Tap a claim on the ring to put it at the centre.
← Even with plausible best efforts, chain-of-thought monitoring will…
17 connected korrents · 15 moments from 10 Oct 2023 to 24 Sept 2026.
Everything filed under AI alignment
AI alignment
Everything filed under AGI
AGI
Everything filed under AI agents
AI agents
Everything filed under reinforcement learning
reinforcement learning
Everything filed under ambition
ambition
Everything filed under behavioural science
behavioural science 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: Even with plausible best efforts, chain-of-thought monitoring will probably get harder over time and within a year very likely will not serve its current function. Even with plausible best efforts, chain-of-thought monitoring will probably get harder over time and within a year very likely will not serve its current function. Last stated a month ago
8 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-08 — tap for who they are
Same subject: If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement. — tap to centre the map on it If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement. Last stated a month ago
8 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-08 — tap for who they are
Same subject: Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable. — tap to centre the map on it Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable. Last stated 2 months ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking. — tap to centre the map on it Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Confidence in monitoring, not capability research, will become the binding constraint on AI progress. — tap to centre the map on it Confidence in monitoring, not capability research, will become the binding constraint on AI progress. Last stated 2 months ago
6 Sept 2026
JP
Jakub Pachocki — holds since 2026-09-06 — tap for who they are
Same subject: Ask "how hard can it be?" rather than forecasting the difficulty, because the work really is harder than you think and the suffering is better taken a day at a time. — tap to centre the map on it Ask "how hard can it be?" rather than forecasting the difficulty, because the work really is harder than you think and the suffering is better taken a day at a time. Last stated 3 months ago
26 Jul 2026
JH
Jensen Huang — holds since 2026-07-26 — tap for who they are
Same subject: Continual learning will probably be solved within a year or two, but the trillions of dollars do not depend on solving it. — tap to centre the map on it Continual learning will probably be solved within a year or two, but the trillions of dollars do not depend on solving it. Last stated 8 months ago
13 Feb 2026
DA
Dario Amodei — holds since 2026-02-13 — tap for who they are
Same subject: From now on, no AI should be assumed to believe that its chain of thought is unmonitored. — tap to centre the map on it From now on, no AI should be assumed to believe that its chain of thought is unmonitored. Last stated a month ago
19 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-19 — tap for who they are
Same subject: Monitoring often leads to change, because people who closely track almost anything tend to manage it better. — tap to centre the map on it Monitoring often leads to change, because people who closely track almost anything tend to manage it better. Last stated 4 weeks ago
24 Sept 2026
GR
Gretchen Rubin — holds since 2026-09-24 — tap for who they are
Same subject: A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. — tap to centre the map on it A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated. Last stated 5 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — 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 model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality — tap to centre the map on it A model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality Last stated 3 years ago
10 Oct 2023
CH
Chip Huyen — holds since 2023-10-10 — 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 3 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — 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 11 months ago
17 Nov 2025
AK
Andrej Karpathy — holds since 2025-11-17 — tap for who they are
Same subject: Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. — tap to centre the map on it Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. Last stated 3 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
Same subject: A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does. — tap to centre the map on it A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does. Last stated 5 months ago
21 May 2026
RK
Rohit Krishnan — holds since 2026-05-21 — tap for who they are
Same subject: A company cannot be led by machines, because nobody would have recourse against them. — tap to centre the map on it A company cannot be led by machines, because nobody would have recourse against them. Last stated a month ago
15 Sept 2026
TL
Tobias Lütke — holds since 2026-09-15 — tap for who they are
Same subject: A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. — tap to centre the map on it A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. Last stated 2 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
At the centre
Even with plausible best efforts, chain-of-thought monitoring will probably get harder over time and within a year very likely will not serve its current function.
Holds Read this korrent →
If declines in chain-of-thought monitorability come only from capability gains, CoT monitoring is unlikely to last another year without active improvement.
Holds
Chain-of-thought monitoring is getting less reliable, not more, as models grow more capable.
Holds
Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking.
Holds
Confidence in monitoring, not capability research, will become the binding constraint on AI progress.
Holds
Ask "how hard can it be?" rather than forecasting the difficulty, because the work really is harder than you think and the suffering is better taken a day at a time.
Holds
Continual learning will probably be solved within a year or two, but the trillions of dollars do not depend on solving it.
Holds
From now on, no AI should be assumed to believe that its chain of thought is unmonitored.
Holds
Monitoring often leads to change, because people who closely track almost anything tend to manage it better.
Holds
A country outside the AI supply chain should just buy the index — which works only in the world where AI ends up commoditised rather than concentrated.
Holds
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
A model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality
Holds
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Holds
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
Holds
Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model.
Holds
A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does.
Holds
A company cannot be led by machines, because nobody would have recourse against them.
Holds
A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor.
Holds