RCT: LLMs fail to significantly boost novices' wet-lab molecular biology success
shae_mcl · x · 2026-09-16
A randomized controlled trial tested whether LLMs help novices do molecular biology wet-lab tasks: only 7% of LLM users got 3/5 tasks right vs 5% with internet alone — no significant end-to-end uplift, below expert predictions.
Related event: RCT finds LLMs fail to significantly boost novice wet-lab success(2 posts)→
More from Research
- Auto-inferring error specs is the next frontier in security, researcher argues — mboehme_ · 2026-11-02
- Security researcher: offense is hard to automate, defending known vuln classes is easier — mboehme_ · 2026-11-02
- Burkov on LLMs' architecture-agnostic low-rank structure over long token sequences — burkov · 2026-11-02
- Adobe & UCLA's Tev: verifiable progress rewards lift long-horizon agent Pass@5 from 0.17 to 0.28 — jiqizhixin · 2026-11-02
- Old trick still works: portal sampling cuts path-tracing noise dramatically at 64spp — ssh4net · 2026-11-02
- Marcel Böhme's paper asks why cybersecurity can never be solved, proposes vulnerability-guided hardening — mboehme_ · 2026-11-02