korrents

On the map

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

← Human preference rankings for RLHF are partly subjective, because…

17 connected korrents · 17 moments from 13 Aug 2023 to 26 Oct 2026. Nearly all of them are about reinforcement learning.

Everything filed under taste taste Everything filed under scaling laws scaling laws Everything filed under LLMs LLMs Everything filed under neural networks neural networks Everything filed under benchmarks benchmarks Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Human preference rankings for RLHF are partly subjective, because raters with limited time cannot always check which answer is correct. Human preference rankings for RLHF arepartly subjective, because raters withlimited time cannot always check whichanswer is correct. 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 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 verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. — tap to centre the map on it A verifiable task can be optimisedby reinforcement learning until aneural network performs it extremelywell. Last stated a year ago 17 Nov 2025 AK Andrej Karpathy — holds since 2025-11-17 — tap for who they are Same subject: Anything precise enough to benchmark is also precise enough to optimize for, and modern RL training increasingly resembles the shape of the benchmarks themselves. — tap to centre the map on it Anything precise enough to benchmarkis also precise enough to optimizefor, and modern RL trainingincreasingly resembles the shape ofthe benchmarks themselves. Last stated 7 months ago 16 Apr 2026 SK Sayash Kapoor — holds since 2026-04-16 — tap for who they are Same subject: Before training a base model with RL to emit think tokens, it is better to do some continued pre-training or supervised fine-tuning with those tokens present. — tap to centre the map on it Before training a base model with RLto emit think tokens, it is betterto do some continued pre-training orsupervised fine-tuning with thosetokens present. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. — tap to centre the map on it Capability does not generalise forfree: a model that will movemountains on an agentic task stilltells the same bad joke it told fiveyears ago. Last stated 8 months ago 20 Mar 2026 AK Andrej Karpathy — holds since 2026-03-20 — tap for who they are Same subject: Current models are unsafe because they are not smart enough, not because they are too smart. — tap to centre the map on it Current models are unsafe becausethey are not smart enough, notbecause they are too smart. Last stated 2 months ago 13 Sept 2026 FC François Chollet — holds since 2026-09-13 — tap for who they are Same subject: Distillation is simpler than reinforcement learning, but reinforcement learning is the state of the art and distillation a more efficient approximation. — tap to centre the map on it Distillation is simpler thanreinforcement learning, butreinforcement learning is the stateof the art and distillation a moreefficient approximation. Last stated a month ago 17 Oct 2026 SR Sebastian Raschka — holds since 2026-10-17 — tap for who they are Same subject: A 'tranquil domestic setting' is not a fitting frame for Jane Austen. — tap to centre the map on it A 'tranquil domestic setting' is nota fitting frame for Jane Austen. Last stated 2 years ago 3 Aug 2024 DL Devoney Looser — holds since 2024-08-03 — tap for who they are Same subject: A big part of taste is delivering high levels of craft in an accessible way so that as many people as possible can experience it. — tap to centre the map on it A big part of taste is deliveringhigh levels of craft in anaccessible way so that as manypeople as possible can experienceit. Last stated 7 months ago 21 Apr 2026 BJ Brandon Jacoby — holds since 2026-04-21 — tap for who they are Same subject: A book is not bad just because its characters have a bad relationship. — tap to centre the map on it A book is not bad just because itscharacters have a bad relationship. Last stated 3 years ago 13 Aug 2023 SD Seth Dickinson — holds since 2023-08-13 — tap for who they are Same subject: A product's craft probably comes down to whether it works without pain and how it makes people feel. — tap to centre the map on it A product's craft probably comesdown to whether it works withoutpain and how it makes people feel. Last stated 2 months ago 10 Sept 2026 RS Robby Stein — holds since 2026-09-10 — tap for who they are Same subject: A shadow in an interface implies a light source, so an elevated element needs a highlight where the light falls, not just a drop shadow. — tap to centre the map on it A shadow in an interface implies alight source, so an elevated elementneeds a highlight where the lightfalls, not just a drop shadow. Last stated 2 years ago 21 Feb 2025 TC Thiago Costa — holds since 2025-02-21 — tap for who they are Same subject: A subwoofer for music should reinforce the bass already in the recording, without adding bloat or artificial bass. — tap to centre the map on it A subwoofer for music shouldreinforce the bass already in therecording, without adding bloat orartificial bass. Last stated a month ago 19 Oct 2026 SH Steve Huff — holds since 2026-10-19 — tap for who they are Same subject: "Scaling" was powerful because it was one word: naming a research direction is what tells a whole field what to do next. — tap to centre the map on it "Scaling" was powerful because itwas one word: naming a researchdirection is what tells a wholefield what to do next. Last stated 12 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it A benchmark result should bereported under a stated budget, oras a curve against test-time compute— never as a single number. Last stated 5 months ago 26 Jun 2026 NB Noam Brown — holds since 2026-06-26 — tap for who they are Same subject: A CPU and memory crunch is coming. — tap to centre the map on it A CPU and memory crunch is coming. Last stated 4 weeks ago 26 Oct 2026 DM Dillon Mulroy — holds since 2026-10-26 — 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 Human preference rankings for RLHF are partly subjective, because raters with limited time cannot always check which answer is correct. Last stated 3 Oct 2026 · 2 months ago Holds Sebastian Raschka Read this korrent →