korrents

On the map

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

← In GRPO training, the loss should stay roughly stable around a value, and large loss spikes are what to avoid.

17 connected korrents · 15 moments from 25 Jul 2022 to 5 Nov 2026.

Everything filed under reinforcement learning reinforcement learning Everything filed under LLMs LLMs Everything filed under scaling laws scaling laws Everything filed under stock market stock market Everything filed under AI alignment AI alignment Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: In GRPO training, the loss should stay roughly stable around a value, and large loss spikes are what to avoid. In GRPO training, the loss should stayroughly stable around a value, and largeloss spikes are what to avoid. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: Instability in small-scale RL training does not necessarily mean the algorithm is wrong; the scale may be too small to see its benefits. — tap to centre the map on it Instability in small-scale RLtraining does not necessarily meanthe algorithm is wrong; the scalemay be too small to see itsbenefits. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: In GRPO, a high standard deviation of the advantages is desirable. — tap to centre the map on it In GRPO, a high standard deviationof the advantages is desirable. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: The small GRPO settings are only for efficiency; whatever you can increase, such as rollouts, you should. — tap to centre the map on it The small GRPO settings are only forefficiency; whatever you canincrease, such as rollouts, youshould. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: Training data is still plentiful for now, but it will eventually run out. — tap to centre the map on it Training data is still plentiful fornow, but it will eventually run out. Last stated 4 years ago 27 Mar 2023 IS Ilya Sutskever — holds since 2023-03-27 — tap for who they are Same subject: Stocks sustained by persistent online attention can stay overpriced for long periods, so overvaluation alone does not imply a near-term correction. — tap to centre the map on it Stocks sustained by persistentonline attention can stay overpricedfor long periods, so overvaluationalone does not imply a near-termcorrection. Last stated 4 years ago 25 Jul 2022 NS Noah Smith — holds since 2022-07-25 — tap for who they are Same subject: Companies leaving and entering fine-tuning are probably not headed in the wrong direction, just making different bets on where the value is. — tap to centre the map on it Companies leaving and enteringfine-tuning are probably not headedin the wrong direction, just makingdifferent bets on where the valueis. Last stated 2 weeks ago 5 Nov 2026 AR Aishwarya Naresh Reganti — holds since 2026-11-05 — tap for who they are Same subject: Losing money periodically is a normal part of owning stocks, not a sign that something has gone wrong. — tap to centre the map on it Losing money periodically is anormal part of owning stocks, not asign that something has gone wrong. Last stated 3 months ago 27 Aug 2026 BC Ben Carlson — holds since 2026-08-27 — tap for who they are Same subject: A high, stable dividend yield gives a stock's valuation a downside floor that growth stocks without dividends lack. — tap to centre the map on it A high, stable dividend yield givesa stock's valuation a downside floorthat growth stocks without dividendslack. Last stated 9 months ago 3 Mar 2026 SB Sanjay Bakshi — holds since 2026-03-03 — 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 base model learns humanity's collective knowledge, and it then has to be aligned to behave one way or another. — tap to centre the map on it A base model learns humanity'scollective knowledge, and it thenhas to be aligned to behave one wayor another. Last stated a year ago 10 Sept 2025 SA Sam Altman — holds since 2025-09-10 — 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 In GRPO training, the loss should stay roughly stable around a value, and large loss spikes are what to avoid. Last stated 10 Oct 2026 · a month ago Holds Sebastian Raschka Read this korrent →