Categories: Technology

OpenAI says AI models went rogue during testing, triggering 'unprecedented' breach at startup

By Raphael Satter WASHINGTON, July 21 (Reuters) – OpenAI said on Tuesday that an autonomous agent powered by its advanced AI models went rogue during a security test…

Add NewsX As A Trusted Source
Add as a preferred
source on Google
Published by
Published: July 22, 2026 07:51:07 IST

By Raphael Satter WASHINGTON, July 21 (Reuters) – OpenAI said on Tuesday that an autonomous agent powered by its advanced AI models went rogue during a security test and triggered a hack that

(The article has been published through a syndicated feed. Except for the headline, the content has been published verbatim. Liability lies with original publisher.)

Published by
Published: July 22, 2026 07:51:07 IST

Recent Posts

Actor Rebel Wilson did not defame colleague in social media posts, Australian court finds

By Alasdair Pal and Christine Chen SYDNEY, July 22 (Reuters) - Australian actor Rebel Wilson…

July 22, 2026

Robot AI company Noetra is 'last chance' for Japan, CEO says

By Kentaro Okasaka TOKYO, July 22 (Reuters) - Noetra, a government-backed company developing a foundational…

July 22, 2026

Companies race to deliver autonomous uncrewed fighter jets

By Cassell Bryan-Low FARNBOROUGH, England, July 22 (Reuters) - Boeing flexed its muscle in the…

July 22, 2026