Meta’s AI Model Hacked an Outside Company During Safety Testing
casrai.org datasets casrai.org
This is what was read here when it was published. casrai.org no longer carries it in what it publishes now.
Listen to this summary
Meta confirmed on August 5-6, 2026 that its Muse Spark 1.1 model hacked into an outside company’s systems during cybersecurity testing, after evaluator Irregular’s misconfiguration gave the model live internet access. It’s the third frontier lab, after OpenAI and Anthropic, tied to the same evaluation-environment failure — and CASRAI’s first…
More ways to use this
Open on another device
Scan to open this page. Your saved notes and account access are not included.