What's this about?
In Latent Space, Liam Fedus and Ekin Doğuş Çubuk explain why automated synthesis, measurement and learning from failed experiments must accompany capable models. A complete publisher transcript was collected; proposed discoveries and business plans remain the guests’ claims.
What exactly is closed-loop science?
Propose an experiment, run it, measure what happened, then use that evidence to choose the next experiment.
What's the community saying / why does it matter?
No substantive independent comment thread was collected. Their practical point is that a convincing prediction becomes scientific knowledge only through contact with reality.
TLDR: Scientific progress needs experiments that can falsify predictions. Failed and noisy measurements are valuable training data. Evaluate physical AI by reproducible experimental outcomes, not fluent proposals. Chapters: physical-world RL 02:49; discovery loop 09:17; experimental ground truth 30:22; negative results 53:16; deployment 01:10:45. Liam Fedus: “you can’t just think your way to a solution” [00:00:29]. Ekin Doğuş Çubuk: “What’s really hard is to synthesize them” [01:21:23].