Yoav Goldberg: new robot models aren't zero-shot — they're trained to the max on each task
benno_krojer · x · 2026-09-13
LerrelPinto describes deep despair in academia as Astra, Fable and Muse appear to zero-shot robotics and world-model benchmarks. Yoav Goldberg pushes back: while the new wave of models does solve tasks that were hard for agents before, they didn't zero-shot anything — he's confident they were trained to the extreme on each and every one of those tasks.
More from Models
- Open TTS Leaderboard adds 14 languages, new LFM3-Audio-2B and maya2-native models — realmrfakename · 2026-10-31
- Developers say the Linux Codex app is broken and neglected — eigenron · 2026-10-31
- Kimi now accepts Russian Mir cards directly: Pro subscription at $39/month without intermediaries — teortaxesTex · 2026-10-31
- Nat Lambert: Open models could be what holds the AI ecosystem together — natolambert · 2026-10-31
- Gemini 4 Carbon debuts #1 on APEX-Agents, the only model averaging above 90% — Swarooprm7 · 2026-10-31
- Sarvam quietly builds an India-focused opencode with 'local inference', gets mocked for the definition — kingslyj · 2026-10-31