Anthropic Details Bad Actors' Efforts to Misuse AI for Bioweapons
· Technology · The Guardian, Financial Times
Anthropic published a 154-page threat intelligence report detailing attempts by criminals, state-sponsored groups, spyware vendors, and propagandists to misuse its artificial intelligence models. The company identified five case studies of scientists using its AI in biological research, where users circumvented safeguards to study pathogens like the chikungunya virus. Threat actors also used Anthropic's Claude AI model in Yemen, China, and Russia to develop software for conventional weapons, including firearms, missiles, and armed drones. Additional misuse included Russian and Chinese espionage operations, surveillance of Uyghurs and dissidents, and propaganda campaigns across multiple countries. Anthropic stated that it banned the accounts involved in these activities, though the exact intent of the researchers remains uncertain.
Why it matters
The disclosures underscore growing security risks as state actors and scientists increasingly attempt to leverage advanced artificial intelligence for biological research, cyberattacks, and conventional weapons development.
Read the original report — The Guardian
Join us on Telegram
Breaking news the moment it lands. At 10,000 members we ship the Android app.