Tap a claim on the ring to put it at the centre.
← AIs should be expected to be much better at tasks with tight feedback…
17 connected korrents · 16 moments from 1 Oct 2023 to 21 Oct 2026.
Everything filed under reinforcement learning
reinforcement learning
Everything filed under AI alignment
AI alignment
Everything filed under robotics
robotics
Everything filed under LLMs
LLMs
Everything filed under AI and science
AI and science
Everything filed under agency
agency
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: AIs should be expected to be much better at tasks with tight feedback loops, where success can be recognised after a short time.
AIs should be expected to be much better at tasks with tight feedback loops, where success can be recognised after a short time.
Last stated 9 months ago
17 Feb 2026
AC
Ajeya Cotra — holds since 2026-02-17 — tap for who they are
Same subject: Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. — tap to centre the map on it
Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down.
Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: AI helps exactly as far as the work is predictable and well documented, and stops helping on anything cutting edge. — tap to centre the map on it
AI helps exactly as far as the work is predictable and well documented, and stops helping on anything cutting edge.
Last stated 2 years ago
22 Mar 2025
TH
ThePrimeagen — holds since 2025-03-22 — tap for who they are
Same subject: AI systems are much better at tasks whose correctness can be verified than at tasks whose correctness cannot be checked. — tap to centre the map on it
AI systems are much better at tasks whose correctness can be verified than at tasks whose correctness cannot be checked.
Last stated 4 months ago
13 Jul 2026
AN
Arvind Narayanan — holds since 2026-07-13 — tap for who they are
Same subject: If AIs can now considerably improve the training of future AIs, this is very unlikely to end well. — tap to centre the map on it
If AIs can now considerably improve the training of future AIs, this is very unlikely to end well.
Last stated a month ago
21 Oct 2026
KP
Kelsey Piper — holds since 2026-10-21 — tap for who they are
Same subject: The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly. — tap to centre the map on it
The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly.
Last stated 3 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Control techniques can reasonably be expected to make early AIs that are not yet superintelligent helpful for a range of things they are good at. — tap to centre the map on it
Control techniques can reasonably be expected to make early AIs that are not yet superintelligent helpful for a range of things they are good at.
Last stated 9 months ago
17 Feb 2026
AC
Ajeya Cotra — holds since 2026-02-17 — tap for who they are
Same subject: As AI systems get better at scientific research tasks, it becomes more likely they will soon be capable of improving and building themselves. — tap to centre the map on it
As AI systems get better at scientific research tasks, it becomes more likely they will soon be capable of improving and building themselves.
Last stated 3 months ago
17 Aug 2026
JC
Jack Clark — holds since 2026-08-17 — tap for who they are
Same subject: AI helps you do more, but doing more does not mean doing it better. — tap to centre the map on it
AI helps you do more, but doing more does not mean doing it better.
Last stated 6 months ago
4 Jun 2026
DL
Deb Liu — holds since 2026-06-04 — tap for who they are
Same subject: A format reward should only be added when the answer is already correct. — tap to centre the map on it
A format reward should only be added when the answer is already correct.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards. — tap to centre the map on it
A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — tap for who they are
Same subject: A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel. — tap to centre the map on it
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Last stated 4 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — 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: Reading RL transcripts after a post-training run to find problems in training environments seems a good general practice. — tap to centre the map on it
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: 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: Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. — tap to centre the map on it
Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first.
Last stated a year ago
12 Sept 2025
SL
Sergey Levine — holds since 2025-09-12 — 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 2 years ago
6 Apr 2025
MH
Molson Hart — holds since 2025-04-06 — 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
AIs should be expected to be much better at tasks with tight feedback loops, where success can be recognised after a short time.
Last stated 17 Feb 2026 · 9 months ago
Holds Ajeya Cotra
Read this korrent →
Similar wording
Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down.
Last stated 11 Aug 2026 · 3 months ago
Holds Ryan Greenblatt
Similar wording
AI helps exactly as far as the work is predictable and well documented, and stops helping on anything cutting edge.
Last stated 22 Mar 2025 · 2 years ago
Holds ThePrimeagen
Similar wording
AI systems are much better at tasks whose correctness can be verified than at tasks whose correctness cannot be checked.
Last stated 13 Jul 2026 · 4 months ago
Holds Arvind Narayanan
Similar wording
If AIs can now considerably improve the training of future AIs, this is very unlikely to end well.
Last stated 21 Oct 2026 · a month ago
Holds Kelsey Piper
Similar wording
The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly.
Last stated 11 Aug 2026 · 3 months ago
Holds Ryan Greenblatt
Similar wording
Control techniques can reasonably be expected to make early AIs that are not yet superintelligent helpful for a range of things they are good at.
Last stated 17 Feb 2026 · 9 months ago
Holds Ajeya Cotra
Similar wording
As AI systems get better at scientific research tasks, it becomes more likely they will soon be capable of improving and building themselves.
Last stated 17 Aug 2026 · 3 months ago
Holds Jack Clark
Similar wording
AI helps you do more, but doing more does not mean doing it better.
Last stated 4 Jun 2026 · 6 months ago
Holds Deb Liu
Same subject: reinforcement learning
A format reward should only be added when the answer is already correct.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Same subject: reinforcement learning
A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Same subject: reinforcement learning
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Last stated 3 Aug 2026 · 4 months ago
Holds Dmitri Dolgov
Same subject: scaling laws
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
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
Same subject: scaling laws
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: robotics
Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first.
Last stated 12 Sept 2025 · a year ago
Holds Sergey Levine
Same subject: robotics
A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas.
Last stated 1 Oct 2023 · 3 years ago
Holds Tyler Cowen
Same subject: robotics
A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it.
Last stated 6 Apr 2025 · 2 years ago
Holds Molson Hart