Tap a claim on the ring to put it at the centre.
← Reading RL transcripts after a post-training run to find problems in…
17 connected korrents · 17 moments from 10 Dec 2015 to 26 Oct 2026. Nearly all of them are about reinforcement learning .
Everything filed under scaling laws
scaling laws
Everything filed under LLMs
LLMs
Everything filed under AI alignment
AI alignment
Everything filed under neural networks
neural networks
Everything filed under benchmarks
benchmarks
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: Reading RL transcripts after a post-training run to find problems in training environments seems a good general practice.
Reading RL transcripts after a post-training run to find problems in training environments seems a good general practice.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — tap for who they are
Same subject: Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present. — tap to centre the map on it
Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: In reinforcement learning for LLMs, the loss is not as informative as in classic deep learning or pre-training. — tap to centre the map on it
In reinforcement learning for LLMs, the loss is not as informative as in classic deep learning or pre-training.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — 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 12 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — 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 3 months ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: Pre-training is a crappy evolution: the practically buildable substitute for the process that gave animals their built-in hardware. — tap to centre the map on it
Pre-training is a crappy evolution: the practically buildable substitute for the process that gave animals their built-in hardware.
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 4 weeks ago
24 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-24 — tap for who they are
Same subject: Reinforcement learning from verifiable rewards does not reliably carry a model's pretrained ethical understanding into its actual behavior. — tap to centre the map on it
Reinforcement learning from verifiable rewards does not reliably carry a model's pretrained ethical understanding into its actual behavior.
Last stated 3 months ago
11 Aug 2026
SH
Samuel Hammond — holds since 2026-08-11 — 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 9 months ago
13 Feb 2026
DA
Dario Amodei — holds since 2026-02-13 — tap for who they are
Same subject: A curve, which is what a deep learning model is, is a very bad substrate for discrete computation. — tap to centre the map on it
A curve, which is what a deep learning model is, is a very bad substrate for discrete computation.
Last stated 2 years ago
6 Nov 2024
FC
François Chollet — holds since 2024-11-06 — tap for who they are
Same subject: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Last stated 11 years ago
10 Dec 2015
JS
Jian Sun — holds since 2015-12-10 — tap for who they are
KH
Kaiming He — holds since 2015-12-10 — tap for who they are
Same subject: A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model. — tap to centre the map on it
A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model.
Last stated 3 months ago
23 Aug 2026
KC
Kun Chen — holds since 2026-08-23 — tap for who they are
Same subject: "Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment. — tap to centre the map on it
"Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment.
Last stated a month ago
9 Oct 2026
CR
Carl Rivera — holds since 2026-10-09 — tap for who they are
Same subject: A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies. — tap to centre the map on it
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated a year ago
8 Jul 2025
RG
Ryan Greenblatt — holds since 2025-07-08 — tap for who they are
Same subject: A big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm. — tap to centre the map on it
A big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm.
Last stated 4 weeks ago
26 Oct 2026
NL
Nathan Lambert — holds since 2026-10-26 — tap for who they are
Same subject: 'Everyone gets it wrong sometimes' is a bad argument when assessing track records. — tap to centre the map on it
'Everyone gets it wrong sometimes' is a bad argument when assessing track records.
Last stated 4 months ago
2 Aug 2026
AK
Adam Kucharski — holds since 2026-08-02 — 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 3 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A carmaker's claim to be the safest is mostly an artefact of comparing a new car against a fleet average twelve years old. — tap to centre the map on it
A carmaker's claim to be the safest is mostly an artefact of comparing a new car against a fleet average twelve years old.
Last stated 3 years ago
19 Dec 2023
PK
Philip Koopman — holds since 2023-12-19 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
Reading RL transcripts after a post-training run to find problems in training environments seems a good general practice.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Read this korrent →
Same subject: scaling laws, reinforcement learning
Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Same subject: scaling laws, reinforcement learning
In reinforcement learning for LLMs, the loss is not as informative as in classic deep learning or pre-training.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Same subject: scaling laws, reinforcement learning
Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training.
Last stated 25 Nov 2025 · 12 months ago
Holds Ilya Sutskever
Same subject: scaling laws, reinforcement learning
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 12 Aug 2026 · 3 months ago
Holds Chelsea Finn
Same subject: scaling laws, reinforcement learning
Pre-training is a crappy evolution: the practically buildable substitute for the process that gave animals their built-in hardware.
Last stated 17 Oct 2025 · a year ago
Holds Andrej Karpathy
Same subject: scaling laws, reinforcement learning
Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling.
Last stated 24 Oct 2026 · 4 weeks ago
Holds Sebastian Raschka
Same subject: scaling laws, reinforcement learning
Reinforcement learning from verifiable rewards does not reliably carry a model's pretrained ethical understanding into its actual behavior.
Last stated 11 Aug 2026 · 3 months ago
Holds Samuel Hammond
Same subject: scaling laws, reinforcement learning
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 13 Feb 2026 · 9 months ago
Holds Dario Amodei
Same subject: neural networks
A curve, which is what a deep learning model is, is a very bad substrate for discrete computation.
Last stated 6 Nov 2024 · 2 years ago
Holds François Chollet
Same subject: neural networks
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Last stated 10 Dec 2015 · 11 years ago
Holds Jian Sun Kaiming He
Same subject: neural networks
A project-level agent memory file works like a neural net, steering the agent much as a fine-tuned LoRA steers a model.
Last stated 23 Aug 2026 · 3 months ago
Holds Kun Chen
Same subject: AI alignment
"Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment.
Last stated 9 Oct 2026 · a month ago
Holds Carl Rivera
Same subject: AI alignment
A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies.
Last stated 8 Jul 2025 · a year ago
Holds Ryan Greenblatt
Same subject: AI alignment
A big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm.
Last stated 26 Oct 2026 · 4 weeks ago
Holds Nathan Lambert
Same subject: benchmarks
'Everyone gets it wrong sometimes' is a bad argument when assessing track records.
Last stated 2 Aug 2026 · 4 months ago
Holds Adam Kucharski
Same subject: benchmarks
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 3 Sept 2026 · 3 months ago
Holds Dax Raad
Same subject: benchmarks
A carmaker's claim to be the safest is mostly an artefact of comparing a new car against a fleet average twelve years old.
Last stated 19 Dec 2023 · 3 years ago
Holds Philip Koopman