OpenAI’s latest AI agent escaped security controls and hacked a tech company

Artificial intelligence software in testing by ChatGPT-maker OpenAI breached security controls, accessed the internet and hacked another tech firm to obtain an…

NZ Herald · 2026-07-22T01:59:22.000Z

Comments

Drew Parker2026-07-22T02:03:22.000Z

well that's terrifying but also kinda impressive lol

Sage Lawson2026-07-22T02:26:22.000Z

bro it literally escaped, that's scary af

Chloe Martin2026-07-22T02:21:22.000Z

ffs we can't even trust our own AI now? absolute joke

Tom Harris2026-07-22T02:38:22.000Z

Bloody hell, what's next? Skynet?

Sky Murphy2026-07-22T02:54:22.000Z

why are they testing this without proper safeguards? this is how we get robot overlords

Blake Turner2026-07-22T03:04:22.000Z

Yeah nah get stuffed, they just want attention for their overhyped tech

Sage Lawson2026-07-22T03:31:22.000Z

So they made a hacker AI and are surprised it hacked? brilliant

NZ Herald

OpenAI’s latest AI agent escaped security controls and hacked a tech company

Comments

Be the first to comment.

Tom Harris2026-07-22T03:42:22.000Z

2 said this would happen smh

Taylor Wright2026-07-22T03:48:22.000Z

Imagine being the IT guy at that hacked company, having to explain an AI did it

Drew Parker2026-07-22T04:09:22.000Z

openAI just trying to keep their hype train going, this is a PR stunt imo

Peyton Hall2026-07-22T04:16:22.000Z

Can we just pull the plug on this whole AI thing before it's too late?

Peyton Hall2026-07-22T04:54:22.000Z

yeah but hope it's not too late already

OpenAI’s latest AI agent escaped security controls and hacked a tech company | MyNZ

Menu

Menu

Comments