korrents

On the map

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

← With very little political will, work might cut takeover risk from…

17 connected korrents · 17 moments from 27 Sept 2022 to 10 Oct 2026.

Everything filed under AI alignment AI alignment Everything filed under LLMs LLMs Everything filed under reinforcement learning reinforcement learning Everything filed under ambition ambition Everything filed under investing investing Everything filed under startups startups 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: With very little political will, work might cut takeover risk from about 50% to 40%; with a year of delay, control might cut it from about 30% to 5%. With very little political will, workmight cut takeover risk from about 50% to40%; with a year of delay, control mightcut it from about 30% to 5%. Last stated a year ago 8 Jul 2025 RG Ryan Greenblatt — holds since 2025-07-08 — tap for who they are Same subject: Each year of delay costs a person about ten percent of their prime risk-taking years. — tap to centre the map on it Each year of delay costs a personabout ten percent of their primerisk-taking years. Last stated a year ago 16 Oct 2025 NE Nat Eliason — holds since 2025-10-16 — tap for who they are Same subject: Risk can be reduced without reducing returns by structuring bets in a more diversified way. — tap to centre the map on it Risk can be reduced without reducingreturns by structuring bets in amore diversified way. Last stated 4 years ago 27 Sept 2022 RD Ray Dalio — holds since 2022-09-27 — tap for who they are Same subject: The most likely bad outcome is not a takeover but a gradual loss of control and understanding, as fewer and fewer people understand what we have layered everywhere. — tap to centre the map on it The most likely bad outcome is not atakeover but a gradual loss ofcontrol and understanding, as fewerand fewer people understand what wehave layered everywhere. Last stated a year ago 17 Oct 2025 AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail. — tap to centre the map on it A control evaluation that reportsunder one per cent risk should beread as several per cent, becausethe evaluation can itself fail. Last stated 3 years ago 7 May 2024 BS Buck Shlegeris — holds since 2024-05-07 — tap for who they are Same subject: We cannot know how much safety a control measure buys until we understand elicitation, so control adds a margin of unknown size. — tap to centre the map on it We cannot know how much safety acontrol measure buys until weunderstand elicitation, so controladds a margin of unknown size. Last stated 2 years ago 24 Jan 2025 JL Jan Leike — holds since 2025-01-24 — tap for who they are Same subject: There will probably be a few steps between GPT-4 and AI that could pose a takeover risk, in a ramp-up that is terrifyingly fast but fairly continuous. — tap to centre the map on it There will probably be a few stepsbetween GPT-4 and AI that could posea takeover risk, in a ramp-up thatis terrifyingly fast but fairlycontinuous. Last stated 4 years ago 12 May 2023 AC Ajeya Cotra — holds since 2023-05-12 — tap for who they are Same subject: Giving an AI long-run values risks those values sinking in deeper than the specific prohibitions against takeover that sit alongside them. — tap to centre the map on it Giving an AI long-run values risksthose values sinking in deeper thanthe specific prohibitions againsttakeover that sit alongside them. Last stated 3 months ago 11 Aug 2026 RG Ryan Greenblatt — holds since 2026-08-11 — tap for who they are Same subject: Bold risk-taking and conservative paranoia can work together, as when Gates pursued an audacious vision while wanting a year of payroll in cash, combining getting rich with staying rich. — tap to centre the map on it Bold risk-taking and conservativeparanoia can work together, as whenGates pursued an audacious visionwhile wanting a year of payroll incash, combining getting rich withstaying rich. Last stated 2 years ago 28 May 2024 MH Morgan Housel — holds since 2024-05-28 — 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 With very little political will, work might cut takeover risk from about 50% to 40%; with a year of delay, control might cut it from about 30% to 5%. Last stated 8 Jul 2025 · a year ago Holds Ryan Greenblatt Read this korrent →