• The piece uses a double pendulum as a proxy for near-chaotic hardware: an ideal frictionless simulation and a friction-damped one started from identical conditions swing in sync briefly before wildly diverging at the 'onset of chaos.'
• The gap between an idealized simulation and a physically realistic one is largest exactly where the dynamics are most expressive, meaning a model trained only on the ideal simulation could learn to exploit a near-chaotic region that doesn't exist in real hardware.
• Numerical solver choice matters as much as physical modeling: swapping a coarse Euler-method solver for a high-order one like DoPri shifts where the simulated chaos boundary falls, since rounding error behaves like an added physical perturbation near the edge of chaos.
• The team frames its goal as finding a 'Goldilocks' level of abstraction rather than maximum fidelity, since a perfectly accurate simulation takes hours per run while their AI scientists need to run millions of passes.

• articleNeural co-evolution, the inevitability of hardware and software co-evolution for AI

• articleSimulation: the new Scaling Law — Joon Sung Park, Simile AIwww.latent.space
• articleVirtual Worlds Teach AI To Think Like a PhysicistMallory Lindahl
• article[AINews] 10% worse, 100x cheaper, 10000x faster: Why Simulation is taking overwww.latent.space

Checking sign-in…

Loading comments…