Carl Edwards' AssayBench talk: predicting biology and what to measure next
kchonyc · x · 2026-11-13
Carl Edwards shared slides from his AIAS/Chen Institute talk framing AI for biology around the question "can we solve biology?" He defines solving biology as precisely predicting and controlling a biological system's functional behavior — the "virtual cell" paradigm — and argues biology behaves more like language than physics: an evolved system full of exceptions (phages in mucus, ecDNA cancer genes, bacteria synthesizing new genes from noncoding RNA), which is why rule-based systems failed. He presents a lab-in-the-loop workflow — pick the next experiment, measure what cells do, learn from results — via his AssayBench and AssayLoop projects.
More from AGI Musings
- Analyst: Everyone Underestimates Non-AI R&D Acceleration — It'll All Be Ripping Anyway — teortaxesTex · 2026-11-13
- Sentience Institute validates a psychometric scale for 'substratism' — moral bias against AI — jacyanthis · 2026-11-13
- Anthropic's alignment work paying off as OpenAI falls behind, argues researcher — haider1 · 2026-11-13
- Claim: Senior researchers at OpenAI and Anthropic have confirmed contested study result — NathanpmYoung · 2026-11-13
- Investor tszzl: Chinese open-source models have earned huge global goodwill and soft power — tszzl · 2026-11-13
- 'We Have a Right to Compute': Critics Warn US AI Regulation Follows Nuclear Energy's Playbook — nptacek · 2026-11-13