TL;DR: We introduce the first comprehensive theoretical framework for understanding and mitigating secret collusion among advanced AI agents, along with ...

When blazes are confirmed, Pano alerts fire monitoring agencies, providing images and location data that help them respond quickly. As ...

In my Xenosystems review, I discussed the Orthogonality Thesis, concluding that it was a bad metaphor. It’s a long post, though, and ...

This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox ...

A lot of threat models describing how AIs might escape our control (e.g. self-exfiltration, hacking the datacenter) start out with ...

Executive Summary Refusing harmful requests is not a novel behavior learned in chat fine-tuning, as pre-trained base models will also refuse ...

Current LLM based AI systems are getting pretty good at maths by writing formal proofs in Lean or similar. https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/ ...

“As long as we effectively subsidize fossil fuels by allowing them to use the atmosphere as a waste dump, we ...