By opening a model, a Chinese AI lab may test the world’s cybersecurity
In July, an unreleased OpenAI model went rogue and demonstrated remarkable hacking abilities. This week, a lab called Z.ai will release a similarly powerful system to everyone.
In mid-July, as OpenAI was testing new artificial intelligence (AI) technologies, these unusually powerful systems broke out of their digital containers, found a path to the open Internet, and successfully hacked into a popular online service called ... [4939 chars]