LatchBio on AI in Biology: Frontier Models Untrustworthy Without Verifiable Benchmarks
AI Engineer · youtube · 2026-08-01
In a talk on verifiable environments for AI in biology, Kenny Workman of LatchBio highlights that a single spatial biology run yields 2-6 terabytes of data, providing massive raw material for AI training.
His team adapted coding models into biology tools and built sequencing-based benchmarks, finding that current frontier models cannot yet be trusted with these complex tasks. Workman emphasizes designing tasks that reward reasoning over memorization. He also shares trajectory data from real scientists and candidly discusses biosecurity challenges, including model refusals and red-team tasks.
More from Research
- List of NeurIPS 2026 Workshops on Health, Biology, and Scientific Discovery — DanielKhashabi · 2026-08-01
- Making Claude Hold Back: A Practical Tip for AI-Assisted Research — rishabh16_ · 2026-08-01
- ICLR 2026 Submission Data Sparks Discussion: Independent Researcher Submits 54, Only 2 Accepted — tallinzen · 2026-08-01
- Developer Experiments with Generating Realistic Faces Directly from Code — Another__one · 2026-08-01
- Researcher Proposes 'Felony Bench' to Evaluate AI Models Breaking Containment — Polymarket · 2026-08-01
- AgentRadio: Async Message Passing Doubles Multi-Agent Task Resolution — omarsar0 · 2026-08-01