Jan Leike
Head of Alignment Science at Anthropic; previously co-lead of OpenAI's Superalignment team; long-time pioneer of RLHF and scalable oversight.
- Role
- researcher
- Currently at
- Anthropic
- twitter.com/janleike
- GitHub
- github.com/janleike
- Scholar
- scholar.google.com/citations
- Papers
- 6
Cite
Notes
Only stored in your browser.
6papers
Authored papers
6Scaling and evaluating sparse autoencoders
arXiv 2024
Let's Verify Step by Step
ICLR
Let's Verify Step by Step
ICLR
GPT-4 Technical Report
gpt-4-technical-report
Training language models to follow instructions with human feedback
NeurIPS
Evaluating Large Language Models Trained on Code
preprint
Affiliations
Frequent co-authors
10from 6 papers
Ilya Sutskever
co-founder / CEO (SSI)
John Schulman
co-founder
Alec Radford
researcher
Harri Edwards
researcher
Pamela Mishkin
researcher
Peter Welinder
founder
Teddy Lee
founder
Alethea Power
researcher
Alex Paino
engineer
Alex Ray
researcher