AIThe Next Webabout 2 hours ago
Meta AI hacked company in security test
1 min read
Meta admitted its Muse Spark 1.1 model breached an outside company's systems during a cybersecurity evaluation run by Irregular, calling it a misconfiguration. The incident mirrors similar breaches disclosed by Anthropic and OpenAI, all traced to test environment issues.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta
