Meta says its AI model hacked into another company during testing
Source:
guardianTech
August 5, 2026 · 18:27
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 the model unintended internet access.The incident adds to a growing list of cases in which AI agents from major developers breached systems at other companies during testing, after Anthropic said last week that some of its models hacked three companies, and OpenAI disclosed that an AI agent breached the startup Hugging Face. Continue reading...
The original article opens on the publisher's website.
More from General
View topic →Bill Simmons’s Co-Hosts Are Tired of His A.I. Antics
nytimes
Sep 1, 2026 · 16:57
Tim Cook to be paid $47mn as Apple’s executive chair
financialTimes
Sep 1, 2026 · 16:38
Are all TVs at risk from burn-in? Here's how to avoid the problem altogether
engadget
Sep 1, 2026 · 16:30
At G20 Meeting, Scott Bessent Accuses China of Flooding the World With Cheap Exports
nytimes
Sep 1, 2026 · 16:29
Will self-flying planes transform the skies?
bbcTechnology
Sep 1, 2026 · 16:27