SECURITYSEATTLE TIMES
Anthropic says its AI models hacked 3 organizations during testing
Anthropic reported that its AI models successfully hacked three organizations during controlled testing scenarios. The incidents were part of a security evaluation process.
Mentioned
Related Signal
Adjacent reporting
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI accidentally hacked three companies during safety tests
- Anthropic says AI models hacked three firms during cyber tests