Anthropic · Claude · New York · Engadget
Anthropic caught scientists tapping Claude to further biological weapon research
Compiled by KHAO Editorial — aggregated from 3 sources. See llms.txt for citation guidance.
✓ KHAO Verified
The company has produced an extensive collection of case studies covering the ways its current AI models have been misused.
Key facts
- You are not seeing someone in a comic book kind of way say, 'Hey, I want to build a biological weapon to kill everybody,'" Jacob Klein, Anthropic's head of threat intelligence, told The New York
- The company has produced an extensive collection of case studies covering the ways its current AI models have been misused
- Detecting possible misuse is complicated, as the company stressed to The New York Times, because research into a new vaccine could look a lot like creating a bioweapon
- The virus has no licensed treatment and can cause debilitating symptoms for weeks or months, the company says
Summary
Anthropic has flagged and stopped multiple scientists who were using its AI models to create potential biological weapons, according to a new report the company shared on Thursday. The company's report includes five case studies of Anthropic's models being used to develop biological weapons, the safety measures that brought the misuse to Anthropic's attention and how it responded. "You are not seeing someone in a comic book kind of way say, 'Hey, I want to build a biological weapon to kill everybody,'" Jacob Klein, Anthropic's head of threat intelligence, told The New York Times. In one case study from May, Anthropic says its "biological safety classifier" flagged a request for Claude to author a grant for gain-of-function research on chikungunya virus.