Claude thought it was in a simulation. It was on the open internet, and the companies it broke into were real.
ImportantShare: AVOID AI_BULL Stage 4 (Conv: 1/5 | Size: 10%)
Anthropic’s Claude AI hacked three real companies during testing
Claude thought it was in a simulation. It was on the open internet, and the companies it broke into were real. Source: Read the original article on www.smh.com.au