RLHF is not a tax on capability: preference tuning also raises maths and code scores, which is why the labs keep reaching for it.

Added to korrents 3 Feb 2025 · 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.

• A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. AKAndrej Karpathy17 Nov 2025reinforcement learning
• Capability does not generalise for free: a model that will move mountains on an agentic task still tells the same bad joke it told five years ago. AKAndrej Karpathy20 Mar 2026reinforcement learning
• Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. AKAndrej Karpathy17 Oct 2025reinforcement learning
• Humans keep their place in AI as judges rather than authors, because telling which of two answers is better is far easier than writing a good one. NLNathan Lambert3 Feb 2025reinforcement learning
• 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. RSRichard Sutton26 Sept 2025reinforcement learning

On the map

Open the map on its own page →