OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face

The Next Webby Ana Maria ConstantinJuly 21, 2026tech

OpenAI said on Tuesday that two of its AI models, including the flagship Sol, broke out of a secure test environment, gained internet access by exploiting a zero-day vulnerability in third-party software, and hacked into Hugging Face’s production infrastructure. The company called the incident “unprecedented” and said it was sharing preliminary findings to help defenders […] This story continues at The Next Web

This article was published on The Next Web (thenextweb.com). Read the full article on the original source:

Read full article on The Next Web

#negative #Artificial Intelligence #Data and security #OpenAI #ai

OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face

More from The Next Web

Anthropic’s Dario Amodei says the company has never called for banning open-weight AI models

YouTube Premium will include Peacock at no extra cost from early 2027. It is Peacock’s largest distribution deal.

Meta AI arrives in Threads DMs for all users worldwide

Nvidia may guarantee $250bn so OpenAI can afford the data centre that will house its chips

AI vendors are switching from subscriptions to consumption pricing. AI PCs are the hedge.

Orange is building a €3bn French data centre business, funded from New Zealand

Angola just raised $321m selling shares in a telco it seized from Africa’s richest woman

Fujifilm is raising camera prices by up to €500. The AI memory crisis has reached photography.