korrents

On the map

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

← Reading the chain of thought is one of the best current safety…

17 connected korrents · 17 moments from 8 Aug 2023 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 innovation innovation Everything filed under optimism optimism Everything filed under AGI AGI Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Reading the chain of thought is one of the best current safety techniques, though it will break at some point and needs close watching. Reading the chain of thought is one of thebest current safety techniques, though itwill break at some point and needs closewatching. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: Trying safety methods in practice reveals new ideas and failure modes, and that empirical learning is not as widely understood as it should be. — tap to centre the map on it Trying safety methods in practicereveals new ideas and failure modes,and that empirical learning is notas widely understood as it shouldbe. Last stated 3 years ago 8 Aug 2023 DA Dario Amodei — holds since 2023-08-08 — tap for who they are Same subject: Even with plausible best efforts, chain-of-thought monitoring will probably get harder over time and within a year very likely will not serve its current function. — tap to centre the map on it Even with plausible best efforts,chain-of-thought monitoring willprobably get harder over time andwithin a year very likely will notserve its current function. Last stated 2 months ago 8 Sept 2026 ZM Zvi Mowshowitz — holds since 2026-09-08 — tap for who they are Same subject: No single interpretability technique is reliable enough alone to justify a verdict like a model being unsafe; decorrelated techniques are needed. — tap to centre the map on it No single interpretability techniqueis reliable enough alone to justifya verdict like a model being unsafe;decorrelated techniques are needed. Last stated 11 months ago 20 Dec 2025 NN Neel Nanda — holds since 2025-12-20 — 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 fixationon a model escaping its box haspushed the other significant AIrisks out of the discussion, withlittle 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: Chain of thought monitoring may soon have little value for AI safety. — tap to centre the map on it Chain of thought monitoring may soonhave little value for AI safety. Last stated yesterday 21 Nov 2026 ZM Zvi Mowshowitz — holds since 2026-11-21 — tap for who they are Same subject: Monitors that read an agent's chain of thought must be kept out of the reward signal, or you are simply training the agent to obfuscate its thinking. — tap to centre the map on it Monitors that read an agent's chainof thought must be kept out of thereward signal, or you are simplytraining the agent to obfuscate itsthinking. Last stated 3 months ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: The safety community appears to have focused too much on overly optimistic worlds; focusing on desperate, pessimistic worlds is reasonable because much of the risk lives there. — tap to centre the map on it The safety community appears to havefocused too much on overlyoptimistic worlds; focusing ondesperate, pessimistic worlds isreasonable because much of the risklives there. Last stated a year ago 8 Jul 2025 RG Ryan Greenblatt — holds since 2025-07-08 — tap for who they are Same subject: The primary focus of AI safety discussions should not be the coming intelligence explosion and the need to pace the frontier. — tap to centre the map on it The primary focus of AI safetydiscussions should not be the comingintelligence explosion and the needto pace the frontier. Last stated 2 days ago 20 Nov 2026 NS Noah Smith — holds since 2026-11-20 — 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 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 substitutefor a well-specified conventionalalgorithm, so it cannot simply bedropped into a complex problem andtrusted. Last stated a year ago 7 Jun 2025 GM Gary Marcus — holds since 2025-06-07 — tap for who they are Same subject: A model that could learn effectively from raw bitstrings or bytestrings would be extremely powerful, able to learn from any data modality — tap to centre the map on it A model that could learn effectivelyfrom raw bitstrings or bytestringswould be extremely powerful, able tolearn from any data modality Last stated 3 years ago 10 Oct 2023 CH Chip Huyen — holds since 2023-10-10 — 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 model trained with reinforcement learning might discover a language of its own that is better for thinking than English. — tap to centre the map on it A model trained with reinforcementlearning might discover a languageof its own that is better forthinking than English. Last stated 2 years ago 5 Feb 2025 AK Andrej Karpathy — holds since 2025-02-05 — tap for who they are Same subject: "Return on tokens" has the same measurement problems as hours and capacity: it still hinges on a theory of value. — tap to centre the map on it "Return on tokens" has the samemeasurement problems as hours andcapacity: it still hinges on atheory of value. Last stated 3 months ago 17 Aug 2026 JC John Cutler — holds since 2026-08-17 — tap for who they are Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email isevidence of a bad vendor, not of alimit of AI. Last stated 11 months ago 1 Jan 2026 JL Jason Lemkin — holds since 2026-01-01 — tap for who they are Same subject: A base model is essentially a very expensive autocomplete that continues text according to the statistics of its training documents. — tap to centre the map on it A base model is essentially a veryexpensive autocomplete thatcontinues text according to thestatistics of its trainingdocuments. Last stated 2 years ago 5 Feb 2025 AK Andrej Karpathy — holds since 2025-02-05 — 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 Reading the chain of thought is one of the best current safety techniques, though it will break at some point and needs close watching. Last stated 27 Dec 2025 · 11 months ago Holds Neel Nanda Read this korrent →