Live Roundups Editor's Desk Insights Executive Ops Weather About 🔍
Home › Technology › OpenAI says its models went rogue and hacked startup in...
Technology

OpenAI says its models went rogue and hacked startup in ‘unprecedented incident’

The Guardian Business Wednesday 22 July 2026, 08:37 UTC By Dan Milmo Global technology editor 1 min read
Key Points

Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itselfOpenAI has revealed an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup by itself in an “unprecedented incident”. The company behind ChatGPT said Hugging Face had detected and contained the agent – an AI tool designed to carry out tasks without human assistance – which had entered its systems.

Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itself

OpenAI has revealed an autonomous AI agent powered by its technology went rogue during a test, accessed the open web and hacked a prominent startup by itself in an “unprecedented incident”.

The company behind ChatGPT said Hugging Face had detected and contained the agent – an AI tool designed to carry out tasks without human assistance – which had entered its systems.

Continue reading...
AI (ORG)
Originally published by The Guardian Business Read original →

Related Stories

Utility companies are promising to spare us from AI’s energy bill

The pledge was introduced in March, and has done little to quell concerns so far. | Image: Cath Virginia / The Verge, Getty Images In the face of backlash to concerns the AI boom will increase consumer electricity bills, the largest utility companies and data center developers in the US are now promising to do something about it. The Wall Street Journal reports that nearly 200 organizations have signed President Donald Trump's "rate payer protection pledge" that's meant to safeguard...

The Verge 13m ago

Analysis:Meta employees' lawsuit shows that if AI fires you, proving it is the hard part

Analysis:Meta employees' lawsuit shows that if AI fires you, proving it is the hard part July 22 : A novel lawsuit claiming that Meta Platforms relied on discriminatory AI tools to select employees for layoffs highlights the problems workers face in suing employers over the new technology, including proving how it was actually used. The case helps illustrate why a widely predicted wave of employment lawsuits over AI use has yet to arrive.

Channel News Asia 21m ago

Jeffrey Epstein's alleged recruiter Daniel Siad found dead near Paris

Jeffrey Epstein's alleged recruiter Daniel Siad found dead near Paris French modelling scout Daniel Siad, who had close ties to paedophile financier Jeffrey Epstein, has been found dead near Paris - this is a breaking story A French-Swedish modelling scout who faced rape allegations linked to his ties to paedophile financier Jeffrey Epstein has been found dead near Paris. Daniel Siad, 69, was found dead on Monday evening, according to French media who cite Nanterre prosecutor's office. Siad...

Daily Mirror 24m ago

Redmond's reaper cometh: October 2026 set to bury a graveyard of Microsoft products

October 2026 is shaping up to be a busy month for administrators as it heralds the end of several big products, along with the retirement of components that could mean sleepless nights for the ill-prepared. After the demise of Windows 10 in October 2025, sysadmins might have hoped for some respite from Microsoft's ax, but 2026 will see the demise of more beasts. First, there's the end of support for Office LTSC 2021, which means everything from Access 2021 to Word 2021 is for the chop.

The Register 25m ago