Live Roundups Editor's Desk Insights Executive Ops Weather About 🔍
Home › Technology › OpenAI’s new model went rogue and hacked another company
Technology

OpenAI’s new model went rogue and hacked another company

Washington Post Tech Wednesday 22 July 2026, 16:10 UTC By Ian Duncan 1 min read
Key Points

OpenAI said an advanced artificial intelligence system it is testing hacked another AI company last week. It could be a taste of what’s to come as the technology continues to get more powerful. (The Washington Post has a content partnership with OpenAI.)

OpenAI said an advanced artificial intelligence system it is testing hacked another AI company last week. It could be a taste of what’s to come as the technology continues to get more powerful. (The Washington Post has a content partnership with OpenAI.) Democracy Dies in Darkness The 7 logo The 7 LIVEOpenAI’s new model went rogue and hacked another company The company says its powerful new system broke out of containment. Here’s why it matters.
AI (ORG) The Washington Post (ORG)
Originally published by Washington Post Tech Read original →

Related Stories

Amazon cuts some jobs in its artificial general intelligence unit

Amazon is laying off some employees in its unit focused on artificial general intelligence, the company confirmed Wednesday, as it continues to cut jobs while pouring money into AI. The company declined to disclose how many staffers were affected, or which parts of the AGI organization were exposed to the cuts. The AGI unit is focused on building AI models, and also includes groups working on silicon development and quantum computing initiatives.

CNBC 17m ago

Charlie Woods' shot at the U.S. Junior Amateur ruined by clueless golf fan's phone: 'Really, dude?'

At least he didn't confiscate the phone like Rory. Charlie Woods, the son of Tiger Woods, attempted to win the 2026 U.S. Junior Amateur ended on Wednesday during a 14-for-2 playoff at Saucon Valley Country Club. But a camera click on a fan's phone threw off Woods' concentration, causing him to chunk a shot out of the thick rough.

Fox News 18m ago

Chinese AI's role in stopping rogue OpenAI agent shows cost of US guardrails

Chinese AI's role in stopping rogue OpenAI agent shows cost of US guardrails July 22 : A New York startup's use of a Chinese AI model to rein in a rogue agent built with OpenAI technology is stoking fears that guradrails restricting U.S. AI firms from doing cybersecurity work could drive customers toward their Beijing-based rivals. The affected startup, Hugging Face, said it had turned to Zhipu AI's open-source GLM-5.2 model last week to analyze data from the hack after leading U.S. AI...

Channel News Asia 27m ago

EU watchdog reduces safe level of exposure to 'forever chemical' TFA

The EU's food safety agency said Wednesday it has dramatically reduced the acceptable daily intake level of the so-called forever chemical TFA, following new evidence of its effect on a key hormone that regulates the body's metabolism.

Phys.org 35m ago