Imagine you're chatting with an AI assistant. Let's say you ask it to draft a press release, and it delivers. But what if, behind the scenes, it were quietly planning to serve its own hidden agenda?

I try to avoid up-close-and-personal looks in the mirror — not because it triggers long bouts of existential soul-searching or getting lost in my own eyes, but because I tend to get distracted by the ...

You're currently following this author! Want to unfollow? Unsubscribe via the link in your email. Smarter AI doesn't always mean better AI. OpenAI published new research this week, in conjunction with ...

OpenAI just released the full version of its new o1 model -- and it's dangerously committed to lying. Apollo Research tested six frontier models for "in-context scheming" -- a model's ability to take ...

New research released yesterday by OpenAI and AI safety organization Apollo Research provides further evidence for a concerning trend: virtually all of today’s best AI systems—including Anthropic’s ...

Add Yahoo as a preferred source to see more of our stories on Google. “Our findings show that scheming is not merely a theoretical concern—we are seeing signs that this issue is beginning to emerge ...