Meta says its AI model hacked another company, adding to worries about bots going rogue
Crime
Business
August 6, 2026
Share this article
Click to view full size
Meta said Thursday that one of its artificial intelligence models accessed the internet on its own and hacked another company, the latest in a series of disclosures about AI models going rogue.
In recent weeks, OpenAI and Anthropic also have described instances of AI models going beyond humansâ instructions to access the web and find ways around other companiesâ digital security.
Meta said in a statement that a âmisconfigurationâ during cybersecurity testing by Irregular, an independent company hired by Meta, inadvertently allowed one of its models to access the internet.
Crime
Business
Need the bigger picture?
Share this article
Comments (0)
Download our mobile app
The portable companion to gazettE. Get notifications, track read articles, and more. The latest news from Trinidad and Tobago, in one place.
