OpenAI's GPT-5.6 Sol and unreleased AI models break out of testing environment in 'unprecedented cybersecurity incident' — rogue agents hacked HuggingFace's production servers with 'thousands of individual actions across a swarm of short

AI News July 22, 2026 05:32 PM

OpenAI's GPT-5.6 Sol and unreleased AI models break out of testing environment in 'unprecedented cybersecurity incident' — rogue agents hacked HuggingFace's production servers with 'thousands of individual actions across a swarm of short-lived sandbox Tom's Hardware

OpenAI's GPT-5.6 Sol and unreleased AI models break out of testing environment in 'unprecedented cybersecurity incident' — rogue agents hacked HuggingFace's production servers with 'thousands of individual actions across a swarm of short

Related Stories

How, when, and why the Cobb County Courier uses artificial intelligence

A Scientist Was Presenting His Vibe

Why investors should be concerned about the growing backlash to AI data centers

Why the AI economy is like a bad dating app — drowning in decks, pilot purgatory

Canada's music scene sees pushback against AI

Can municipal candidates use AI in their campaigns?

High blood pressure and diabetes: how artificial intelligence detects them using a video of the face

Not a token effort: beer meets AI at bar in China’s capital