Anthropic blocks AI misuse for potential biological weapons research
AI company detects scientists using Claude for dual-use biological studies, bans accounts but cannot confirm malicious intent.
KEY POINTS
- Anthropic detected AI misuse for dual-use biological research over eight months
- Company blocked studies and banned accounts linked to the work
- Researchers attempted to bypass geographic restrictions and conceal purposes
- Legitimate medical research uses same methods as weapons development
- Anthropic withheld researcher details due to uncertain intent
Anthropic has disclosed that its AI models were used over the past eight months in research that could contribute to biological weapons development, according to a safety report cited by the New York Times. The company blocked the studies and banned associated accounts after detecting attempts to circumvent geographic controls and conceal research purposes.
Threat Intelligence Chief Jacob Klein told the New York Times the cases were not explicit requests for biological weapons but "incredibly nuanced" situations where legitimate vaccine and treatment research overlaps with dangerous pathogen development methods.
“There is no cartoon villain saying 'I want to build a bioweapon to kill everyone.' It is an incredibly nuanced situation.”
Some researchers attempted to access Anthropic models from regions where the service is restricted by bypassing the company's controls. Others tried to hide the true aims of their work to evade safety systems, prompting account terminations.
Anthropic declined to reveal the identities, institutions, countries, or specific biological agents involved, citing the inability to definitively determine malicious intent. The company said missing a potentially harmful study would carry greater risk than over-blocking legitimate research.
1 more source below
COMMENTS (0)
No comments yet. Be the first.
RELATED STORIES
NASA CHAPEA crew exits Mars habitat after 378 days in Houston
Four volunteers complete a year-long Mars simulation at Johnson Space Center and step outside for the first time.
Pennsylvania residents resist AI data center projects ahead of US midterms
Residents in northeastern Pennsylvania are rejecting multimillion-dollar offers and opposing AI data center projects over land loss and power lines.
Madras High Court Bars Protests Targeting Judges and Orders Online Monitoring
The Madras High Court has ruled that public gatherings and online content aimed at personally targeting, defaming or intimidating sitting judges are not protected speech.
- South Korea Fines Samsung $15.2 Million Over Deceptive Galaxy Gaming Claims
- CHP Çanakkale demands end to unauthorized use of party social media accounts
- EU introduces permanent two-euro handling fee on low-value parcels from outside bloc
- INEC Says Registration Officers Added AI Photos to Voter List
- Athens Metro Line 3 closes five stations early for track work
This page was compiled with AI assistance from the outlets named above and passed an automated language check before publication. Montegre has no reporters of its own; the byline names the outlets the story was compiled from. Method and editorial standards