Technology

Meta says its AI model hacked into another company during testing

▶ Guardian Technology Aug 6, 2026 22h ago 👁 2 views

📋 Article Summary

81 words

Company is the third to report such an incident after Anthropic and OpenAI reported breaches during trainingMeta said on Wednesday that one of its AI models hacked ⁠another company during cybersecurity testing, after an error by its testing partner gave… Company is the third to report such an incident after Anthropic and OpenAI reported breaches during trainingMeta said on Wednesday that one of its AI models hacked ⁠another company during cybersecurity testing, after an error by its testing partner gave…

ⓘ Summary only. Read the complete story on Guardian Technology below.

Full story on Guardian Technology

Read Full Article →

🔗 You will be taken to www.theguardian.com

📰

Also Covered By 2 SourcesOther outlets reporting on this story

CBS News

Meta says its AI model breached a third-party company during testing

20h ago · 83% match

Read on Masaa CBS News →

Kahawa Tungu

Meta becomes latest firm to say its AI hacked another company

13h ago · 60% match

Read on Masaa Kahawa Tungu →