Andy Jones
Anthropic researcher; previously DeepMind; known for scaling-laws and Hex/board-game RL work.
- Role
- researcher
- Currently at
- Anthropic
- twitter.com/andy_l_jones
- GitHub
- github.com/andyljones
- Scholar
- scholar.google.com/citations
- Papers
- 4
Cite
Notes
Only stored in your browser.
4papers
Authored papers
4Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
preprint
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
arXiv 2022
Discovering Language Model Behaviors with Model-Written Evaluations
arXiv 2022
Constitutional AI: Harmlessness from AI Feedback
arXiv 2022
Affiliations
Previously
Frequent co-authors
10from 4 papers
Amanda Askell
researcher
Anna Chen
researcher
Ben Mann
founder
Catherine Olsson
researcher
Danny Hernandez
researcher
Dario Amodei
CEO
Dawn Drain
researcher
Deep Ganguli
researcher
Jackson Kernion
researcher
Jared Kaplan
co-founder / Chief Science Officer