Jacob Pfau


contact: [first].pfau@gmail.com

PhD student at the NYU Alignment Research Group. Current research projects include:

  • applying causal behavioral analysis to problems of introspective truthfulness in LMs
  • studying scaling properties of LM performance as a function of empty space in prompts
  • formalizing limitations of RL fine-tuning of LMs

I like to post about research on Twitter and Lesswrong. I also like to create prediction markets e.g. “Will an AI produce encyclopedia-worthy philosophy by 2026” on Manifold, and “Will transformer derived architectures accelerate progress in deep learning?” on Metaculus.


latest posts

selected publications