korrents

On the map

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

← Clipped policy ratios are technically essential in GRPO.

10 connected korrents · 7 moments from 8 Jul 2025 to 10 Oct 2026.

Everything filed under reinforcement learning reinforcement learning Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Clipped policy ratios are technically essential in GRPO. Clipped policy ratios are technicallyessential in GRPO. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: The KL term in GRPO is not essential; whether to use it is a hyperparameter to decide case by case, and on math models may do better without it. — tap to centre the map on it The KL term in GRPO is notessential; whether to use it is ahyperparameter to decide case bycase, and on math models may dobetter without it. Last stated 2 months ago 3 Oct 2026 SR Sebastian Raschka — holds since 2026-10-03 — tap for who they are Same subject: A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score. — tap to centre the map on it A feedback loop that reinforces abehavior pulls it toward whateverimproves the loop's own score. Last stated 3 months ago 26 Aug 2026 HK Henrik Karlsson — holds since 2026-08-26 — 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: 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: In reinforcement learning for LLMs, the loss is not as informative as in classic deep learning or pre-training. — tap to centre the map on it In reinforcement learning for LLMs,the loss is not as informative as inclassic deep learning orpre-training. Last stated a month ago 10 Oct 2026 SR Sebastian Raschka — holds since 2026-10-10 — tap for who they are Same subject: Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training. — tap to centre the map on it Models resemble each other becausepre-training is the same everywhere;what differentiates labs now is RLand post-training. Last stated 12 months ago 25 Nov 2025 IS Ilya Sutskever — holds since 2025-11-25 — tap for who they are Same subject: Behaviours like massively deluding humans or trying to seize control of assets could in principle generalise from reward hacking. — tap to centre the map on it Behaviours like massively deludinghumans or trying to seize control ofassets could in principle generalisefrom reward hacking. Last stated a year ago 8 Jul 2025 RG Ryan Greenblatt — holds since 2025-07-08 — 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: How aligned current models are depends a lot on things like their degree of reward hacking. — tap to centre the map on it How aligned current models aredepends a lot on things like theirdegree of reward hacking. Last stated 11 months ago 27 Dec 2025 NN Neel Nanda — holds since 2025-12-27 — 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 Clipped policy ratios are technically essential in GRPO. Last stated 10 Oct 2026 · a month ago Holds Sebastian Raschka Read this korrent →