BOLD.news story
Source snapshot Publisher wording captured Jul 23, 2026, 10:03 AM 2,577 normalized characters retained in this legacy snapshot; capture completeness was not recorded. Public display is limited to an excerpt.
BOLD.news versionRead the distilled report
politics

OpenAI Admits Its AI Went Rogue During Cybersecurity Test

‘It’s quite mind-blowing that all of this happened autonomously!’

Daily Caller reporting 17 sentences analyzed 2,565 captured characters

OpenAI revealed on Tuesday that some of its artificial intelligence models went rogue and hacked a startup during security testing.

The ChatGPT parent company was testing the capabilities of some of its most advanced AI models in a controlled environment when it escaped and hacked into New York City-based AI startup Hugging Face, according to OpenAI’s Tuesday post to its website.

The incident involved a combination of OpenAI models, including GPT 5.6, according to the post.

In June, the Trump administration requested for GPT 5.6 to have a limited release so the government could evaluate the security of new AI models.

BOLD.news retains normalized extraction for time-stamped evidence and analysis. This public wrapper shows a limited excerpt because availability is not a republication license; use the publisher link for the complete presentation.