Addison J. Wu

Currently, I'm...

• making sure AI development goes smoothly @ Center for AI Safety
• tinkering around @ Princeton Language and Intelligence, advised by Tom Griffiths and Zhuang Liu
  • teaching models to be fair, honest, and healthily cautious
  • digging into whatever else catches my interest — strategy, data, RL, the physical world

I've published co-first-authored papers at ICML (including a 2026 Oral), COLM, and NeurIPS.
My work has also been featured in several press and TV outlets. Check out the rest at Google Scholar