Tap a claim on the ring to put it at the centre.
← Training models to stop a bad behaviour and showing they no longer…
17 connected korrents · 13 moments from 12 May 2023 to 3 Nov 2026.
Everything filed under AI alignment
AI alignment
Everything filed under AGI
AGI
Everything filed under AI agents
AI agents
Everything filed under OpenAI
OpenAI
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: Training models to stop a bad behaviour and showing they no longer display it on a new dataset is not enough to show they are safe.
Training models to stop a bad behaviour and showing they no longer display it on a new dataset is not enough to show they are safe.
Last stated 4 years ago
12 May 2023
AC
Ajeya Cotra — holds since 2023-05-12 — tap for who they are
Same subject: If a model answers every rollout correctly all the time, training might as well stop, because there is no learning signal left. — tap to centre the map on it
If a model answers every rollout correctly all the time, training might as well stop, because there is no learning signal left.
Last stated a month ago
10 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-10 — tap for who they are
Same subject: Removing problematic training data and environments is better than adding training to patch a behavior out, which may only suppress it. — tap to centre the map on it
Removing problematic training data and environments is better than adding training to patch a behavior out, which may only suppress it.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — tap for who they are
Same subject: Safety evaluations should report over-refusal, since a model that always refuses would be trivially safe. — tap to centre the map on it
Safety evaluations should report over-refusal, since a model that always refuses would be trivially safe.
Last stated 11 months ago
27 Dec 2025
NN
Neel Nanda — holds since 2025-12-27 — tap for who they are
Same subject: Current models are unsafe because they are not smart enough, not because they are too smart. — tap to centre the map on it
Current models are unsafe because they are not smart enough, not because they are too smart.
Last stated 2 months ago
13 Sept 2026
FC
François Chollet — holds since 2026-09-13 — tap for who they are
Same subject: It is never a bad idea to check your training data, because data is often the most precious thing and errors in it give poor results. — tap to centre the map on it
It is never a bad idea to check your training data, because data is often the most precious thing and errors in it give poor results.
Last stated a month ago
17 Oct 2026
SR
Sebastian Raschka — holds since 2026-10-17 — tap for who they are
Same subject: ML researchers may be underrating how much pressure there will be to move to less safe training strategies once their advantage over safer ones becomes apparent. — tap to centre the map on it
ML researchers may be underrating how much pressure there will be to move to less safe training strategies once their advantage over safer ones becomes apparent.
Last stated 4 years ago
12 May 2023
AC
Ajeya Cotra — holds since 2023-05-12 — tap for who they are
Same subject: The risk of AI behavior being unpredictable can be managed and trained out of models. — tap to centre the map on it
The risk of AI behavior being unpredictable can be managed and trained out of models.
Last stated a month ago
19 Oct 2026
SN
Steven Novella — holds since 2026-10-19 — 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: 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 PHP vulnerability found with GPT-5.6 Sol will cause havoc this week. — tap to centre the map on it
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Last stated a month ago
21 Oct 2026
PS
Peter Steinberger — holds since 2026-10-21 — 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: 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 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
Training models to stop a bad behaviour and showing they no longer display it on a new dataset is not enough to show they are safe.
Last stated 12 May 2023 · 4 years ago
Holds Ajeya Cotra
Read this korrent →
Similar wording
If a model answers every rollout correctly all the time, training might as well stop, because there is no learning signal left.
Last stated 10 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
Removing problematic training data and environments is better than adding training to patch a behavior out, which may only suppress it.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Similar wording
Safety evaluations should report over-refusal, since a model that always refuses would be trivially safe.
Last stated 27 Dec 2025 · 11 months ago
Holds Neel Nanda
Similar wording
Current models are unsafe because they are not smart enough, not because they are too smart.
Last stated 13 Sept 2026 · 2 months ago
Holds François Chollet
Similar wording
It is never a bad idea to check your training data, because data is often the most precious thing and errors in it give poor results.
Last stated 17 Oct 2026 · a month ago
Holds Sebastian Raschka
Similar wording
ML researchers may be underrating how much pressure there will be to move to less safe training strategies once their advantage over safer ones becomes apparent.
Last stated 12 May 2023 · 4 years ago
Holds Ajeya Cotra
Similar wording
The risk of AI behavior being unpredictable can be managed and trained out of models.
Last stated 19 Oct 2026 · a month ago
Holds Steven Novella
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
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: OpenAI
A PHP vulnerability found with GPT-5.6 Sol will cause havoc this week.
Last stated 21 Oct 2026 · a month ago
Holds Peter Steinberger
Same subject: OpenAI
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 18 Mar 2024 · 3 years ago
Holds Sam Altman
Same subject: OpenAI
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 18 Mar 2024 · 3 years ago
Holds Sam Altman