korrents

On the map

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

← The clip value of 10 taken from DeepSeek-R1 is large in practice; values such as 0.1 are more usual.

17 connected korrents · 17 moments from 1 Oct 2023 to 12 Nov 2026.

Everything filed under reinforcement learning reinforcement learning Everything filed under LLMs LLMs Everything filed under robotics robotics Everything filed under AI alignment AI alignment Everything filed under semiconductors semiconductors Everything filed under optimizers optimizers Everything filed under value investing value investing Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: The clip value of 10 taken from DeepSeek-R1 is large in practice; values such as 0.1 are more usual. The clip value of 10 taken fromDeepSeek-R1 is large in practice; valuessuch as 0.1 are more usual. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: Quoting a number for P(doom) is a ridiculous notion, because it implies a precision that nobody actually has. — tap to centre the map on it Quoting a number for P(doom) is aridiculous notion, because itimplies a precision that nobodyactually has. Last stated a year ago 23 Jul 2025 DH Demis Hassabis — holds since 2025-07-23 — tap for who they are Same subject: Falling back to older 7-nanometre chips would not rescue AI compute, because the real gap between chip generations is twentyfold, not the threefold the flops suggest. — tap to centre the map on it Falling back to older 7-nanometrechips would not rescue AI compute,because the real gap between chipgenerations is twentyfold, not thethreefold the flops suggest. Last stated 8 months ago 13 Mar 2026 DP Dylan Patel — holds since 2026-03-13 — tap for who they are Same subject: Gradient norm clipping guards against an unlucky bad batch producing a huge gradient that shocks the optimization. — tap to centre the map on it Gradient norm clipping guardsagainst an unlucky bad batchproducing a huge gradient thatshocks the optimization. Last stated 2 years ago 9 Jun 2024 AK Andrej Karpathy — holds since 2024-06-09 — tap for who they are Same subject: A teacher from the same model family likely distills better, because the student is more familiar with its prompt format and answer structure. — tap to centre the map on it A teacher from the same model familylikely distills better, because thestudent is more familiar with itsprompt format and answer structure. Last stated a month ago 17 Oct 2026 SR Sebastian Raschka — holds since 2026-10-17 — tap for who they are Same subject: Once a language model reads the results, search can trade precision for recall, because the model does not care that the right link came ninth. — tap to centre the map on it Once a language model reads theresults, search can trade precisionfor recall, because the model doesnot care that the right link cameninth. Last stated 2 years ago 19 Jun 2024 AS Aravind Srinivas — holds since 2024-06-19 — tap for who they are Same subject: The chances of significant AI risks are far greater than 10%. — tap to centre the map on it The chances of significant AI risksare far greater than 10%. Last stated a week ago 12 Nov 2026 ZM Zvi Mowshowitz — holds since 2026-11-12 — tap for who they are Same subject: Judging one model worse than another from a one-shot, probabilistic output on a given day is not a good way to evaluate it. — tap to centre the map on it Judging one model worse than anotherfrom a one-shot, probabilisticoutput on a given day is not a goodway to evaluate it. Last stated 6 months ago 19 May 2026 TG Tommy Geoco — holds since 2026-05-19 — tap for who they are Same subject: Keeping a valuation to 15 to 20 inputs lets you know what each input does, which a 400-line-item model does not. — tap to centre the map on it Keeping a valuation to 15 to 20inputs lets you know what each inputdoes, which a 400-line-item modeldoes not. Last stated 3 weeks ago 3 Nov 2026 AD Aswath Damodaran — holds since 2026-11-03 — 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: One pre-trained robot model now matches or beats the specialists that were fine-tuned with reinforcement learning for the very tasks they were built for. — tap to centre the map on it One pre-trained robot model nowmatches or beats the specialiststhat were fine-tuned withreinforcement learning for the verytasks they were built for. Last stated 3 months ago 12 Aug 2026 CF Chelsea Finn — holds since 2026-08-12 — tap for who they are Same subject: Reading RL transcripts after a post-training run to find problems in training environments seems a good general practice. — tap to centre the map on it Reading RL transcripts after apost-training run to find problemsin training environments seems agood general practice. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — tap for who they are Same subject: RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does. — tap to centre the map on it RL environments exist to make amodel generalise, not to teach iteach skill one at a time — exactlyas pre-training does. Last stated 9 months ago 13 Feb 2026 DA Dario Amodei — holds since 2026-02-13 — tap for who they are Same subject: Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. — tap to centre the map on it Reinforcement learning only worksonce a model already knowssomething, which is why robots mustbe pre-trained by imitation first. Last stated a year ago 12 Sept 2025 SL Sergey Levine — holds since 2025-09-12 — tap for who they are Same subject: A highly dynamic economy that cheaply mass-produces robots may increase rather than decrease the risk of Malthusian resource dilemmas. — tap to centre the map on it A highly dynamic economy thatcheaply mass-produces robots mayincrease rather than decrease therisk of Malthusian resourcedilemmas. Last stated 3 years ago 1 Oct 2023 TC Tyler Cowen — holds since 2023-10-01 — tap for who they are Same subject: A humanoid robot is the wrong tool on a factory floor, because a machine specialised in the task beats it. — tap to centre the map on it A humanoid robot is the wrong toolon a factory floor, because amachine specialised in the taskbeats it. Last stated 2 years ago 6 Apr 2025 MH Molson Hart — holds since 2025-04-06 — 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 clip value of 10 taken from DeepSeek-R1 is large in practice; values such as 0.1 are more usual. Last stated 10 Oct 2026 · a month ago Holds Sebastian Raschka Read this korrent →