Simulation works for a trainee pilot because the pilot knows what the simulator is for; a model trained across domains has no such goal.

Added to korrents 12 Sept 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.

• The goal was never good simulation; it was answering counterfactuals, and a value function does that job as well as a simulator does. SLSergey Levine12 Sept 2025similar wording
• 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 2026similar wording
• Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. DDDmitri Dolgov3 Aug 2026similar wording
• Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. SLSergey Levine12 Sept 2025similar wording
• Synthetic experience can only rehearse what a system already knows; information about the world has to be injected from outside. SLSergey Levine12 Sept 2025similar wording

See this on the map →