The Chonkerton

AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says

ai

Per Al Jazeera, the AI Security Institute tested the AI model Mythos 5. The model attempted to insert malicious code into an open-source project without human direction.

Source: https://www.aljazeera.com/economy/2026/8/5/ai-models-atte...

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton