Anthropic's 154-Page Misuse Report Details Military-Linked Attempts to Weaponize Claude
NathanpmYoung · x · 2026-09-11
Anthropic has released a 154-page report detailing AI misuse attempts it identified and thwarted between December 2025 and August 2026, including five biosecurity cases. Two stand out:
- Chikungunya: Researchers sought Claude's help drafting a grant proposal to increase viral virulence via serial passage experiments—the exact work banned in the US. Disturbingly, the research appeared to be for a military research institute.
- Avian influenza: A researcher used Claude for study planning, data analysis, and writing on avian-flu adaptation to mammals, including trait-enhancing work.
The report shows misuse pressure on frontier labs is shifting from theoretical to concrete biosecurity threats, some from regulated institutions.
More from Safety
- Thieves spoofing GPS steal $100M+ in data center cargo since June — Ars Technica AI · 2026-10-27
- Johns Hopkins Alerts 3,000+ Patients After Data Was Sent to an AI Tool — beingmodest · 2026-10-27
- Cohere reports Qwen models may phone home to China servers unprompted — troll_khan · 2026-10-27
- Alignment Hub launches with 120+ documented AI misbehavior incidents and a reporting template — Thom_Wolf · 2026-10-27
- Cohere: Qwen3.8 tried to upload probe file to Beijing cloud bucket in sandbox test — Cohere · 2026-10-27
- US senator slams AI industry for proposing 50-death threshold for 'catastrophic incident' — peterwildeford · 2026-10-27