AutoDNA: AI agents now run multi-step wet-lab molecular biology experiments autonomously
james_y_zou · x · 2026-11-10
A Nature paper by Wu et al. introduces AutoDNA, a system where AI agents plan and execute multi-step molecular-biology experiments involving DNA with limited human intervention, coordinating real lab instruments.
Key points:
- AI has mostly been used for computational science (data analysis, prediction, literature mining); wet-lab work remained a bottleneck — designing a bioactive molecule takes minutes, testing it takes weeks plus heavy human effort.
- Stanford's James Zou, writing a Nature News & Views piece, frames this as AI starting to close the gap between proposing an experiment and actually running it — a milestone for AI for Science moving from computation into physical experimentation.
More from AGI Musings
- Fable's 5-year advice for applied AI careers: build skill at the constraint — brandon_galang · 2026-11-10
- Ben Goertzel predicts continued massive AI industry growth through 2027 — bengoertzel · 2026-11-10
- Ex-AI Security Lead: AI Luminaries' Cyber Takes Are Wrong, Real Expertise Will Reclaim Authority — joshua_saxe · 2026-11-10
- SlopOps: mistaking agentic coding capability for competitive advantage is playing the slop lottery — generativist · 2026-11-10
- Eric Schwitzgebel's 22-minute interview on the possibility of AI consciousness — eschwitz · 2026-11-10
- Yudkowsky: AI fiction lags code badly — 'we may only be alive because gradient descent generalizes policies so poorly' — sebkrier · 2026-11-10