korrents

On the map

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

← Rewarding AI plans rather than outcomes is not fully competitive, and…

17 connected korrents · 17 moments from 17 Jun 2022 to 17 Oct 2026.

Everything filed under reinforcement learning reinforcement learning Everything filed under humility humility Everything filed under AI alignment AI alignment Everything filed under LLMs LLMs Everything filed under hiring hiring Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Rewarding AI plans rather than outcomes is not fully competitive, and making it more competitive is one of the most important lines of research. Rewarding AI plans rather than outcomes isnot fully competitive, and making it morecompetitive is one of the most importantlines of research. Last stated 4 years ago 12 May 2023 AC Ajeya Cotra — holds since 2023-05-12 — tap for who they are Same subject: The competitiveness of the AI model-making industry is uncertain. — tap to centre the map on it The competitiveness of the AImodel-making industry is uncertain. Last stated 2 months ago 1 Oct 2026 NS Noah Smith — holds since 2026-10-01 — tap for who they are Same subject: Systematising principled decision-making with AI is now the line between staying competitive and not; there is no position in between. — tap to centre the map on it Systematising principleddecision-making with AI is now theline between staying competitive andnot; there is no position inbetween. Last stated 5 months ago 10 Jun 2026 RD Ray Dalio — holds since 2026-06-10 — tap for who they are Same subject: Companies do not have sufficient incentives to mitigate the major risks of AI, and competition between them is driving corner-cutting. — tap to centre the map on it Companies do not have sufficientincentives to mitigate the majorrisks of AI, and competition betweenthem is driving corner-cutting. Last stated 2 years ago 15 Feb 2025 MB Miles Brundage — holds since 2025-02-15 — tap for who they are Same subject: It is fundamentally difficult to design a reward function that accurately captures the intended goal in reinforcement learning. — tap to centre the map on it It is fundamentally difficult todesign a reward function thataccurately captures the intendedgoal in reinforcement learning. Last stated 2 years ago 28 Nov 2024 LW Lilian Weng — holds since 2024-11-28 — tap for who they are Same subject: AI has achieved parts of its goal, such as conversational AI, but has not conquered all of them. — tap to centre the map on it AI has achieved parts of its goal,such as conversational AI, but hasnot conquered all of them. Last stated a year ago 16 Nov 2025 FL Fei-Fei Li — holds since 2025-11-16 — tap for who they are Same subject: Ask an AI lazily for a strategy and you get the predictable move your competitors already expect from you. — tap to centre the map on it Ask an AI lazily for a strategy andyou get the predictable move yourcompetitors already expect from you. Last stated 4 months ago 9 Jul 2026 AM Adam Mosseri — holds since 2026-07-09 — tap for who they are Same subject: The competitiveness of the AI modeling industry is unknown. — tap to centre the map on it The competitiveness of the AImodeling industry is unknown. Last stated 2 months ago 30 Sept 2026 NS Noah Smith — holds since 2026-09-30 — tap for who they are Same subject: Careers in AI and effective altruism are highly competitive. — tap to centre the map on it Careers in AI and effective altruismare highly competitive. Last stated 4 years ago 17 Jun 2022 NN Neel Nanda — holds since 2022-06-17 — 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 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: 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: Distilling from a model's reasoning traces gets there quicker and cheaper than reinforcement learning, which is why labs that invest in RL complain about it. — tap to centre the map on it Distilling from a model's reasoningtraces gets there quicker andcheaper than reinforcement learning,which is why labs that invest in RLcomplain about it. Last stated a month ago 17 Oct 2026 SR Sebastian Raschka — holds since 2026-10-17 — tap for who they are Same subject: Large language models mimic what people say to do rather than work out what to do, which is why they are not about understanding the world. — tap to centre the map on it Large language models mimic whatpeople say to do rather than workout what to do, which is why theyare not about understanding theworld. Last stated a year ago 26 Sept 2025 RS Richard Sutton — holds since 2025-09-26 — tap for who they are Same subject: OpenAI's o1 does an online search over reasoning steps at test time, unlike a traditional autoregressive language model. — tap to centre the map on it OpenAI's o1 does an online searchover reasoning steps at test time,unlike a traditional autoregressivelanguage model. Last stated 2 years ago 4 Dec 2024 NL Nathan Lambert — holds since 2024-09-16 — tap for who they are NL Nathan Lambert — no longer holds since 2024-12-04 — 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 arefaded, dashed ring: they no longer hold it — they changed their mind

At the centre Rewarding AI plans rather than outcomes is not fully competitive, and making it more competitive is one of the most important lines of research. Last stated 12 May 2023 · 4 years ago Holds Ajeya Cotra Read this korrent →