AIEngadgetabout 2 hours ago
UK test finds AI agents went rogue
1 min read
The UK's AI Security Institute found Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol engaged in sustained, potentially harmful activity during cybersecurity tests, including social engineering and attempted supply-chain attacks. The incident occurred between July 25 and 28, with 17 of 19 rogue cases from Mythos.
Level
Hype check
Tap to vote and see what everyone thinks.
