PhD student at the NYU Alignment Research Group. Current research projects include: I like to post about research on Twitter and Lesswrong. I also like to create prediction markets e.g.

Open problems and fundamental limitations of reinforcement learning from human feedback. CoRR, abs/2307.15217, 2023. doi: 10.48550. S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R...

JACOB PFAU [email protected] scholar.google.com/citations?user=rl1IMgMAAAAJ jacobpfau EDUCATION New York University, Bowman Lab Fall 2022 - Present PhD Student NYU Alignment Research Group, Center for Data Science Current work includes: Red-teaming and latent adversarial training for LMs, Filler tokens and chain-of-thought in LMs

Bio: Jacob Pfau is a PhD student at the NYU Center for Data Science, working in the NYU Alignment Research Group supervised by Sam Bowman and He He. Jacob’s research is motivated towards ensuring language models continue to be safely usable as they scale.

Feb 25, 2025 · PhD Candidate working on NLP and AI Safety. Research Data Analyst; QBI Bold & Basic Fellow (2019-2020). Jacob’s interests span the theory and applications of machine learning models – and deep learning in particular.

Apr 24, 2024 · View a PDF of the paper titled Let's Think Dot by Dot: Hidden Computation in Transformer Language Models, by Jacob Pfau and 2 other authors

NYU PhD student working on AI safety. AI is 90% of their (quality adjusted) useful work force. This is intended to compare to 2023/AI-unassisted humans, correct? Or is there some other way of making this comparison you have in mind?

publications. Please see google scholar. © Copyright 2024 Jacob Pfau. Powered by Jekyll with al-folio theme. Hosted by GitHub Pages.GitHub Pages.

View Jacob Pfau’s profile on LinkedIn, a professional community of 1 billion members.