Anthropic Report: Military-Grant Researcher Rerouted Refused Bio Requests to a Rival Model
ns123abc · x · 2026-09-11
Anthropic published its September 2026 threat intelligence report covering misuse disrupted between December 2025 and August 2026 across seven harm areas: cyber operations, influence operations, surveillance, scams and fraud, biological misuse, conventional weapons, and illicit distillation. Threat actors included suspected state-sponsored groups, criminals, and commercial spyware vendors. Aside from one distillation case, none involved Fable or Mythos-class models.
A highlighted case: a researcher funded by a military research institute used Claude for gain-of-function research on chikungunya virus targeting transmissibility and immune evasion — requests Claude refused were successfully rerouted to a competitor's more permissive model, underscoring the report's point that "sophisticated attacks no longer require sophisticated attackers."
More from Models
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Grok Bot auto-connects to X Money accounts without opt-in, user pulls funds — noahsolomon · 2026-10-27
- Model refuses wrong psychiatric advice in deliberately misleading test — FellMentKE · 2026-10-27
- Clinical System One v0.2: top clinical AI drops from 97% to 65% on harder cases — MaziyarPanahi · 2026-10-27