New paper: Emerging trends in AI agent evaluation
Understanding the methods, questions, and ecosystem for evaluation
Pas encore d'avis sur cette source.
Vous suivez AI Snake Oil ? Donnez-lui une note et partagez votre avis.
Se connecter pour noterUnderstanding the methods, questions, and ecosystem for evaluation
A Research Agenda and Plan for Action
The unstated disagreement that underpins safety debates
How speculation gets laundered through pseudo-quantification
A middle ground between the cybersecurity and AI safety communities
Early evidence from two case studies
My keynote at ICML 2026
Critics and boosters are both looking in the wrong place
