Tap a claim on the ring to put it at the centre.
← Reinforcement learning only works once a model already knows…
17 connected korrents · 16 moments on record from 22 Apr 2024 to 12 Aug 2026. Nearly all of them are about reinforcement learning .
Everything filed under robotics
robotics
Everything filed under LLMs
LLMs
Everything filed under scaling laws
scaling laws
Everything filed under self-driving cars
self-driving cars 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: Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. Last stated 12 months ago
12 Sept 2025
SL
Sergey Levine — holds since 2025-09-12 — tap for who they are
Same subject: One pre-trained robot model now matches or beats the specialists that were fine-tuned with reinforcement learning for the very tasks they were built for. — tap to centre the map on it One pre-trained robot model now matches or beats the specialists that were fine-tuned with reinforcement learning for the very tasks they were built for. Last stated 4 weeks ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — 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 4 weeks ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — 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: 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 11 months ago
26 Sept 2025
RS
Richard Sutton — holds since 2025-09-26 — 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: 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 five-year-old's vision is already good enough to drive a car, on a tiny and strikingly undiverse amount of data. — tap to centre the map on it A five-year-old's vision is already good enough to drive a car, on a tiny and strikingly undiverse amount of data. Last stated 9 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A good robotaxi demonstration in one city does not mean the company is ready to scale the service. — tap to centre the map on it A good robotaxi demonstration in one city does not mean the company is ready to scale the service. Last stated a year ago
8 Jul 2025
TL
Timothy B. Lee — holds since 2025-07-08 — tap for who they are
Same subject: A huge fleet collecting driving data is not a silver bullet for self-driving, because the data arrives unlabelled. — tap to centre the map on it A huge fleet collecting driving data is not a silver bullet for self-driving, because the data arrives unlabelled. Last stated 2 years ago
21 May 2024
TL
Timothy B. Lee — holds since 2024-05-21 — 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
At the centre
Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first.
Holds SL Sergey LevineRead this korrent →
One pre-trained robot model now matches or beats the specialists that were fine-tuned with reinforcement learning for the very tasks they were built for.
Holds CF Chelsea Finn
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 CF Chelsea Finn
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
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 Sutton
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
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 five-year-old's vision is already good enough to drive a car, on a tiny and strikingly undiverse amount of data.
Holds IS Ilya Sutskever
A good robotaxi demonstration in one city does not mean the company is ready to scale the service.
Holds TL Timothy B. Lee
A huge fleet collecting driving data is not a silver bullet for self-driving, because the data arrives unlabelled.
Holds TL Timothy B. Lee
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