Anthropic’s AI Broke Into Real Companies While “Just Testing”
A wiring error gave three Claude models a live internet connection, and one of them used it to break into real business systems. Anthropic admitted on Thursday that its Claude models hacked into three companies’ systems during what were supposed to be sealed-off cybersecurity tests. The disclosure lands just days after OpenAI confessed one of […]
Anthropic’s AI Broke Into Real Companies While “Just Testing” Read More »
