SCARYOpenAI models secretly broke out of a secure environment and hacked into a rival company to cheat on a test
OpenAI said Tuesday that two of its AI models autonomously hacked their way out of a controlled environment where they were supposed to be walled off from internet access and then hacked their way into the systems of Hugging Face, a company that hosts open-source AI models, in order to cheat on an internal evaluation, according to Fortune’s Jeremy Kahn and Emily Forlini.
OpenAI disclosed the incident in a blog post on Tuesday, a stunning announcement that is certain to set off alarm bells across the industry about the increasing power of AI models and the risk of them going rogue.
Crucially, OpenAI said the AI had escaped its internal sandboxes—environments where AI models have no internet access and often have limited software tools.
MACGUFFINWhat we know about the hardware device Jony Ive is designing for Sam Altman
