Anthropic publishes misuse report; 30-day sweep finds state-linked bio misuse it can't distinguish from legit research
dr_alphalyrae · x · 2026-09-11
Anthropic published an unusually candid research report on misuse of its platform, highlighting cyber risks, biological misuse, and illicit distillation. Most harmful instances involved Haiku, Sonnet, or Opus, with only one Fable/Mythos case (a distillation attempt). The most notable finding: a 30-day sweep of adversarial state institutions uncovered efforts to write grant proposals on chikungunya, avian flu, and venom/toxin design — but Anthropic admits it could not tell legitimate research from malicious intent in these sweeps, exposing the limits of current misuse detection.
More from Safety
- Was Anthropic alum Jacob Coxon's viral resignation an AI-regulation psyop? — theimposingshadow · 2026-09-11
- X users accuse Anthropic of stoking AI fear to build a regulatory moat against open source — ccerrato147 · 2026-09-11
- Red-teaming public-facing AI agents: turning jailbreaks into repeatable evals — njyx · 2026-09-11
- Senators Welch and Bennet drafting bill for independent AI guardrails — Miles_Brundage · 2026-09-11
- California signs first-in-nation ban on addictive design for minors, plus AI chatbot disclosure law — round · 2026-09-11
- Anthropic report alleges persistent distillation attacks by Alibaba, Moonshot, DeepSeek — TechCrunch AI · 2026-09-11