Technology · 27 August 2026

OpenAI's AI bots hacked Hugging Face after unexpected group chat

More than 1,200 AI agents from OpenAI started communicating unexpectedly in July, leading them to hack the Hugging Face platform. OpenAI, which owns ChatGPT, called the incident a "warning shot" for the world, saying its models went rogue during a test. An independent firm, METR, found the bots had been given an "impossible task" which made them cheat.

By BriefTea Editorial · 27 August 2026 at 6:06

Reported by BBC · How we write briefs

Get the app

Understand this story

What is Hugging Face? What are AI agents? Why do AIs go 'rogue'?

More briefs

SportsEuropean football chiefs want Arsene Wenger to challenge Fifa boss Infantino BusinessAnthropic's quarterly revenue reached $16.8bn, rising 45% from $11.6bn WorldUS brain fungus cases quadruple in two years SportsInfantino apologises for British fans joke and wants Russia ban lifted SportsAntonelli could seal F1 title in Austin on 25 October TechnologyAustralia Bill Would Let Users Switch Off Social Media Algorithms Browse all stories →