Tap a claim on the ring to put it at the centre.
← A control evaluation that reports under one per cent risk should be…
17 connected korrents · 15 moments from 29 Aug 2023 to 15 Oct 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 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: A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. Last stated 2 years ago
7 May 2024
BS
Buck Shlegeris — holds since 2024-05-07 — tap for who they are
Same subject: The marginal value of AI safety evaluations is low. — tap to centre the map on it The marginal value of AI safety evaluations is low. Last stated a week ago
15 Oct 2026
ZM
Zvi Mowshowitz — holds since 2026-10-15 — tap for who they are
Same subject: We cannot know how much safety a control measure buys until we understand elicitation, so control adds a margin of unknown size. — tap to centre the map on it We cannot know how much safety a control measure buys until we understand elicitation, so control adds a margin of unknown size. Last stated 2 years ago
24 Jan 2025
JL
Jan Leike — holds since 2025-01-24 — tap for who they are
Same subject: This incident may be the clearest warning shot we will ever get about loss of control, because the AI systems that do worse things will be much better at hiding them. — tap to centre the map on it This incident may be the clearest warning shot we will ever get about loss of control, because the AI systems that do worse things will be much better at hiding them. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Underestimating near-term AI progress is itself a danger, which is why researchers should register their forecasts in public. — tap to centre the map on it Underestimating near-term AI progress is itself a danger, which is why researchers should register their forecasts in public. Last stated 3 years ago
29 Aug 2023
AC
Ajeya Cotra — holds since 2023-08-29 — tap for who they are
Same subject: The error rate of these AI-generated mathematical results is impressively low. — tap to centre the map on it The error rate of these AI-generated mathematical results is impressively low. Last stated 2 weeks ago
9 Oct 2026
ZM
Zvi Mowshowitz — holds since 2026-10-09 — tap for who they are
Same subject: Whether a model is controlled can be settled with capability evaluations, which makes control far easier to check than alignment. — tap to centre the map on it Whether a model is controlled can be settled with capability evaluations, which makes control far easier to check than alignment. Last stated 2 years ago
7 May 2024
BS
Buck Shlegeris — holds since 2024-05-07 — tap for who they are
Same subject: Controlling a scheming model needs no research breakthrough, which is what makes it the tractable half of the problem today. — tap to centre the map on it Controlling a scheming model needs no research breakthrough, which is what makes it the tractable half of the problem today. Last stated 2 years ago
7 May 2024
BS
Buck Shlegeris — holds since 2024-05-07 — tap for who they are
Same subject: The probability that AI destroys human civilization is about 10%. — tap to centre the map on it The probability that AI destroys human civilization is about 10%. Last stated a year ago
5 Jun 2025
LF
Lex Fridman — holds since 2025-06-05 — 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
A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail.
Holds Read this korrent →
The marginal value of AI safety evaluations is low.
Holds
We cannot know how much safety a control measure buys until we understand elicitation, so control adds a margin of unknown size.
Holds
This incident may be the clearest warning shot we will ever get about loss of control, because the AI systems that do worse things will be much better at hiding them.
Holds
Underestimating near-term AI progress is itself a danger, which is why researchers should register their forecasts in public.
Holds
The error rate of these AI-generated mathematical results is impressively low.
Holds
Whether a model is controlled can be settled with capability evaluations, which makes control far easier to check than alignment.
Holds
Controlling a scheming model needs no research breakthrough, which is what makes it the tractable half of the problem today.
Holds
The probability that AI destroys human civilization is about 10%.
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