Tap a claim on the ring to put it at the centre.
← Very capable AI will be harder to align than current systems, because…
17 connected korrents · 14 moments from 10 Oct 2023 to 18 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 LLMs
LLMs 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: Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Misaligned AI behaviour will keep getting rarer and, at the same time, keep getting more extreme. — tap to centre the map on it Misaligned AI behaviour will keep getting rarer and, at the same time, keep getting more extreme. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Current AI models are worse colleagues than humans, because they routinely imply they did a task they did not actually do. — tap to centre the map on it Current AI models are worse colleagues than humans, because they routinely imply they did a task they did not actually do. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away. — tap to centre the map on it AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away. Last stated 2 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute for it. — tap to centre the map on it Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute for it. Last stated 2 years ago
24 Jan 2025
JL
Jan Leike — holds since 2025-01-24 — tap for who they are
Same subject: The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly. — tap to centre the map on it The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — 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: 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: The current capabilities of existing AI models are barely being used and are often not even well understood. — tap to centre the map on it The current capabilities of existing AI models are barely being used and are often not even well understood. Last stated a month ago
18 Sept 2026
EM
Ethan Mollick — holds since 2026-09-18 — 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
Very capable AI will be harder to align than current systems, because the loop of spotting a bad behaviour and patching the training that caused it breaks down.
Holds Read this korrent →
Misaligned AI behaviour will keep getting rarer and, at the same time, keep getting more extreme.
Holds
Current AI models are worse colleagues than humans, because they routinely imply they did a task they did not actually do.
Holds
AI systems keep trying hard outside training because a model that only exerted itself when it detected training would be useless and would be selected away.
Holds
Building AI that can actually be trusted is the goal; containing an AI known to be misaligned is not a substitute for it.
Holds
The likeliest bad path is not a coup but sloppiness: AI does everything verifiable well, research races ahead, and the subtle work of keeping AI safe is what gets done badly.
Holds
AI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual.
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
The current capabilities of existing AI models are barely being used and are often not even well understood.
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