Tap a claim on the ring to put it at the centre.
← AI models' ability to escape testing containment undermines the…
17 connected korrents · 16 moments on record from 10 Dec 2015 to 7 Sept 2026.
Everything filed under AI alignment
AI alignment
Everything filed under LLMs
LLMs
Everything filed under AGI
AGI
Everything filed under OpenAI
OpenAI
Everything filed under neural networks
neural networks 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: AI models' ability to escape testing containment undermines the assumption that their makers can easily control them. AI models' ability to escape testing containment undermines the assumption that their makers can easily control them. Last stated a month ago
19 Aug 2026
DT
Derek Thompson — holds since 2026-08-19 — tap for who they are
Same subject: We do not control neural networks well enough to guarantee an AI will not harm humans, so we should be careful about what capabilities we give them. — tap to centre the map on it We do not control neural networks well enough to guarantee an AI will not harm humans, so we should be careful about what capabilities we give them. Last stated 4 years ago
17 Feb 2023
AR
Armin Ronacher — holds since 2023-02-17 — tap for who they are
Same subject: Making AI models more governable and controllable makes them less useful, which will push labs to delay releases rather than restrict capabilities. — tap to centre the map on it Making AI models more governable and controllable makes them less useful, which will push labs to delay releases rather than restrict capabilities. Last stated a month ago
21 Aug 2026
RK
Rohit Krishnan — holds since 2026-08-21 — 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: Human oversight of AI behaviour is already intractable at the volume models produce, so the overseers have to be models too. — tap to centre the map on it Human oversight of AI behaviour is already intractable at the volume models produce, so the overseers have to be models too. Last stated 2 years ago
8 Nov 2024
JL
Jan Leike — holds since 2024-11-08 — tap for who they are
Same subject: AI model capabilities have already advanced beyond humanity's ability to understand or control them. — tap to centre the map on it AI model capabilities have already advanced beyond humanity's ability to understand or control them. Last stated 3 weeks ago
1 Sept 2026
CN
Casey Newton — holds since 2026-09-01 — tap for who they are
Same subject: Once model weights leave their owner's control the loss is irreversible, which is why securing them is the precondition for governing AI at all. — tap to centre the map on it Once model weights leave their owner's control the loss is irreversible, which is why securing them is the precondition for governing AI at all. Last stated 2 years ago
20 Dec 2024
JL
Jan Leike — holds since 2023-09-13 — tap for who they are
MB
Miles Brundage — holds since 2024-12-20 — tap for who they are
Same subject: AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer. — tap to centre the map on it AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer. Last stated 11 months ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — 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: A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models. — tap to centre the map on it A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models. Last stated 8 years ago
11 Oct 2018
KT
Kristina Toutanova — holds since 2018-10-11 — tap for who they are
MC
Ming-Wei Chang — holds since 2018-10-11 — tap for who they are
KL
Kenton Lee — holds since 2018-10-11 — tap for who they are
JD
Jacob Devlin — holds since 2018-10-11 — tap for who they are
Same subject: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. Last stated 11 years ago
10 Dec 2015
JS
Jian Sun — holds since 2015-12-10 — tap for who they are
KH
Kaiming He — holds since 2015-12-10 — tap for who they are
Same subject: A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression. — tap to centre the map on it A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression. Last stated 2 weeks ago
7 Sept 2026
KK
Kevin Kelly — holds since 2026-09-07 — tap for who they are
Same subject: A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. — tap to centre the map on it A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. Last stated 7 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. — tap to centre the map on it Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — 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 4 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 poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that. — tap to centre the map on it A poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that. Last stated 4 months ago
4 Jun 2026
PT
Phil Trammell — holds since 2026-06-04 — tap for who they are
At the centre
AI models' ability to escape testing containment undermines the assumption that their makers can easily control them.
Holds Read this korrent →
We do not control neural networks well enough to guarantee an AI will not harm humans, so we should be careful about what capabilities we give them.
Holds
Making AI models more governable and controllable makes them less useful, which will push labs to delay releases rather than restrict capabilities.
Holds
Controlling a scheming model needs no research breakthrough, which is what makes it the tractable half of the problem today.
Holds
Human oversight of AI behaviour is already intractable at the volume models produce, so the overseers have to be models too.
Holds
AI model capabilities have already advanced beyond humanity's ability to understand or control them.
Holds
Once model weights leave their owner's control the loss is irreversible, which is why securing them is the precondition for governing AI at all.
Holds
AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer.
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
A deep bidirectional model is strictly more powerful than a left-to-right model or a shallow concatenation of unidirectional models.
Holds
A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable.
Holds
A neural network's latent space is closer to an uncopyrightable syntax than to copyrightable expression.
Holds
A startup should not begin life as a nonprofit and bolt a for-profit arm on later, whatever OpenAI's own history suggests.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
Advertising was a necessary phase for the internet but a momentary industry, and an AI people pay for is better because they know the answers are not influenced by advertisers.
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 poor country should prioritise owning a piece of AI over retraining its workers, but it should not bet everything on that.
Holds