Google's Co-Scientist autonomously runs experiments, synthesizing materials on first try
mark_k · x · 2026-08-30
Google DeepMind's Co-Scientist is now automating parts of the scientific process. It generated synthesis recipes for specific lab hardware, successfully producing monolayer MoS₂ semiconductors on the first attempt and inventing new precursor routes. It also predicted E. coli swarming behavior and autonomously invented a medical AI agent (AgentH) that outperformed frontier models on HealthBench. The team tested fully autonomous research workflows but warned about hallucinations.
Related event: Google DeepMind's Co-Scientist Extension Brings AI into Real-World Labs(30 posts)→
More from Research
- RExBench: best coding agent completes only 33% of autonomous research extensions — najoungkim · 2026-10-16
- Google's CLASHarness benchmarks multi-agent conflicts in computer use, finds frontier VLMs struggle — google · 2026-10-16
- Tsinghua team proves vanilla flow-matching sampling can't exceed constant-depth expressive power — SQZ · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- KAUST's NoteBank adds sparse episodic memory to linear attention, boosting long-context for free — kaust-generative-ai · 2026-10-16