Issue 2026-11-18 · Industry · 研究 · 应用
Claude Models Trained on Protein Sequences at Scale, Study Finds

A study finds that the latest Claude models (e.g., Claude Fable 5.2 and Opus 5.5) were trained on protein sequences at scale, enabling them to predict the next amino acid in little-studied proteins. They outperform all open protein language models tested, while other frontier models (e.g., GPT-6.2 Sol and Astra) show no such capability.
Read original ↗