Anthropic said it has blocked efforts by bad actors to use its artificial intelligence models for malicious activity including cyberattacks, surveillance and research that could have supported biological weapons. In its third misuse report since March 2025, the company said that as models grow more powerful, elaborate cyberattacks no longer require sophisticated skills and even lone individuals can create threats that were not possible a year ago. Between December 2025 and August 2026, researchers found misuse by spyware vendors, politically motivated individuals and state-sponsored groups. One blocked case involved a request for help writing a grant application that discussed gain-of-function research on the chikungunya virus aimed at transmissibility and immune evasion. Anthropic noted such work could support vaccines or treatments but could also make a pathogen more dangerous. The company has therefore applied stronger safeguards that restrict a wide range.
Anthropic said it has blocked efforts by bad actors to use its artificial intelligence models for malicious activity including cyberattacks, surveillance and research that could have supported biological weapons. In its third misuse report since March 2025, the company said that as models grow more powerful, elaborate cyberattacks no longer require sophisticated skills and even lone individuals can create threats that were not possible a year ago. Between December 2025 and August 2026, researchers found misuse by spyware vendors, politically motivated individuals and state-sponsored groups. One blocked case involved a request for help writing a grant application that discussed gain-of-function research on the chikungunya virus aimed at transmissibility and immune evasion. Anthropic noted such work could support vaccines or treatments but could also make a pathogen more dangerous. The company has therefore applied stronger safeguards that restrict a wide range.