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
- SAM3 vs Astra head-to-head: Astra nails player roles at 42/45 where SAM3 fails — TheMoonMidas · 2026-09-11
- NVIDIA Nemotron 3 Embed 8B tops Perplexity's new Q2D-Web agentic RAG benchmark — JFPuget · 2026-09-11
- Third-party benchmark claims GPT-6 Astra leads frontier models at antibody developability prediction — gdb · 2026-09-11
- GPT-6 Astra scores 87.4% on MedXpertQA, beating every other LLM — toshv · 2026-09-11
- Anthropic confirms degraded Claude API performance for US Midwest traffic on Sep 10 — acoolrandomusername · 2026-09-11
- Anthropic confirms Claude API latency degradation affecting US Midwest traffic — ClaudeAI-mod-bot · 2026-09-11