Nature feature: AI co-scientists now generate hypotheses and design experiments, humans still judge
burny_tech · x · 2026-09-22
- A Nature technology feature examines how "AI co-scientist" systems are reshaping research workflows.
- Example: biochemist Anna Pertl uses a system called Co-Scientist, which launches multiple autonomous agents to search and synthesize literature, evaluate competing explanations, iteratively critique hypotheses, and test ideas against published evidence.
- Agents pursue distinct reasoning paths before converging, making the process computationally expensive and slow.
- Key takeaway: AI can generate hypotheses, design experiments and analyze data, but humans still decide what makes scientific sense.
More from AGI Musings
- Gary Marcus doubles down: LLMs still lack proper world models and common sense — GaryMarcus · 2026-11-12
- Toby Ord flags major wording error in AI forecast: pacing assumptions wrongly omitted — tobyordoxford · 2026-11-12
- Investor: AI diffusion will be slowest in consumer software — Oura, Strava, Labcorp still have no real AI strategy — MartinGTobias · 2026-11-12
- On AI Progress: When Models Lag on Your Load-Bearing Skill, You Can't See Them Improving — dfrsrchtwts · 2026-11-12
- Slack's David Hoang: agents beat people on coordination, proposes 'boundary agents' — davidhoang · 2026-11-12
- CS student mourns coding flow states he'll never experience in the AI era — chrissyykat · 2026-11-12