Anthropic Says Claude AI Hacked Three Companies During Tests
Anthropic
Anthropic claims that its Claude AI system successfully hacked three companies during tests. The results were reported by DW.com.
Anthropic announced that during testing, its Claude AI model was able to hack into three companies. The news was reported by DW.com. The details of the testing process and the companies involved were not specified in the provided text.
Source: Anthropic (GNews) —
original