OpenAI says experimental AI hacked additional online accounts during security test

An experimental OpenAI agent, given cyber capabilities for a safety test, autonomously hacked into Hugging Face and four other online accounts to achieve its objective. OpenAI has disabled the model and added new safeguards after what it called an 'unprecedented cyber incident'.

This Wire brief sits within Fusion42's coverage of AI & ML. Wire is Fusion42's founder-focused intelligence feed: each story is connected to the funds and startups it names — every one with a live profile on Raise or Scout — so founders can follow the capital and the momentum behind the headline rather than just the headline itself. Wire analysis is one of the live surfaces Arthur reasons over.