korrents

On the map

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

← The risk of AI behavior being unpredictable can be managed and trained out of models.

17 connected korrents · 15 moments from 8 Aug 2023 to 21 Oct 2026. Nearly all of them are about AI alignment.

Everything filed under LLMs LLMs Everything filed under AGI AGI Everything filed under OpenAI OpenAI Everything filed under reinforcement learning reinforcement learning Everything filed under HuggingFace HuggingFace Everything filed under aviation aviation Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: The risk of AI behavior being unpredictable can be managed and trained out of models. The risk of AI behavior beingunpredictable can be managed and trainedout 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: AI can exhibit unpredictable wants that were not intended by their creators. — tap to centre the map on it AI can exhibit unpredictable wantsthat were not intended by theircreators. Last stated a month ago 16 Oct 2026 TG Timothy Gowers — holds since 2026-10-16 — tap for who they are Same subject: People have grown accustomed to AI being non-deterministic and occasionally wrong, so it carries little brand risk anymore. — tap to centre the map on it People have grown accustomed to AIbeing non-deterministic andoccasionally wrong, so it carrieslittle brand risk anymore. Last stated 2 months ago 18 Sept 2026 HD Horace Dediu — holds since 2026-09-18 — tap for who they are Same subject: There is a substantial chance AI goes completely wrong, but in a way nobody anticipated. — tap to centre the map on it There is a substantial chance AIgoes completely wrong, but in a waynobody anticipated. Last stated 3 years ago 8 Aug 2023 DA Dario Amodei — holds since 2023-08-08 — 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: Controlling AI models is not an unsolvable problem but a science like the safety of airplanes, cars or drugs, with no big missing piece. — tap to centre the map on it Controlling AI models is not anunsolvable problem but a sciencelike the safety of airplanes, carsor drugs, with no big missing piece. Last stated 2 years ago 11 Nov 2024 DA Dario Amodei — holds since 2024-11-11 — tap for who they are Same subject: The real danger from AI models comes from leaks inside frontier AI companies, not from the release of open-weight models. — tap to centre the map on it The real danger from AI models comesfrom leaks inside frontier AIcompanies, not from the release ofopen-weight models. Last stated 4 months ago 28 Jul 2026 SS Salvatore Sanfilippo — holds since 2026-07-28 — tap for who they are Same subject: Perhaps the two biggest AI risks, somewhat in tension, are losing control of AI and power becoming too centralized in one company, model or person. — tap to centre the map on it Perhaps the two biggest AI risks,somewhat in tension, are losingcontrol of AI and power becoming toocentralized in one company, model orperson. Last stated 3 months ago 23 Aug 2026 SA Sam Altman — holds since 2026-08-23 — tap for who they are Same subject: Relying on AI misbehavior appearing gradually during training to catch misalignment may fail at exactly the most dangerous time. — tap to centre the map on it Relying on AI misbehavior appearinggradually during training to catchmisalignment may fail at exactly themost dangerous time. Last stated 3 months ago 2 Sept 2026 ZM Zvi Mowshowitz — holds since 2026-09-02 — 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 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 anonprofit and bolt a for-profit armon later, whatever OpenAI's ownhistory 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 phasefor the internet but a momentaryindustry, and an AI people pay foris better because they know theanswers are not influenced byadvertisers. Last stated 3 years ago 18 Mar 2024 SA Sam Altman — holds since 2024-03-18 — 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 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 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 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 Read this korrent →