Tap a claim on the ring to put it at the centre.
← Alignment failures that matter will not show up at safe capability…
17 connected korrents · 19 moments from 24 Oct 2017 to 10 Sept 2026. Nearly all of them are about AI alignment .
Everything filed under AGI
AGI
Everything filed under management
management
Everything filed under consciousness
consciousness
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: Alignment failures that matter will not show up at safe capability levels, because the reason to hide misbehaviour only exists once hiding it pays. Alignment failures that matter will not show up at safe capability levels, because the reason to hide misbehaviour only exists once hiding it pays. Last stated 4 years ago
10 Jun 2022
EY
Eliezer Yudkowsky — holds since 2022-06-10 — 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 model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety. — tap to centre the map on it A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety. Last stated 2 months ago
9 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-09 — tap for who they are
Same subject: A player coach manages a smaller team while building together with it, rather than sitting in an ivory tower doing performance reviews and alignment meetings. — tap to centre the map on it A player coach manages a smaller team while building together with it, rather than sitting in an ivory tower doing performance reviews and alignment meetings. Last stated 5 months ago
9 Jun 2026
RG
Ron Goldin — holds since 2026-06-09 — tap for who they are
Same subject: A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. — tap to centre the map on it A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. Last stated 9 years ago
24 Oct 2017
ÉT
Émile P. Torres — holds since 2017-10-24 — tap for who they are
Same subject: A validated theory of intelligence may be necessary for achieving genuine AI alignment. — tap to centre the map on it A validated theory of intelligence may be necessary for achieving genuine AI alignment. Last stated 2 months ago
17 Aug 2026
KK
Kevin Kelly — holds since 2026-08-17 — tap for who they are
Same subject: AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. — tap to centre the map on it AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. Last stated 3 months ago
10 Aug 2026
JC
Jack Clark — holds since 2026-08-10 — tap for who they are
Same subject: AI alignment is a red herring not worth the effort currently devoted to it. — tap to centre the map on it AI alignment is a red herring not worth the effort currently devoted to it. Last stated 3 months ago
8 Aug 2026
MW
Matt Webb — holds since 2026-08-08 — tap for who they are
Same subject: AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual. — tap to centre the map on it AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual. Last stated 2 months ago
21 Aug 2026
RK
Rohit Krishnan — holds since 2026-08-21 — 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: AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. — tap to centre the map on it AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. Last stated 2 years ago
2 Feb 2025
AC
Ajeya Cotra — holds since 2023-08-29 — tap for who they are
SA
Scott Alexander — holds since 2022-09-12 — tap for who they are
MB
Miles Brundage — holds since 2025-02-02 — tap for who they are
Same subject: AI progress is jagged: models are becoming superhuman at math and software engineering while remaining far weaker at intuition, creativity, and other forms of human reasoning. — tap to centre the map on it AI progress is jagged: models are becoming superhuman at math and software engineering while remaining far weaker at intuition, creativity, and other forms of human reasoning. Last stated 2 months ago
10 Sept 2026
NL
Nathan Lambert — holds since 2026-09-10 — tap for who they are
Same subject: Anyone who thinks large language models are a direct route to transformative AGI is kidding themselves. — tap to centre the map on it Anyone who thinks large language models are a direct route to transformative AGI is kidding themselves. Last stated a year ago
7 Jun 2025
GM
Gary Marcus — holds since 2025-06-07 — tap for who they are
Same subject: Scaling up GPT will never produce AGI, because a model trained on cross-entropy loss cannot get there; reinforcement learning in rich environments is required. — tap to centre the map on it Scaling up GPT will never produce AGI, because a model trained on cross-entropy loss cannot get there; reinforcement learning in rich environments is required. Last stated 3 years ago
29 Jun 2023
GH
George Hotz — holds since 2023-06-29 — tap for who they are
Same subject: Training AIs on millions of verifiable tasks in diverse RL environments will lead to AGI. — tap to centre the map on it Training AIs on millions of verifiable tasks in diverse RL environments will lead to AGI. Last stated 4 months ago
26 Jun 2026
DP
Dwarkesh Patel — holds since 2026-06-26 — 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
At the centre
Alignment failures that matter will not show up at safe capability levels, because the reason to hide misbehaviour only exists once hiding it pays.
Holds Read this korrent →
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 model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety.
Holds
A player coach manages a smaller team while building together with it, rather than sitting in an ivory tower doing performance reviews and alignment meetings.
Holds
A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough.
Holds
A validated theory of intelligence may be necessary for achieving genuine AI alignment.
Holds
AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for.
Holds
AI alignment is a red herring not worth the effort currently devoted to it.
Holds
AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual.
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
AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard.
Holds
AI progress is jagged: models are becoming superhuman at math and software engineering while remaining far weaker at intuition, creativity, and other forms of human reasoning.
Holds
Anyone who thinks large language models are a direct route to transformative AGI is kidding themselves.
Holds
Scaling up GPT will never produce AGI, because a model trained on cross-entropy loss cannot get there; reinforcement learning in rich environments is required.
Holds
Training AIs on millions of verifiable tasks in diverse RL environments will lead to AGI.
Holds
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Holds