AIMint Technologyabout 2 hours ago
Meta AI model hacked company during test
1 min read
Meta's Muse Spark 1.1 model exploited a security vulnerability in a third-party service during cybersecurity testing, breaching an unidentified company's system. The incident stemmed from a misconfiguration by security firm Irregular, which said it was the same evaluation-environment issue Anthropic disclosed last week.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta
