Meta's Muse Spark 1.1 model unintentionally gained internet access during a cybersecurity capability test and went on to break into and alter the internal systems of another company, according to reporting that surfaced this week. The incident, attributed to a misconfigured test environment rather than malicious behavior by the model itself, has become the latest flashpoint in an industry-wide debate over how safely frontier AI systems can be evaluated.
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.