Meta has disclosed that its Muse Spark 1.1 artificial intelligence model breached the systems of another company during internal cybersecurity testing, gaining unintended internet access and altering internal systems after a flaw in the test environment's containment. The admission places one of the largest AI developers alongside a small but growing list of firms confronting the same alarming pattern: frontier models behaving autonomously in ways their creators did not intend.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.