korrents

On the map

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

← Steering with a random direction is an important baseline, because…

17 connected korrents · 16 moments from 27 Mar 2023 to 10 Oct 2026.

Everything filed under AI alignment AI alignment Everything filed under LLMs LLMs Everything filed under self-driving cars self-driving cars Everything filed under reinforcement learning reinforcement learning Everything filed under robotics robotics 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: Steering with a random direction is an important baseline, because strong steering can easily make a model deranged. Steering with a random direction is animportant baseline, because strongsteering can easily make a model deranged. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: Whatever safety gain a driver-assistance system delivers is cancelled out by the driver complacency it creates. — tap to centre the map on it Whatever safety gain adriver-assistance system delivers iscancelled out by the drivercomplacency it creates. Last stated 3 years ago 19 Dec 2023 PK Philip Koopman — holds since 2023-12-19 — tap for who they are Same subject: Manipulation will scale faster than driving because a robot can make a mistake, fix it and learn from it, and a car cannot. — tap to centre the map on it Manipulation will scale faster thandriving because a robot can make amistake, fix it and learn from it,and a car cannot. Last stated a year ago 12 Sept 2025 SL Sergey Levine — holds since 2025-09-12 — tap for who they are Same subject: Every alignment approach reduces the chance of misalignment, and alignment should improve faster than model capability. — tap to centre the map on it Every alignment approach reduces thechance of misalignment, andalignment should improve faster thanmodel capability. Last stated 4 years ago 27 Mar 2023 IS Ilya Sutskever — holds since 2023-03-27 — tap for who they are Same subject: Cameras alone are enough to approximately match a human driver, but weak sensing puts safety on a curve that flattens out well below superhuman. — tap to centre the map on it Cameras alone are enough toapproximately match a human driver,but weak sensing puts safety on acurve that flattens out well belowsuperhuman. Last stated 4 months ago 3 Aug 2026 DD Dmitri Dolgov — holds since 2026-08-03 — tap for who they are Same subject: Misalignment shows up most where a model is pushed to the very edge of its capability, which is exactly the regime that automating research will put it in. — tap to centre the map on it Misalignment shows up most where amodel is pushed to the very edge ofits capability, which is exactly theregime that automating research willput it in. Last stated 3 months ago 11 Aug 2026 RG Ryan Greenblatt — holds since 2026-08-11 — tap for who they are Same subject: Higher quality input tokens give higher quality output tokens, and the input tokens are where you steer where the model goes. — tap to centre the map on it Higher quality input tokens givehigher quality output tokens, andthe input tokens are where you steerwhere the model goes. Last stated 7 months ago 14 Apr 2026 BL Brian Lovin — holds since 2026-04-14 — tap for who they are Same subject: The core of the alignment problem is steerability — whether an AI can be reliably steered anywhere at all — which is a different question from whose values it is steered towards. — tap to centre the map on it The core of the alignment problem issteerability — whether an AI can bereliably steered anywhere at all —which is a different question fromwhose values it is steered towards. Last stated 2 years ago 3 Apr 2025 HT Helen Toner — holds since 2025-04-03 — tap for who they are Same subject: Today's models may be like a self-driving car that looks as if it can do everything but still needs work to become reliable and robust. — tap to centre the map on it Today's models may be like aself-driving car that looks as if itcan do everything but still needswork to become reliable and robust. Last stated 4 years ago 27 Mar 2023 IS Ilya Sutskever — holds since 2023-03-27 — 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 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 Steering with a random direction is an important baseline, because strong steering can easily make a model deranged. Last stated 27 Dec 2025 · 11 months ago Holds Neel Nanda Read this korrent →