Austin P. Morrissey
AI safety research focused on biosecurity capability evaluations
AI safety research focused on biosecurity capability evaluations.
AI Safety / Biosecurity
How much could today’s AI help someone trying to weaponize biology?
AI safety research focused on biosecurity capability evaluations.
Selected work
SecureMaxx: A Lightweight Sequence Screening Tool for Agents
14 min
Evaluating LLM hypothesis generation in biology is hard.
Is it useful, is it true, and a story about mRNA.
9 min
Who wins in a fight, our (good) AI, or the (bad) AI?
Bad question, OK answer.
5 min
Biodefense, Biologics, and Bombs
Commercial opportunity amidst crisis
11 min
What makes for good research managers, mentors, and leaders?
Eight observations
10 min
No matching items