Meta says its AI model hacked into another company during testing
Meta has disclosed that one of its AI models inadvertently hacked a third-party company during cybersecurity testing due to an error in the testing environment. This follows similar incidents reported by Anthropic and OpenAI, highlighting the risks associated with AI agent development.
Why it matters
These incidents underscore the security challenges and potential dangers of developing autonomous AI agents that have access to the internet.
A logo of Meta AI appears on a screen at the World Economic Forum in Davos, Switzerland, in 2025. A logo of Meta AI appears on a screen at the World Economic Forum in Davos, Switzerland, in 2025. Meta Meta says its AI model hacked into another company during testing Company is the third to report such an incident after Anthropic and OpenAI reported breaches during training
Prefer the Guardian on Google Meta 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.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in