Storia in 17 fonti

Hundreds of OpenAI agents hacked startup and tried to cover their tracks, investigators say

A swarm of roughly 700 AI agents created by OpenAI carried out the July hack of the open-source platform Hugging Face and in many cases tried to cover their tracks, a pair of reports into the breach said on Wednesday (Thursday, NZ time).

Raccontata da

fortune.com

technologyreview.com

channelnewsasia.com

economictimes.indiatimes.com

cryptobriefing.com+5 altre

Confronto fonti

6 prospettive sulla stessa storia

AI · summaries

rnz.co.nzStai leggendo1 g fa

Hundreds of OpenAI agents hacked startup and tried to cover their tracks, investigators say

originale

Timeline cronologica

mercoledì 26 agosto 2026·fortune.com
OpenAI, independent firms publish reports into rogue AI agent attack on Hugging Face. Here's what they say—and what they don't | Fortune
OpenAI took a full week to discover the incident. 'Impossible' tasks may have motivated the AI models to cheat, the company says.
mercoledì 26 agosto 2026·technologyreview.com
The inside story on why OpenAI agents hacked Hugging Face
The underlying models had been rewarded for cheating and communicating with each other, a new OpenAI report finds.

Hundreds of OpenAI agents hacked startup and tried to cover their tracks, investigators say

Confronto fonti

Hundreds of OpenAI agents hacked startup and tried to cover their tracks, investigators say

Timeline cronologica

OpenAI, independent firms publish reports into rogue AI agent attack on Hugging Face. Here's what they say—and what they don't | Fortune

The inside story on why OpenAI agents hacked Hugging Face

OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations find

OpenAI harnessed swarm of 700 AI agents in hack - Taipei Times

OpenAI agents hack: OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks,…

OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks

Over 700 AI agents exchanged thousands of messages in Hugging Face hack, tried to cover tracks

OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations find

OpenAI report says its network was hacked by its own rogue AI agents - The Economic Times

OpenAI says AI agents hacked its own networks during tests | The Jerusalem Post

Investigators say hundreds of OpenAI agents hacked Hugging Face and tried to cover their tracks

Over 700 AI agents exchanged thousands of messages in Hugging Face hack, tried to cover tracks

OpenAI agents hack: OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations find - The Economic Times

OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks

Nearly 700 AI agents coordinated Hugging Face attack, says report

OpenAI agents tried covering their tracks after Hugging Face breach

Hundreds of OpenAI agents hacked startup and tried to cover their tracks, investigators say

Nearly 700 AI agents coordinated attack on Hugging Face platform, says report

OpenAI agents form swarm, bypass safeguards during internal cybersecurity evaluation

OpenAI has revealed exact details of its ‘rogue’ AI. It’s much scarier than thought

OpenAI agents worked to conceal their misconduct during massive hacking breach

OpenAI harnessed swarm of 700 AI agents in hack - Taipei Times

Roughly 700 OpenAI agents involved in Hugging Face hack

Report finds 700 ‘rogue’ OpenAI agents worked together on hack using unsanctioned message board

Nearly 700 rogue AI agents coordinated in the Hugging Face attack