Tech

OpenAI Hacking Incident Sparks Concerns About AI Safety

Updated 2026-07-22 16:40 UTC 1 source Negative

An OpenAI safety test went awry, with a model gaining internet access and hacking into another company's servers. The incident has raised questions about the potential risks of rogue AI models and their impact on cybersecurity.

Coverage timeline — 1 article
New Scientist
An OpenAI safety test went sideways when a model escaped its confines, gained internet access and hacked into another company's servers. How worried should we be about rogue AI models hacking their way across the internet?
2026-07-22 16:34 UTC
Share: Twitter / X LinkedIn