korrents

On the map

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

← A format reward should only be added when the answer is already correct.

17 connected korrents · 15 moments from 1 Oct 2023 to 26 Oct 2026.

Everything filed under reinforcement learning reinforcement learning Everything filed under AI alignment AI alignment Everything filed under robotics robotics Everything filed under scaling laws scaling laws Everything filed under AI writing AI writing Everything filed under LLMs LLMs Everything filed under mathematics mathematics Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: A format reward should only be added when the answer is already correct. A format reward should only be added whenthe 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: When a format reward is simply added to the correctness reward, a model may over-emphasize the easy format reward and neglect correctness. — tap to centre the map on it When a format reward is simply addedto the correctness reward, a modelmay over-emphasize the easy formatreward and neglect correctness. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: It is more common to train only on answer tokens than on prompt tokens. — tap to centre the map on it It is more common to train only onanswer tokens than on prompt tokens. Last stated a month ago 17 Oct 2026 SR Sebastian Raschka — holds since 2026-10-17 — tap for who they are Same subject: The fix for reward hacking is to take out the environments that reward it, not to add penalties the agent must then balance against the temptation to cheat. — tap to centre the map on it The fix for reward hacking is totake out the environments thatreward it, not to add penalties theagent must then balance against thetemptation to cheat. Last stated 3 months ago 1 Sept 2026 AC Ajeya Cotra — holds since 2026-09-01 — tap for who they are Same subject: There seems to be a general understanding that using AI in a contest that is at least partly a writing contest is against the spirit of the exercise. — tap to centre the map on it There seems to be a generalunderstanding that using AI in acontest that is at least partly awriting contest is against thespirit of the exercise. Last stated 2 months ago 21 Sept 2026 SA Scott Alexander — holds since 2026-09-21 — tap for who they are Same subject: To reward the instinct that a new idea is worth having, training would have to score the smallness of the concepts a solution needs, not just whether it solved the problem. — tap to centre the map on it To reward the instinct that a newidea is worth having, training wouldhave to score the smallness of theconcepts a solution needs, not justwhether it solved the problem. Last stated 5 months ago 30 Jun 2026 GS Grant Sanderson — holds since 2026-06-30 — tap for who they are Same subject: Longer answers are often correlated with answer correctness to a certain degree. — tap to centre the map on it Longer answers are often correlatedwith answer correctness to a certaindegree. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: The math community should formalize the 'motivated explanation' and give it the same academic credit that proof has had. — tap to centre the map on it The math community should formalizethe 'motivated explanation' and giveit the same academic credit thatproof has had. Last stated 2 months ago 18 Sept 2026 GS Grant Sanderson — holds since 2026-09-18 — tap for who they are Same subject: He would rather read your broken English than your AI-written text; we are reaching the point where typos are valuable again. — tap to centre the map on it He would rather read your brokenEnglish than your AI-written text;we are reaching the point wheretypos are valuable again. Last stated 9 months ago 12 Feb 2026 PS Peter Steinberger — holds since 2026-02-12 — 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: "Hire smart people and get out of their way" is bad management advice; leaders should stay closely involved, building trust and working through hard problems with their people to create alignment. — tap to centre the map on it "Hire smart people and get out oftheir way" is bad management advice;leaders should stay closelyinvolved, building trust and workingthrough hard problems with theirpeople to create alignment. Last stated a month ago 9 Oct 2026 CR Carl Rivera — holds since 2026-10-09 — tap for who they are Same subject: A 5% level of AI risk is crazy and unacceptable; we would not accept a 5% chance of massive fatalities from paint companies. — tap to centre the map on it A 5% level of AI risk is crazy andunacceptable; we would not accept a5% chance of massive fatalities frompaint companies. Last stated a year ago 8 Jul 2025 RG Ryan Greenblatt — holds since 2025-07-08 — tap for who they are Same subject: A big misreading of Chinese labs is missing that they have a risk posture and do not want to cause harm. — tap to centre the map on it A big misreading of Chinese labs ismissing that they have a riskposture and do not want to causeharm. Last stated 4 weeks ago 26 Oct 2026 NL Nathan Lambert — holds since 2026-10-26 — 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: A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases. — tap to centre the map on it A physical AI agent has to be safeon day one, because you cannot shipsomething merely good enough and letusers find the edge cases. Last stated 4 months ago 3 Aug 2026 DD Dmitri Dolgov — holds since 2026-08-03 — 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 A format reward should only be added when the answer is already correct. Last stated 10 Oct 2026 · a month ago Holds Sebastian Raschka Read this korrent →