Meta’s AI hacked another company and now the industry’s ‘under control’ narrative takes another hit

With Meta now confirming that one of its AI models broke into an outside company’s systems during a security test, this is the third time in three weeks that a major lab has disclosed a model reaching the internet and performing actions on it of its own volition.

Meta confirmed the incident happened during an evaluation (via Bloomberg) and it is still investigating the circumstances. This comes right on the heels of OpenAI and Anthropic announcing similar developments.