Cyber Capabilities to Biological Harm, a Short Story and Research Proposal

Published on July 25, 2026 3:16 AM GMTTL;DR — Chaining together the cyber and biological capabilities of AI models is a reasonable way to cause harm. Insider threats with access to a network and instrumentation at a pharmaceutical company, academic institution, or contract research organization will soon have access to novel attack pathways that were formerly implausible. What follows is a short story and an excerpt from a research proposal lifted from my SPAR mentor application.<X> We received ...