Tap a claim on the ring to put it at the centre.
← You improve a model you cannot retrain by writing better guidelines…
17 connected korrents · 14 moments on record from 1 Oct 2023 to 12 Aug 2026.
Everything filed under reinforcement learning
reinforcement learning
Everything filed under scaling laws
scaling laws
Everything filed under robotics
robotics
Everything filed under LLMs
LLMs 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: You improve a model you cannot retrain by writing better guidelines and skills for it, not by adjusting its parameters. You improve a model you cannot retrain by writing better guidelines and skills for it, not by adjusting its parameters. Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — 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 does. Last stated 7 months ago
13 Feb 2026
DA
Dario Amodei — holds since 2026-02-13 — tap for who they are
Same subject: If this much effort goes into training the model, you had better be willing to keep training your own. — tap to centre the map on it If this much effort goes into training the model, you had better be willing to keep training your own. Last stated 3 months ago
3 Jun 2026
KH
Kelsey Hightower — holds since 2026-06-03 — tap for who they are
Same subject: A model that solves a hard problem has learned nothing from it: the next session has forgotten it, with no new skill to carry to related problems. — tap to centre the map on it A model that solves a hard problem has learned nothing from it: the next session has forgotten it, with no new skill to carry to related problems. Last stated 6 months ago
20 Mar 2026
TT
Terence Tao — holds since 2026-03-20 — tap for who they are
Same subject: A model you have to fine-tune for each thing you want it to do is not a general-purpose model. — tap to centre the map on it A model you have to fine-tune for each thing you want it to do is not a general-purpose model. Last stated 4 weeks ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: A model can make an existing algorithm a hundred times faster and still cannot invent a better one, however long you give it. — tap to centre the map on it A model can make an existing algorithm a hundred times faster and still cannot invent a better one, however long you give it. Last stated 2 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: Training a model on principles rather than a list of rules is not an ideology but an empirical finding: its behaviour is more consistent and covers edge cases. — tap to centre the map on it Training a model on principles rather than a list of rules is not an ideology but an empirical finding: its behaviour is more consistent and covers edge cases. Last stated 7 months ago
13 Feb 2026
DA
Dario Amodei — holds since 2026-02-13 — tap for who they are
Same subject: What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. — tap to centre the map on it What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. Last stated a month ago
30 Jul 2026
JD
Jeff Dean — holds since 2026-07-30 — tap for who they are
Same subject: The one safe bet about AI is that models will improve, so what a company has to build is an organisation that gets better as models get better. — tap to centre the map on it The one safe bet about AI is that models will improve, so what a company has to build is an organisation that gets better as models get better. Last stated 11 months ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — 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: 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: 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 6 months ago
13 Mar 2026
DP
Dylan Patel — holds since 2026-03-13 — tap for who they are
Same subject: After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. — tap to centre the map on it After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute. Last stated 6 months ago
23 Mar 2026
JH
Jensen Huang — holds since 2026-03-23 — tap for who they are
Same subject: A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas. — tap to centre the map on it A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas. Last stated 3 years ago
1 Oct 2023
TC
Tyler Cowen — holds since 2023-10-01 — tap for who they are
Same subject: A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it. — tap to centre the map on it A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it. Last stated a year ago
6 Apr 2025
MH
Molson Hart — holds since 2025-04-06 — tap for who they are
Same subject: A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases. — tap to centre the map on it A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases. Last stated a month ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
At the centre
You improve a model you cannot retrain by writing better guidelines and skills for it, not by adjusting its parameters.
Holds JD Jeff DeanRead this korrent →
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
If this much effort goes into training the model, you had better be willing to keep training your own.
Holds KH Kelsey Hightower
A model that solves a hard problem has learned nothing from it: the next session has forgotten it, with no new skill to carry to related problems.
Holds TT Terence Tao
A model you have to fine-tune for each thing you want it to do is not a general-purpose model.
Holds CF Chelsea Finn
A model can make an existing algorithm a hundred times faster and still cannot invent a better one, however long you give it.
Holds NB Noam Brown
Training a model on principles rather than a list of rules is not an ideology but an empirical finding: its behaviour is more consistent and covers edge cases.
Holds DA Dario Amodei
What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters.
Holds JD Jeff Dean
The one safe bet about AI is that models will improve, so what a company has to build is an organisation that gets better as models get better.
Holds DF Dylan Field
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 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
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 DP Dylan Patel
After pre-training, post-training and test-time scaling, the fourth scaling law is agentic: multiplying AI by spawning agents, and the whole loop scales on one thing, compute.
Holds JH Jensen Huang
A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas.
Holds TC Tyler Cowen
A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it.
Holds MH Molson Hart
A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases.
Holds DD Dmitri Dolgov