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
- If embeddings are so powerful, why is retrieval their only mainstream use? — ProposalOrganic1043 · 2026-09-14
- An OOD test worth watching: asking Gemini 4.1 Pro to paint surrealism with pure Python code — teortaxesTex · 2026-09-14
- Leaked GPT-6 Sol Output Impresses, But OpenAI Reportedly Has Stronger Bell Internally — VraserX · 2026-09-14
- Chinese LLMs have caught up a lot, argues Kevin Bass — the US should widen its AI lead, not slow down — kevinnbass · 2026-09-14
- ARC-AGI-3's non-standard scoring under fire as GPT-6 hits ~100% — peterwildeford · 2026-09-14
- eigenrobot compares sol vs astra: tighter, colder reasoning, 'net less fun' but a strength — eigenrobot · 2026-09-14