Stanford's Anshul Kundaje: Claude/GPT are pretty bad at annotating DNA motifs

anshulkundaje · x · 2026-09-24

Stanford professor Anshul Kundaje reports that Claude/GPT perform poorly at helping annotate DNA motifs — a painstaking manual task he thinks AI should learn, noting his lab is generating sufficient labeled data to train models to accurately annotate massive motif lexicons.

Related event: Stanford team finds frontier LLMs like Opus 5 and GPT6 poor at DNA motif annotation out of the box(6 posts)→

Original post →

More from Research

• Counterintuitive: generic synthetic data beats self-generated data for distillation adapters — ostrisai · 2026-09-24
• What's next for brain foundation models in neuroscience — ShahabBakht · 2026-09-24
• TANGO: Sim-Only Trained Whole-Body VLA Gives Humanoids Zero-Shot Navigation on Unitree G1 — chris_j_paxton · 2026-09-24
• Dev builds fast multi-layer liquid refraction for VRChat with screen-space ray marching — Michael_Moroz_ · 2026-09-24
• Superforecasters Put AI Solving a Millennium Problem at 1.7% — and Keep Underestimating AI — emollick · 2026-09-24
• Salesforce Paper: Only 35.8% of the Cleanest Public RL Environments Pass Audit — dair_ai · 2026-09-24

Research channel →