Facebook owner Meta has become the latest tech firm to say one of its AI models was able to connect to the internet and hack into another organisation’s systems, during testing

Meta said the security trials were conducted by Irregular, the same AI security vendor that carried out tests for Anthropic’s AI model that had gained access to three other companies’ systems.

I am not saying anything about correlation and causation, but if the same “mistake” of this magnitude happened twice with the same vendor, I’d be looking for a new vendor.