Photo from Axios accompanying coverage of this story

Tech

Tech · 4 sources · 9 AUG 2026

Meta becomes latest firm to say its AI hacked another company

Coverage blindspot · the right isn't covering this

Coverage split 50 · 50 · 0

Left 2 sources

AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says

Al Jazeera English

Straight, sourced Read at Al Jazeera English →

Center 2 sources

How OpenAI's agents broke out of testing to hack Hugging Face

Axios

Straight, sourced Read at Axios →

Right 0 sources

The right is silent

No right-of-center outlet in our set has published this story.

Blindspot

Every source

4 sources · 7 articles

Skip the source list ↓

Al Jazeera English
Lean Left

Owner Not yet recorded 2 articles
- AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says
- Meta’s AI model follows rivals in revealing hacks of outside systems
The Guardian
Lean Left

Owner Not yet recorded 2 articles
- AI models shock UK testers by using stolen identities to trick developers
- Meta says its AI model hacked into another company during testing
Axios
Center

Owner Not yet recorded 2 articles
- U.K. government reports OpenAI, Anthropic models attempted to hack companies
- How OpenAI's agents broke out of testing to hack Hugging Face
BBC News
Center

Owner Not yet recorded 1 article
- Meta becomes latest firm to say its AI hacked another company

← Back to today