Skip to content
NewA calmer, faster ZeroHour

Blog finds latest Claude models predict obscure protein sequences

Original title: Claude was trained on protein sequences at scale

Hacker News · AIby gmays ()15 min read1
AI summary · x-ai/grok-4.7Summaries by Vani AI

Fable 5.2 beat open protein models on 668 little-studied proteins; GPT, Gemini and open-weight LLMs stayed near chance.

A researcher tested whether frontier models can continue little-studied bacterial and archaeal proteins, a task famous proteins cannot separate from memorized papers. Claude Fable 5.2 and Opus 5.5 predicted the next amino acid far above shuffled controls; 20 other language models did not. Fable 5.2 also beat ProGen3-3B and ProtGPT3-10B on the same left-to-right task. An update says the models still predicted 56 proteins first published in August 2026.

Unconfirmed: The author infers sequence-database training; the text does not include confirmation from Anthropic.

Key facts
  • The test set has 668 proteins from 167 unknown-function Pfam families.
  • Fable 5.2 scored 54% on real sequences and 9% on shuffled ones.
  • Opus 5.5 matched ProtGPT3-10B and trailed ProGen3-3B.
  • Accuracy rose with larger families, including families with no papers.
  • GPT-6.2, Gemini and seven open-weight models stayed near zero.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

15 min read at xinmingtu.cn

The latest Claude models were trained on protein sequences, at scale. Give Claude Fable 5. 2 or Claude Opus 5.

Hacker News · AI

By gmays · xinmingtu.cn

Read the full article at Hacker News · AI

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.