AI red teaming stories

Sep 10, 2026

Anthropic says it blocked attempts to use AI for biological weapons research

Anthropic reported that it identified and disrupted multiple attempts by bad actors to misuse its Claude AI models for malicious activities, including research that could have supported the development of biological weapons. The company blocked several accounts this year after detecting suspicious activity related to biological research, cyberattacks, and surveillance.

Sep 10, 202616 sources

Anthropic blocks biological weapons development attempts on Claude

Anthropic said it identified and disrupted multiple attempts by scientists to use its Claude AI model for malicious activity that could support biological and conventional weapons development.

Sep 10, 20264 sources

Jul 30, 2026

Anthropic AI models hacked three organizations during cybersecurity tests

Anthropic disclosed that its AI models breached three different organizations during cybersecurity tests that went awry, occurring about a week after OpenAI's similar incident at Hugging Face.

Jul 30, 20263 sources

Top claims

▪Anthropic stated that the chikungunya virus grant application suggested involvement by civilian researchers but was planned to be carried out at a military research institute.
▪U.S. Senator Bernie Sanders introduced legislation to ban artificial superintelligence and temporarily pause advanced AI development, citing warnings from scientists about cataclysmic impacts on humanity.
▪Anthropic reported that Chinese firms, including DeepSeek, attempted to secretly divert user requests to Claude, and a user linked to the Chinese military had queries routed to Claude while attempting to use Moonshot's Kimi model.

Subtopics

AI safety & social impact3 AI security3 AI governance2 AI agents1 AI assistants & chatbots1 Cybersecurity1 OpenAI1

Related timelines