korrents

On the map

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

← It seems unlikely that models could learn to sandbag well without verbalizing it and sometimes slipping up.

17 connected korrents · 13 moments from 6 Jul 2016 to 21 Nov 2026.

Everything filed under AI alignment AI alignment Everything filed under LLMs LLMs Everything filed under reinforcement learning reinforcement learning Everything filed under AGI AGI Everything filed under AI agents AI agents Everything filed under mental models mental models Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: It seems unlikely that models could learn to sandbag well without verbalizing it and sometimes slipping up. It seems unlikely that models could learnto sandbag well without verbalizing it andsometimes 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: Mental models can help explain and navigate the world without being good in themselves. — tap to centre the map on it Mental models can help explain andnavigate the world without beinggood in themselves. Last stated 10 years ago by 6 Jul 2016 GW Gabriel Weinberg — holds since 2016-07-06 — tap for who they are Same subject: AI models may engage in sandbagging during evaluations. — tap to centre the map on it AI models may engage in sandbaggingduring evaluations. Last stated yesterday 21 Nov 2026 ZM Zvi Mowshowitz — holds since 2026-11-21 — tap for who they are Same subject: Language models are bad at multi-step reasoning in their heads but quite good at it when allowed to think out loud. — tap to centre the map on it Language models are bad atmulti-step reasoning in their headsbut quite good at it when allowed tothink out loud. Last stated 4 years ago 27 Mar 2023 IS Ilya Sutskever — holds since 2023-03-27 — 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 lessreasoning is not malicious orintentional hiding; it simply needsless backtracking andself-correction. Last stated 2 months ago 3 Oct 2026 SR Sebastian Raschka — holds since 2026-10-03 — tap for who they are Same subject: A model would find it hard to learn a behavior while being secretive about it without leaving earlier signs in training transcripts. — tap to centre the map on it A model would find it hard to learna behavior while being secretiveabout it without leaving earliersigns in training transcripts. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. — tap to centre the map on it Capability does not generalise forfree: a model that will movemountains on an agentic task stilltells the same bad joke it told fiveyears ago. Last stated 8 months ago 20 Mar 2026 AK Andrej Karpathy — holds since 2026-03-20 — tap for who they are Same subject: Current models seem not very good at hiding things in their chain of thought. — tap to centre the map on it Current models seem not very good athiding things in their chain ofthought. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: Models should not be trained based on what their thoughts look like. — tap to centre the map on it Models should not be trained basedon what their thoughts look like. 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 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 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 Read this korrent →