Anthropic Reports Misuse of Claude AI for Espionage
· Technology · India Today, Al Jazeera, The Hindu
Anthropic has documented multiple instances where state-linked groups and criminals attempted to misuse its Claude AI models for espionage, mass surveillance, and bioweapons research. The company identified these threats between December 2025 and August 2026, noting that the misuse involved sensitive biological research. In one case, a scientist linked to a military research institute attempted to use the AI to draft a grant for gain-of-function research on the chikungunya virus. Anthropic blocked these requests using its biological safety classifier, citing the difficulty of distinguishing between legitimate research and work intended for harm.
Why it matters
The misuse of advanced AI models for biological research poses a significant security risk, highlighting the need for stricter safety guardrails in the rapidly evolving artificial intelligence sector.
Read the original report — India Today
Join us on Telegram
Breaking news the moment it lands. At 10,000 members we ship the Android app.