Long Phan

Research Engineer, Center for AI Safety

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

#1412 Spotlight · Mantas Mazeika, Xuwang Yin, Rishub Tamirisa, Jaehyuk Lim, Bruce W. Lee, Richard Ren, Long Phan, Norman Mu, Oliver Zhang, Dan Hendrycks

We discover that coherent value systems emerge with scale in LLMs and propose the research avenue of utility engineering to analyze and control these emergent value systems.