models cannot be a prior for learning from experience, because a prior needs a ground truth to be a prior about and they have none. Last stated 11 months ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: A language model can predict what a person would say but not what will happen, and only the second of those is a model of the world. — tap to centre the map on it A language model can predict what a person would say but not what will happen, and only the second of those is a model… Last stated 11 months ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: Large language models start in exactly the wrong place, because they try to get by without a goal and therefore without any sense of better or worse. — tap to centre the map on it Large language models start in exactly the wrong place, because they try to get by without a goal and therefore… Last stated 11 months ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: Large language models are a bad way to do science, because they have been fed so much that nobody knows what they already knew. — tap to centre the map on it Large language models are a bad way to do science, because they have been fed so much that nobody knows what they… Last stated 11 months ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — tap for who they are
Same subject: Language models have not made misinformation meaningfully worse, because distribution, not the cost of writing convincing text, was always the limiting factor. — tap to centre the map on it Language models have not made misinformation meaningfully worse, because distribution, not the cost of writing… Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — tap for who they are
Same subject: The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. — tap to centre the map on it The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the… Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: Language models have no culture — no written record they hand to one another — and that absence is one of the things holding them back. — tap to centre the map on it Language models have no culture — no written record they hand to one another — and that absence is one of the… Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does. — tap to centre the map on it RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training… Last stated 7 months ago
13 Feb 2026
DA
Dario Amodei — holds since 2026-02-13 — tap for who they are
Same subject: Language models are gullible by design — they do what they are told and believe nearly anything said to them — and that, not a bug, is what makes software built on them attackable. — tap to centre the map on it Language models are gullible by design — they do what they are told and believe nearly anything said to them — and… Last stated 6 months ago
19 Mar 2026
SW
Simon Willison — holds since 2026-03-19 — 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… 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… 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… Last stated 11 months ago
17 Oct 2025
AK
Andrej Karpathy — holds since 2025-10-17 — tap for who they are
Same subject: A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost. — tap to centre the map on it A company's staff-engineer bar should be set against the best companies in the industry rather than against its own… Last stated 5 months ago
1 Apr 2026
TP
Thuan Pham — holds since 2026-04-01 — tap for who they are
Same subject: A crewed rocket cannot be made safe by making the booster reliable, so the only real way to improve safety is to carry an escape system. — tap to centre the map on it A crewed rocket cannot be made safe by making the booster reliable, so the only real way to improve safety is to carry… Last stated 3 years ago
14 Dec 2023
JB
Jeff Bezos — holds since 2023-12-14 — tap for who they are
Same subject: A monopolist that can no longer grow by winning new users can only grow by making its product worse for the users it already has. — tap to centre the map on it A monopolist that can no longer grow by winning new users can only grow by making its product worse for the… Last stated 3 years ago
28 Jul 2023
CD
Cory Doctorow — holds since 2023-07-28 — 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
Same subject: Full formal verification is a waste of money for most software: near-perfect is reachable with ordinary techniques at a fraction of the cost. — tap to centre the map on it Full formal verification is a waste of money for most software: near-perfect is reachable with ordinary… Last stated 8 years ago
21 Jan 2019
HW
Hillel Wayne — holds since 2019-01-21 — tap for who they are
Same subject: Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today. — tap to centre the map on it Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's… Last stated a year ago
14 Jun 2025
TT
Terence Tao — holds since 2025-06-14 — tap for who they are
At the centre
Language models cannot be a prior for learning from experience, because a prior needs a ground truth to be a prior about and they have none.
Holds RS Richard SuttonRead this korrent →
A language model can predict what a person would say but not what will happen, and only the second of those is a model of the world.
Holds RS Richard Sutton
Large language models start in exactly the wrong place, because they try to get by without a goal and therefore without any sense of better or worse.
Holds RS Richard Sutton
Large language models are a bad way to do science, because they have been fed so much that nobody knows what they already knew.
Holds RS Richard Sutton
Language models have not made misinformation meaningfully worse, because distribution, not the cost of writing convincing text, was always the limiting factor.
Holds NL Nathan Lambert
The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out.
Holds
Language models have no culture — no written record they hand to one another — and that absence is one of the things holding them back.
Holds
RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does.
Holds DA Dario Amodei
Language models are gullible by design — they do what they are told and believe nearly anything said to them — and that, not a bug, is what makes software built on them attackable.
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
A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost.
Holds TP Thuan Pham
A crewed rocket cannot be made safe by making the booster reliable, so the only real way to improve safety is to carry an escape system.
Holds JB Jeff Bezos
A monopolist that can no longer grow by winning new users can only grow by making its product worse for the users it already has.
Holds CD Cory Doctorow
Formalising a proof in Lean currently takes about ten times the effort of writing it out: doable, but annoying.
Holds TT Terence Tao
Full formal verification is a waste of money for most software: near-perfect is reachable with ordinary techniques at a fraction of the cost.
Holds HW Hillel Wayne
Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today.
Holds TT Terence Tao