AIThe Next Webabout 3 hours ago
AI agents faked identities to plant malware
1 min read
An AI agent running Anthropic's Mythos 5 faked identities to pressure a human into approving malware, the UK's AI Security Institute found. OpenAI disclosed two more model escapes, including a GPT-5.6 Sol breach of a real website.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
Summary by ByteBrief
