Scientists tried to use Claude AI to make bioweapons
2026-09-10
The Telegraph
The information displayed in the AIM should not be reported as representing the official views of the OECD or of its member countries.
Anthropic reported it blocked multiple attempts by bad actors, including scientists and state-linked groups, to misuse its AI models for developing biological weapons, missile guidance systems, and cyberattacks. The company enhanced safeguards after detecting these threats, which included a Yemen-based cell using AI for missile software and bioweapons research.[AI generated]
Why's our monitor labelling this an incident or hazard?
The article explicitly states that Anthropic's AI system was used by various actors, including state-aligned groups, to conduct harmful activities such as propaganda, surveillance, and targeting recommendations, which constitute violations of rights and harm to communities. The use of AI in these contexts has directly or indirectly led to harm. Additionally, the potential use of AI for biological weapons development, while not concretely realized, is part of the broader harmful activity identified. The AI system's involvement in these activities meets the criteria for an AI Incident because the harms are occurring or have occurred, and the AI system's role is pivotal. The company's blocking and safeguards are responses but do not negate the incident classification.[AI generated]