Pot spune cu încredere că echipa noastră de la @xAI este de 10 ori mai competentă decât fosta mea echipă de la @OpenAI.

1/4 În ultimii ani am lucrat part-time la laboratorul FAIR din Meta, pe lângă faptul că am fost profesor la UC Berkeley. Acea fază s-a încheiat acum, iar începând cu 5 ianuarie, voi conduce un efort de cercetare în robotică la Amazon FAR în San Francisco, continuând în același timp la Berkeley.

(1/N)🚀Today we launch two tightly connected milestones in the Physics of LM series: a sharpened Part 4.1 (v2.0) and a brand new Part 4.2 — together forming a clear, reproducible, textbook-style reference for principled architecture research. Part 4.1 introduced a synthetic pretraining playground — our Galileo experiment for LLMs🍎. Our v2.0 strengthens it with Gated DeltaNet (GDN) and stricter alignment, building an even cleaner “Pisa tower” for testing architectural limits. Part 4.2 shows these synthetic predictions resonate in reality 🌍 — across 1–8B / 1T-token pretraining — confirming which design principles actually matter. Together, Parts 4.1 and 4.2 bring the synthetic and real worlds into surprising agreement 🤝— one more step toward a more scientific understanding of LLM architectures. If you’re curious about: 🧠why some models reason deeper ⚙️ why linear models struggle at retrieval 🎶why a tiny horizontal mixer (Canon) changes everything … this release ties it all together. (Links at the end)