On the map

At the centre Simulation works for a trainee pilot because the pilot knows what the simulator is for; a model trained across domains has no such goal. Holds SLSergey Levine Read this korrent →

• Similar wording The goal was never good simulation; it was answering counterfactuals, and a value function does that job as well as a simulator does. Holds SLSergey Levine
• Similar wording If we live in a simulation, whoever is running it does not know how it ends, because nobody runs a simulation whose outcome they already know. Holds EMElon Musk
• Similar wording RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does. Holds DADario Amodei
• Similar wording Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model. Holds DDDmitri Dolgov
• Similar wording Reinforcement learning only works once a model already knows something, which is why robots must be pre-trained by imitation first. Holds SLSergey Levine
• Similar wording Synthetic experience can only rehearse what a system already knows; information about the world has to be injected from outside. Holds SLSergey Levine