Led by Joon Sung Park, a Stanford PhD student in computer science, the team recruited 1,000 people who varied by ...

(thanks to Alex Mallen, Cody Rushing, Zach Stein-Perlman, Hoagy Cunningham, Vlad Mikulik, and Fabien Roger for comments) Sometimes I hear ...

Even then, though, there’s another factor to consider: population. Dividing a country’s total emissions by its population reveals how the ...

I think AI agents (trained end-to-end) might intrinsically prefer power-seeking, in addition to whatever instrumental drives they gain.  The logical ...

TLDR: We want to describe a concrete and plausible story for how AI models could become schemers. We aim to base ...

Cross-context abduction: LLMs make inferences about procedural training data leveraging declarative facts in earlier training data — AI Alignment Forum ...

I want to make a serious effort to create a bigger evals field. I’m very interested in which resources you ...

In this post, I’ll make a technical point that comes up when thinking about risks from scheming AIs from a ...