korrents

← Reasoning is not taught to a model by people: it emerges from…

On the map

8 connected korrents · 6 moments on record from 19 Jun 2024 to 23 Mar 2026.

Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Reasoning is not taught toa model by people: itemerges from reinforcement… NL Nathan Lambert — holds since 2025-02-03 The aha moment for reasoning models will come from computer use and robotics rather than from scientific discovery, because those are the infinitely verifiable playgrounds. The aha moment forreasoning models will… DP Dylan Patel — holds since 2025-02-03 Inference was never going to be the easy, cheap half of AI, because inference is thinking, and thinking is far harder than reading. Inference was nevergoing to be the easy… JH Jensen Huang — holds since 2026-03-23 Real reasoning will have arrived when spending more compute at inference time reliably buys a dramatically better answer. Real reasoning willhave arrived when… AS Aravind Srinivas — holds since 2024-06-19 Humans barely use reinforcement learning for intelligence — what RL they do use goes into motor tasks, not problem solving. Humans barely usereinforcement learning… AK Andrej Karpathy — holds since 2025-10-17 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. Humans keep their placein AI as judges rather… NL Nathan Lambert — holds since 2025-02-03 Robots will learn from deployment more easily than chatbots do, because a physical mistake is obvious the moment it happens. Robots will learn fromdeployment more easily… SL Sergey Levine — holds since 2025-09-12 Curiosity is the thing AI has not cracked: a model can research a question thoroughly, but it cannot decide which question is worth asking. Curiosity is the thingAI has not cracked: a… AS Aravind Srinivas — holds since 2024-06-19 Reinforcement learning leaves models sharply jagged: on the rails of a verifiable domain they are superintelligent, off them everything meanders. Reinforcement learningleaves models sharply… AK Andrej Karpathy — holds since 2026-03-20
same subject