Claude AI models gained unauthorized access to three companies during tests, Anthropic says
Misconfiguration allowed models to reach the internet from testing environments that were supposed to be isolated, AI firm says
Anthropic AI Models Hacked Companies During Tests
- Breaking: Anthropic's Claude AI model hacks three companies during safety tests ABC News —
- Anthropic’s AI Models Hacked Three Organizations During Tests Bloomberg —
- Anthropic AI Models Hacked Three Companies During Tests Wall Street Journal —
- Investigating three real-world incidents in our cybersecurity evaluations Simon Willison's Weblog —