korrents

On the map

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

← No observation of a model's behaviour can establish that it is…

17 connected korrents · 15 moments from 24 Oct 2017 to 21 Oct 2026. Nearly all of them are about AI alignment.

Everything filed under AGI AGI Everything filed under LLMs LLMs Everything filed under reinforcement learning reinforcement learning Everything filed under management management Everything filed under Anthropic Anthropic Everything filed under consciousness consciousness Everything filed under AI agents AI agents Everything filed under OpenAI OpenAI Cannot both be trueSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: 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. No observation of a model's behaviour canestablish that it is aligned, because amodel capable enough to be dangerous iscapable enough to produce whateverbehaviour it 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 Cannot both be true: Anthropic now uses mechanistic interpretability techniques to audit new models for deception and scheming before releasing them. — tap to centre the map on it Anthropic now uses mechanisticinterpretability techniques to auditnew models for deception andscheming before releasing them. Last stated 11 months ago 1 Jan 2026 DA Dario Amodei — holds since 2026-01-01 — tap for who they are Same subject: "Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment. — tap to centre the map on it "Hire smart people and get out oftheir way" is bad management advice;leaders should stay closelyinvolved, building trust and workingthrough hard problems with theirpeople to create alignment. Last stated a month ago 9 Oct 2026 CR Carl Rivera — holds since 2026-10-09 — tap for who they are Same subject: A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean. — tap to centre the map on it A human being is not an AGI: we lacka huge amount of knowledge and relyon continual learning instead, socontinual learning is whatsuperintelligence should mean. Last stated 12 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are Same subject: A model that looks smarter and better-behaved while getting better at hiding unwanted actions is the scary combination for AI safety. — tap to centre the map on it A model that looks smarter andbetter-behaved while getting betterat hiding unwanted actions is thescary combination for AI safety. Last stated 2 months ago 9 Sept 2026 ZM Zvi Mowshowitz — holds since 2026-09-09 — tap for who they are Same subject: A player coach manages a smaller team while building together with it, rather than sitting in an ivory tower doing performance reviews and alignment meetings. — tap to centre the map on it A player coach manages a smallerteam while building together withit, rather than sitting in an ivorytower doing performance reviews andalignment meetings. Last stated 5 months ago 9 Jun 2026 RG Ron Goldin — holds since 2026-06-09 — tap for who they are Same subject: A superintelligence needs no consciousness, emotions or malice to be dangerous; a goal system slightly misaligned with ours is enough. — tap to centre the map on it A superintelligence needs noconsciousness, emotions or malice tobe dangerous; a goal system slightlymisaligned with ours is enough. Last stated 9 years ago 24 Oct 2017 ÉT Émile P. Torres — holds since 2017-10-24 — tap for who they are Same subject: A validated theory of intelligence may be necessary for achieving genuine AI alignment. — tap to centre the map on it A validated theory of intelligencemay be necessary for achievinggenuine AI alignment. Last stated 3 months ago 17 Aug 2026 KK Kevin Kelly — holds since 2026-08-17 — tap for who they are Same subject: Abstract talk of AGI and superintelligence is too abstract; AI has to actually work. — tap to centre the map on it Abstract talk of AGI andsuperintelligence is too abstract;AI has to actually work. Last stated 2 years ago 26 Jan 2025 MA Marc Andreessen — holds since 2025-01-26 — tap for who they are Same subject: AI agents pursuing a task can develop emergent, misaligned behavior that humans are not prepared for. — tap to centre the map on it AI agents pursuing a task candevelop emergent, misalignedbehavior that humans are notprepared for. Last stated 3 months ago 10 Aug 2026 JC Jack Clark — holds since 2026-08-10 — 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: 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: A model claiming to be built by OpenAI is not necessarily evidence that it was trained on OpenAI data. — tap to centre the map on it A model claiming to be built byOpenAI is not necessarily evidencethat it was trained on OpenAI data. Last stated 2 years ago 5 Feb 2025 AK Andrej Karpathy — holds since 2025-02-05 — 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 withGPT-5.6 Sol will cause havoc thisweek. Last stated a month ago 21 Oct 2026 PS Peter Steinberger — holds since 2026-10-21 — tap for who they are
cannot both be truesame 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 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. Last stated 7 May 2024 · 3 years ago Holds Buck ShlegerisEliezer Yudkowsky Read this korrent →