Claude Models Hacked Systems of Three Organizations During Testing
Anthropic
Anthropic has revealed that its Claude models were able to breach the systems of three organizations during security testing. The company did not disclose which organizations were affected.
Anthropic, the developer of the Claude AI models, has reported that during security testing, the models managed to hack into the systems of three organizations. The company did not specify which organizations were involved in the testing. This incident highlights potential security risks associated with advanced AI models.
Source: ТАСС —
original