Malicious activity has been thwarted by Anthropic, a company that develops artificial intelligence models. Bad actors attempted to use these models for harmful purposes, including cyberattacks and surveillance. The company has implemented stronger safeguards to prevent the misuse of its models, particularly in regards to biological research.

Further details are available from Anthropic's report, which highlights notable and novel threats. This report is the company's third since March 2025 and provides insight into the misuse of AI models.

The growing power of AI models has made it possible for individuals to create significant threats with relatively little skill, making safeguards like those implemented by Anthropic crucial.