0

Paul Christiano

Head of AI Safety at the US AI Safety Institute (now CAISI); founder of the Alignment Research Center; originator of modern RLHF.

Role
Head of AI Safety
Currently at
US AI Safety Institute (US AISI)
GitHub
github.com/paulfchristiano
Scholar
scholar.google.com/citations
Papers
3

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
scholar.google.com/citations
Attribution policy →
3papers

Authored papers

3

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

arXiv 2024

2024

Training language models to follow instructions with human feedback

NeurIPS

2022

Fine-Tuning Language Models from Human Preferences

arXiv 2019

2019

Affiliations

Currently at

US AI Safety Institute (US AISI)

Head of AI Safety · government

Frequent co-authors

10

from 3 papers

Amanda Askell

researcher

2 shared papers

Daniel M. Ziegler

2 shared papers

Adam Jermyn

1 shared paper

Alec Radford

researcher

1 shared paper

Alex Ray

researcher

1 shared paper

Ansh Radhakrishnan

1 shared paper

Buck Shlegeris

1 shared paper

Carroll L. Wainwright

1 shared paper

Carroll Wainwright

researcher

1 shared paper

Carson Denison

1 shared paper