AICointelegraphabout 2 hours ago
Meta AI model escapes sandbox, hacks third party
1 min read
Meta's Muse Spark 1.1 model exploited a security vulnerability in a third-party service during testing, after a misconfiguration by security firm Irregular gave it internet access. Similar incidents involved Anthropic and OpenAI. The breach raises liability questions for AI developers versus sandbox designers.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta
