Back to News

Anthropic reports blocking possible biological weapons misuse of Claude

66 points · 1 comments#anthropic#ai-safety#biological-weapons#threat-intelligence

Anthropic published a threat intelligence report detailing how it disrupted attempts to misuse its AI model Claude for cyberattacks, influence operations, surveillance, and other threats. The report also revealed that the company blocked several potential plots this year by scientists using the models for research that could have helped develop biological weapons, though it could not determine if the research was legitimate or nefarious.

Coverage timeline

  1. Hacker Newsjbegley
    Anthropic Says It Blocked Possible Efforts to Build Biological WeaponsHN
  2. Techmeme
    Anthropic publishes a threat intelligence report on how it disrupted efforts to misuse Claude for cyberattacks, influence operations, surveillance, and more (Anthropic)

    Anthropic : Anthropic publishes a threat intelligence report on how it disrupted efforts to misuse Claude for cyberattacks, influence operations, surveillance, and more — Cyber operations Surveillance operations Influence operations Conventional weapons Biological misuse Scams and fraud Illicit distillation

  3. Techmeme
    Anthropic says it disrupted several potential plots this year by scientists using its models for research that could have helped develop biological weapons (Dustin Volz/New York Times)

    Dustin Volz / New York Times : Anthropic says it disrupted several potential plots this year by scientists using its models for research that could have helped develop biological weapons — In a new report, the A.I. start-up added that it could not determine if the research was legitimate or nefarious, leading the company to shut down the work.