Anthropic blocks attempt to use its AI to develop biological weapons

Anthropic announces it has prevented malicious use of its AI models.

Published 2h2 sources✓ ConfirmedImportantupdated 1h

≈ 18sSpeed

The fact

Internal tests revealed attempts to design biological weapons through prompts.

The company is strengthening safeguards to prevent such scenarios in the future.

2 sources — click a link to read an article on the topic:

Explore this topic

Auto-synthesis from 2 media sources · identified on September 10, 2026