One pre-trained robot model now matches or beats the specialists that were fine-tuned with reinforcement learning for the very tasks they were built for.

Added to korrents 12 Aug 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training. ISIlya Sutskever25 Nov 2025scaling lawsreinforcement learning
• Pre-training is a crappy evolution: the practically buildable substitute for the process that gave animals their built-in hardware. AKAndrej Karpathy17 Oct 2025scaling lawsreinforcement learning
• RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does. DADario Amodei13 Feb 2026scaling lawsreinforcement learning
• 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. CFChelsea Finn12 Aug 2026roboticsreinforcement learning
• Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. SLSergey Levine12 Sept 2025roboticsreinforcement learning

On the map

Open the map on its own page →