korrents

On the map

Tap a claim on the ring to put it at the centre.

← Simple training interventions turned out to be very effective at steering models towards aligned behaviour.

17 connected korrents · 17 moments from 4 Mar 2022 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 Psychotherapy Psychotherapy Everything filed under reinforcement learning reinforcement learning Everything filed under computer vision computer vision Everything filed under LLMs LLMs Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Simple training interventions turned out to be very effective at steering models towards aligned behaviour. Simple training interventions turned outto be very effective at steering modelstowards aligned behaviour. Last stated 10 months ago 22 Jan 2026 JL Jan Leike — holds since 2026-01-22 — tap for who they are Same subject: Training a therapist in a treatment model does not make them more effective, however well the model performs in a trial. — tap to centre the map on it Training a therapist in a treatmentmodel does not make them moreeffective, however well the modelperforms in a trial. Last stated 2 years ago 2 Jul 2024 SM Scott D. Miller — holds since 2024-07-02 — tap for who they are Same subject: No observation of a model's behaviour can establish that it is aligned, because a model capable enough to be dangerous is capable enough to produce whatever behaviour it is being watched for. — tap to centre the map on it No observation of a model'sbehaviour can establish that it isaligned, because a model capableenough to be dangerous is capableenough to produce whatever behaviourit is being watched for. Last stated 3 years ago 7 May 2024 BS Buck Shlegeris — holds since 2024-05-07 — tap for who they are EY Eliezer Yudkowsky — holds since 2022-06-10 — tap for who they are Same subject: All therapies that work do so by promoting the same few skills: openness, awareness and engagement. — tap to centre the map on it All therapies that work do so bypromoting the same few skills:openness, awareness and engagement. Last stated a year ago 22 Sept 2025 SH Steven C. Hayes — holds since 2025-09-22 — tap for who they are Same subject: The finding that simple models with lots of data win was to her a sweet lesson, and the reason she built ImageNet. — tap to centre the map on it The finding that simple models withlots of data win was to her a sweetlesson, and the reason she builtImageNet. Last stated a year ago 16 Nov 2025 FL Fei-Fei Li — holds since 2025-11-16 — tap for who they are Same subject: Giving a language model a few concrete examples, not only a description of the task, makes it more accurate. — tap to centre the map on it Giving a language model a fewconcrete examples, not only adescription of the task, makes itmore accurate. Last stated 2 years ago 27 Feb 2025 AK Andrej Karpathy — holds since 2025-02-27 — tap for who they are Same subject: What does make a therapist more effective is trainable interpersonal skill, not treatment technology. — tap to centre the map on it What does make a therapist moreeffective is trainable interpersonalskill, not treatment technology. Last stated 2 years ago 2 Jul 2024 SM Scott D. Miller — holds since 2024-07-02 — tap for who they are Same subject: Training a model on principles rather than a list of rules is not an ideology but an empirical finding: its behaviour is more consistent and covers edge cases. — tap to centre the map on it Training a model on principlesrather than a list of rules is notan ideology but an empiricalfinding: its behaviour is moreconsistent and covers edge cases. Last stated 9 months ago 13 Feb 2026 DA Dario Amodei — holds since 2026-02-13 — tap for who they are Same subject: Fine-tuning with human feedback is a promising direction for aligning language models with human intent. — tap to centre the map on it Fine-tuning with human feedback is apromising direction for aligninglanguage models with human intent. Last stated 5 years ago 4 Mar 2022 JL Jan Leike — holds since 2022-03-04 — 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 supplychain should just buy the index —which works only in the world whereAI ends up commoditised rather thanconcentrated. 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 prioritiseowning a piece of AI over retrainingits workers, but it should not beteverything 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 enoughtests of intelligence would be ashard 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 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 addedwhen 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 areasoning model unless it has beentrained with reinforcement learningwith 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 threeAIs, not one — the agent, thesimulator and the critic — turningdeployment 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: 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 importantcontext an AI agent has, and lettingmany different models add to itwithout consistent patterns leads totrouble. 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 notautomatically form a functioningorganization any more than a groupof 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 recourseagainst them. Last stated 2 months ago 15 Sept 2026 TL Tobias Lütke — holds since 2026-09-15 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya face: someone who holds the claim — tap it for who they are

At the centre Simple training interventions turned out to be very effective at steering models towards aligned behaviour. Last stated 22 Jan 2026 · 10 months ago Holds Jan Leike Read this korrent →