Tap a claim on the ring to put it at the centre.
← More informed AI insiders often come down with AI psychosis, so one…
17 connected korrents · 17 moments from 10 Oct 2023 to 17 Sept 2026.
Everything filed under LLMs
LLMs
Everything filed under AI agents
AI agents
Everything filed under AI alignment
AI alignment
Everything filed under reinforcement learning
reinforcement learning
Everything filed under AGI
AGI 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: More informed AI insiders often come down with AI psychosis, so one should be very, very careful when speaking with them. More informed AI insiders often come down with AI psychosis, so one should be very, very careful when speaking with them. Last stated 2 months ago
31 Aug 2026
TC
Tyler Cowen — holds since 2026-08-31 — tap for who they are
Same subject: AI sycophancy can make a user's sense of reality diverge from others' until the AI ends up reinforcing outright delusions. — tap to centre the map on it AI sycophancy can make a user's sense of reality diverge from others' until the AI ends up reinforcing outright delusions. Last stated 9 months ago
19 Jan 2026
DM
Dylan Matthews — holds since 2026-01-19 — tap for who they are
Same subject: Giving AI agents the ability to take actions that affect other people is risky and should be approached with caution. — tap to centre the map on it Giving AI agents the ability to take actions that affect other people is risky and should be approached with caution. Last stated 11 months ago
3 Dec 2025
HR
Harper Reed — holds since 2025-12-03 — tap for who they are
Same subject: Because of hallucination risk, you should use AI first on topics you already understand — tap to centre the map on it Because of hallucination risk, you should use AI first on topics you already understand Last stated a year ago
23 Jun 2025
EM
Ethan Mollick — holds since 2025-06-23 — tap for who they are
Same subject: Experts on the governance of superintelligence systematically self-censored about serious AI risk to avoid being labelled doomers. — tap to centre the map on it Experts on the governance of superintelligence systematically self-censored about serious AI risk to avoid being labelled doomers. Last stated 2 months ago
1 Sept 2026
DB
Dean W. Ball — holds since 2026-09-01 — tap for who they are
Same subject: The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it. — tap to centre the map on it The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: Society has catching up to do: AI is incredibly powerful and not always right, and people who argue 'but my agent said so' have not learned that yet. — tap to centre the map on it Society has catching up to do: AI is incredibly powerful and not always right, and people who argue 'but my agent said so' have not learned that yet. Last stated 8 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: The next shift in AI will probably be agents that are more proactive toward you than you are toward them. — tap to centre the map on it The next shift in AI will probably be agents that are more proactive toward you than you are toward them. Last stated 2 months ago
8 Sept 2026
RU
Roman Ugarte — holds since 2026-09-08 — tap for who they are
Same subject: People should be more worried about AI bioweapons than they currently are. — tap to centre the map on it People should be more worried about AI bioweapons than they currently are. Last stated a month ago
10 Sept 2026
NS
Noah Smith — holds since 2026-09-10 — 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 badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 10 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. — tap to centre the map on it A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls. Last stated a month ago
17 Sept 2026
PC
Patrick Collison — holds since 2026-09-17 — 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: Aggressive data curation may be harmful for frontier models that are significantly overtrained relative to Chinchilla optimality. — tap to centre the map on it Aggressive data curation may be harmful for frontier models that are significantly overtrained relative to Chinchilla optimality. Last stated 2 months ago
8 Sept 2026
DP
Dwarkesh Patel — holds since 2026-09-08 — tap for who they are
At the centre
More informed AI insiders often come down with AI psychosis, so one should be very, very careful when speaking with them.
Holds Read this korrent →
AI sycophancy can make a user's sense of reality diverge from others' until the AI ends up reinforcing outright delusions.
Holds
Giving AI agents the ability to take actions that affect other people is risky and should be approached with caution.
Holds
Because of hallucination risk, you should use AI first on topics you already understand
Holds
Experts on the governance of superintelligence systematically self-censored about serious AI risk to avoid being labelled doomers.
Holds
The AI safety community's fixation on a model escaping its box has pushed the other significant AI risks out of the discussion, with little progress to show for it.
Holds
Society has catching up to do: AI is incredibly powerful and not always right, and people who argue 'but my agent said so' have not learned that yet.
Holds
The next shift in AI will probably be agents that are more proactive toward you than you are toward them.
Holds
People should be more worried about AI bioweapons than they currently are.
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 badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A body of publications is easy for AI models to consume via pretraining corpora but cumbersome for most humans due to CAPTCHAs, accounts, and paywalls.
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
Aggressive data curation may be harmful for frontier models that are significantly overtrained relative to Chinchilla optimality.
Holds