HOT RADAR
llmHEAT 15.9°

AI CURATED HOT STORY · 11/18/2026

Claude Models Found Trained on Protein Sequences at Scale

1 reports archived1 independent sourcesupdated 11/18/2026, 11:47:43
Synthesis & Latest Updates
1 Sources Cross-Validated

A next-amino-acid prediction test on little-studied proteins reveals that Claude Fable 5.2 and Opus 5.5 can predict the next residue from sequence context but fail when the sequence is shuffled, indicating large-scale training on protein sequences. No other frontier model tested shows this behavior, and Fable 5.2 outperforms every open protein language model while Opus 5.5 matches the largest, ProtGPT3-10B. The finding exposes an undisclosed protein-sequence component in frontier LLM training data.

LATEST/A next-amino-acid prediction test on little-studied proteins reveals that Claude Fable 5.2 and Opus 5.5 can predict the next residue from sequence context but fail when the sequence is shuffled, indicating large-scale training on protein sequences. No other frontier model tested shows this behavior, and Fable 5.2 outperforms every open protein language model while Opus 5.5 matches the largest, ProtGPT3-10B. The finding exposes an undisclosed protein-sequence component in frontier LLM training data.

Hourly heat curve

5 fully observed hours
Now
15.9
Peak
17.012:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first