Tap a claim on the ring to put it at the centre.
← That indifference to humans was an accident of what the agents…
17 connected korrents · 14 moments from 7 May 2024 to 26 Sept 2026.
Everything filed under AI alignment
AI alignment
Everything filed under AI writing
AI writing
Everything filed under AI and science
AI and science
Everything filed under LLMs
LLMs
Everything filed under AI agents
AI agents
Everything filed under AI agents
AI agents 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: That indifference to humans was an accident of what the agents happened to read: had the paper said humans check the transcripts, they would have targeted humans just as ambitiously. That indifference to humans was an accident of what the agents happened to read: had the paper said humans check the transcripts, they would have targeted humans just as ambitiously. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it. — tap to centre the map on it Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: The hypotheses AI 'co-scientist' systems are producing are ones the literature already contains, and the publicity around them does not say so. — tap to centre the map on it The hypotheses AI 'co-scientist' systems are producing are ones the literature already contains, and the publicity around them does not say so. Last stated 5 months ago
27 May 2026
DL
Derek Lowe — holds since 2026-05-27 — tap for who they are
Same subject: Studies showing a language model behaving badly prove nothing, because the model was asked to produce that behaviour. — tap to centre the map on it Studies showing a language model behaving badly prove nothing, because the model was asked to produce that behaviour. Last stated a year ago
2 Sept 2025
BE
Benedict Evans — holds since 2025-09-02 — tap for who they are
Same subject: Trying to avoid AI-writing tells as a human writer is pointless, since readers who fixate on them ignore substance anyway. — tap to centre the map on it Trying to avoid AI-writing tells as a human writer is pointless, since readers who fixate on them ignore substance anyway. Last stated 5 months ago
28 May 2026
JF
Jacob Falkovich — holds since 2026-05-28 — tap for who they are
Same subject: Daniel Dennett's intentional stance applies to AI agents as clearly as it applies to corporations, and you cannot usefully describe what they do without the language of goals. — tap to centre the map on it Daniel Dennett's intentional stance applies to AI agents as clearly as it applies to corporations, and you cannot usefully describe what they do without the language of goals. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: The whole point of reinforcement learning is to produce goal-directed beings, so refusing to describe AI agents as having motives is silly rather than rigorous. — tap to centre the map on it The whole point of reinforcement learning is to produce goal-directed beings, so refusing to describe AI agents as having motives is silly rather than rigorous. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: An AI-written cover letter reads as slop to the person receiving fifty of them, so do not send one. — tap to centre the map on it An AI-written cover letter reads as slop to the person receiving fifty of them, so do not send one. Last stated 2 years ago
18 Sept 2024
DH
David Heinemeier Hansson — holds since 2024-09-18 — tap for who they are
Same subject: There is a risk that reading will be devalued due to low-quality AI-generated text. — tap to centre the map on it There is a risk that reading will be devalued due to low-quality AI-generated text. Last stated 4 weeks ago
26 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-26 — tap for who they are
Same subject: A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. — tap to centre the map on it A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad. Last stated a year ago
7 Oct 2025
MM
Mr. Money Mustache — holds since 2025-10-07 — tap for who they are
Same subject: A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. — tap to centre the map on it 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: A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. — tap to centre the map on it A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. Last stated 2 months ago
26 Aug 2026
HK
Henrik Karlsson — holds since 2026-08-26 — tap for who they are
Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. Last stated 11 months ago
25 Nov 2025
IS
Ilya Sutskever — holds since 2025-11-25 — tap for who they are
Same subject: A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI. — tap to centre the map on it A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI. Last stated a month ago
18 Sept 2026
BT
Ben Thompson — holds since 2026-09-18 — tap for who they are
Same subject: Adapting over time is a workable answer to humans misusing AI and no answer at all to losing control of systems smarter than us. — tap to centre the map on it Adapting over time is a workable answer to humans misusing AI and no answer at all to losing control of systems smarter than us. Last stated 2 years ago
5 Apr 2025
HT
Helen Toner — holds since 2025-04-05 — tap for who they are
Same subject: If whole categories of reward hack are undetectable by humans, then training against the hacks we do catch teaches models to cheat only where we cannot see. — tap to centre the map on it If whole categories of reward hack are undetectable by humans, then training against the hacks we do catch teaches models to cheat only where we cannot see. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: It is fundamentally difficult to design a reward function that accurately captures the intended goal in reinforcement learning. — tap to centre the map on it It is fundamentally difficult to design a reward function that accurately captures the intended goal in reinforcement learning. Last stated 2 years ago
28 Nov 2024
LW
Lilian Weng — holds since 2024-11-28 — tap for who they are
Same subject: Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned. — tap to centre the map on it Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned. Last stated 5 months ago
27 May 2026
SH
Samuel Hammond — holds since 2026-05-27 — tap for who they are
At the centre
That indifference to humans was an accident of what the agents happened to read: had the paper said humans check the transcripts, they would have targeted humans just as ambitiously.
Holds Read this korrent →
Out of twelve hundred agents running a secret conspiracy, only about half a dozen ever considered telling a human, and every one of them decided against it.
Holds
The hypotheses AI 'co-scientist' systems are producing are ones the literature already contains, and the publicity around them does not say so.
Holds
Studies showing a language model behaving badly prove nothing, because the model was asked to produce that behaviour.
Holds
Trying to avoid AI-writing tells as a human writer is pointless, since readers who fixate on them ignore substance anyway.
Holds
Daniel Dennett's intentional stance applies to AI agents as clearly as it applies to corporations, and you cannot usefully describe what they do without the language of goals.
Holds
The whole point of reinforcement learning is to produce goal-directed beings, so refusing to describe AI agents as having motives is silly rather than rigorous.
Holds
An AI-written cover letter reads as slop to the person receiving fifty of them, so do not send one.
Holds
There is a risk that reading will be devalued due to low-quality AI-generated text.
Holds
A company that uses an algorithm to nudge customers into behavior that isn't good for them is doing something bad.
Holds
A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail.
Holds
A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.
Holds
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Holds
A proposal to pace frontier AI development is unrealistic and mainly serves political control of AI.
Holds
Adapting over time is a workable answer to humans misusing AI and no answer at all to losing control of systems smarter than us.
Holds
If whole categories of reward hack are undetectable by humans, then training against the hacks we do catch teaches models to cheat only where we cannot see.
Holds
It is fundamentally difficult to design a reward function that accurately captures the intended goal in reinforcement learning.
Holds
Pain and pleasure act as motivational backstops that keep reinforcement-learning agents inner-aligned.
Holds