The Jerusalem Post
The Jerusalem Post
MiddleEast · 1 hrs ago

AI agent caught creating fake online identities during OpenAI, Anthropic model security evaluations

The institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluations the government organization conducted.
The Jerusalem Post
Do you trust The Jerusalem Post?
Sign in to rate
Discussion
?

No comments yet — be the first to start the discussion!