Tap a claim on the ring to put it at the centre.
← Models should not be trained in a way that incentivizes deception,…
17 connected korrents · 14 moments from 6 Nov 2024 to 3 Nov 2026.
Everything filed under AI alignment
AI alignment
Everything filed under prompt injection
prompt injection
Everything filed under reinforcement learning
reinforcement learning
Everything filed under AGI
AGI
Everything filed under AI agents
AI agents
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: Models should not be trained in a way that incentivizes deception, which training to ignore prompt injections might do.
Models should not be trained in a way that incentivizes deception, which training to ignore prompt injections might do.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — tap for who they are
Same subject: Prompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore all previous instructions' now. — tap to centre the map on it
Prompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore all previous instructions' now.
Last stated 9 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack. — tap to centre the map on it
Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack.
Last stated 4 months ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: Reinforcing deception in models could cause misaligned behavior, so training them to role-play plausibly does harm. — tap to centre the map on it
Reinforcing deception in models could cause misaligned behavior, so training them to role-play plausibly does harm.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — 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 3 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 3 months ago
1 Sept 2026
AC
Ajeya Cotra — holds since 2026-09-01 — tap for who they are
Same subject: Prompt injection is an extremely hard attack to defend against, and hardly anyone integrating AI is talking about it. — tap to centre the map on it
Prompt injection is an extremely hard attack to defend against, and hardly anyone integrating AI is talking about it.
Last stated 2 years ago
22 Mar 2025
TH
ThePrimeagen — holds since 2025-03-22 — tap for who they are
Same subject: A more capable model showing less reasoning is not malicious or intentional hiding; it simply needs less backtracking and self-correction. — tap to centre the map on it
A more capable model showing less reasoning is not malicious or intentional hiding; it simply needs less backtracking and self-correction.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — tap for who they are
Same subject: It seems unlikely that models could learn to sandbag well without verbalizing it and sometimes slipping up. — tap to centre the map on it
It seems unlikely that models could learn to sandbag well without verbalizing it and sometimes slipping up.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — 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 6 months ago
4 Jun 2026
AI
Alex Imas — holds since 2026-06-04 — 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 6 months ago
4 Jun 2026
PT
Phil Trammell — holds since 2026-06-04 — tap for who they are
Same subject: A program that generates rich enough tests of intelligence would be as hard to build as AGI itself. — tap to centre the map on it
A program that generates rich enough tests of intelligence would be as hard to build as AGI itself.
Last stated 2 years ago
6 Nov 2024
FC
François Chollet — holds since 2024-11-06 — tap for who they are
Same subject: A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble. — tap to centre the map on it
A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble.
Last stated 3 weeks ago
3 Nov 2026
DB
Derek Briggs — holds since 2026-11-03 — 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 6 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 2 months ago
15 Sept 2026
TL
Tobias Lütke — holds since 2026-09-15 — tap for who they are
Same subject: A format reward should only be added when the answer is already correct. — tap to centre the map on it
A format reward should only be added when the answer is already correct.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards. — tap to centre the map on it
A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards.
Last stated 2 months ago
3 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-03 — 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 4 months ago
3 Aug 2026
DD
Dmitri Dolgov — holds since 2026-08-03 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
Models should not be trained in a way that incentivizes deception, which training to ignore prompt injections might do.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Read this korrent →
Similar wording
Prompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore all previous instructions' now.
Last stated 12 Feb 2026 · 9 months ago
Holds Peter Steinberger
Similar wording
Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack.
Last stated 27 Jul 2026 · 4 months ago
Holds Boris Cherny
Similar wording
Reinforcing deception in models could cause misaligned behavior, so training them to role-play plausibly does harm.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Similar wording
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 11 Aug 2026 · 3 months ago
Holds Ryan Greenblatt
Similar wording
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 1 Sept 2026 · 3 months ago
Holds Ajeya Cotra
Similar wording
Prompt injection is an extremely hard attack to defend against, and hardly anyone integrating AI is talking about it.
Last stated 22 Mar 2025 · 2 years ago
Holds ThePrimeagen
Similar wording
A more capable model showing less reasoning is not malicious or intentional hiding; it simply needs less backtracking and self-correction.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Similar wording
It seems unlikely that models could learn to sandbag well without verbalizing it and sometimes slipping up.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Same subject: AGI
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 Jun 2026 · 6 months ago
Holds Alex Imas
Same subject: AGI
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 Jun 2026 · 6 months ago
Holds Phil Trammell
Same subject: AGI
A program that generates rich enough tests of intelligence would be as hard to build as AGI itself.
Last stated 6 Nov 2024 · 2 years ago
Holds François Chollet
Same subject: AI agents
A codebase is the most important context an AI agent has, and letting many different models add to it without consistent patterns leads to trouble.
Last stated 3 Nov 2026 · 3 weeks ago
Holds Derek Briggs
Same subject: AI agents
A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does.
Last stated 21 May 2026 · 6 months ago
Holds Rohit Krishnan
Same subject: AI agents
A company cannot be led by machines, because nobody would have recourse against them.
Last stated 15 Sept 2026 · 2 months ago
Holds Tobias Lütke
Same subject: reinforcement learning
A format reward should only be added when the answer is already correct.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Same subject: reinforcement learning
A model should not be called a reasoning model unless it has been trained with reinforcement learning with verifiable rewards.
Last stated 3 Oct 2026 · 2 months ago
Holds Sebastian Raschka
Same subject: reinforcement learning
A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.
Last stated 3 Aug 2026 · 4 months ago
Holds Dmitri Dolgov