Verifiable Environments for AI Agents in Biology: Why Frontier Models Can't Be Trusted Yet
kenbwork · x · 2026-08-02
This is an in-depth talk on building verifiable environments for AI agents in biology. It covers measurement methods in modern bio research, utilizing data analysis as an executable substrate for science, and five years of lessons from applying coding models to biological workflows.
The presentation also explores why current frontier models cannot be fully trusted (yet) in these scenarios, detailing the design principles of SpatialBench, the anatomy of evaluations, human verification, and new work in multi-omics, therapeutics, and biosecurity.
Related event: LatchBio Warns Frontier AI Models Remain Unreliable in Biology(2 posts)→
More from coding & agent
- Should Spark Be Rewritten for the Agentic Era? Engineer Riffs on MapReduce — _arohan_ · 2026-08-02
- Dropping Model Routing? Single GPT Workflow Outperforms Mixed Models — kevinkern · 2026-08-02
- Slack introduces !fork command to spin up new agents with full context — KlausCodes · 2026-08-02
- Hugging Face Launches Free Public Endpoint for DeepSeek, No Account Required — victormustar · 2026-08-02
- Mintlify CTO: AI Enables Everyone to Code, and That's the Problem — stuffyokodraws · 2026-08-02
- a16z's huybery: Coding Agents Have Driven Much of AI's Progress — huybery · 2026-08-02