korrents

On the map

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

← Reinforcement learning cannot be scaled for robots the way it was for…

8 connected korrents · 9 moments on record from 12 Sept 2022 to 12 Aug 2026.

Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute. Reinforcement learning cannot bescaled for robots the way it was forlanguage models, because everyattempt spends real robot hoursinstead of data-centre compute. CF Chelsea Finn — holds since 2026-08-12 — tap for who they are Same subject: Computer-use agents had to wait for language models: without pre-trained representations the reward is too sparse to ever learn from. — tap to centre the map on it Computer-use agents had towait for language models:without pre-trainedrepresentations the reward is… AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. — tap to centre the map on it Humans barely usereinforcement learning forintelligence — what RL they douse goes into motor tasks, not… AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. — tap to centre the map on it Reinforcement learning onlyworks once a model alreadyknows something, which is whyrobots must be pre-trained by… SL Sergey Levine — holds since 2025-09-12 — 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 mimicwhat people say to do ratherthan work out what to do,which is why they are not… RS Richard Sutton — holds since 2025-09-26 — tap for who they are Same subject: Once a robot is good enough, you can teach it with words instead of with demonstrations, and language becomes a training signal for motor skill. — tap to centre the map on it Once a robot is good enough,you can teach it with wordsinstead of withdemonstrations, and language… SL Sergey Levine — holds since 2025-09-12 — tap for who they are Same subject: An end-to-end self-improving AI is probably possible, but it is not even desirable, because it is a hard-takeoff scenario. — tap to centre the map on it An end-to-end self-improvingAI is probably possible, butit is not even desirable,because it is a hard-takeoff… DH Demis Hassabis — holds since 2025-07-23 — tap for who they are Same subject: AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. — tap to centre the map on it AI progress is faster thanpeople expect, and ordinaryscaling can be enough to solveproblems that looked very… AC Ajeya Cotra — holds since 2023-08-29 — tap for who they are SA Scott Alexander — holds since 2022-09-12 — tap for who they are MB Miles Brundage — holds since 2025-02-02 — tap for who they are Same subject: Large language models will not get to real agency, because a mind has to be embedded in a world through a body. — tap to centre the map on it Large language models will notget to real agency, because amind has to be embedded in aworld through a body. AF Adam Frank — holds since 2024-12-22 — tap for who they are
same subject or similar wording

At the centre Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute. Holds Chelsea Finn Read this korrent →