Nicholas Joseph
Founding team member and technical staff at Anthropic; previously at OpenAI on GPT-3.
- Role
- researcher
- Currently at
- Anthropic
- Scholar
- scholar.google.com/citations
- Papers
- 6
Cite
Notes
Only stored in your browser.
Authored papers
6Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
arXiv 2023
Training 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
Evaluating Large Language Models Trained on Code
preprint
Affiliations
Previously
Frequent co-authors
10from 6 papers
Jared Kaplan
co-founder / Chief Science Officer
Sam McCandlish
founder
Anna Chen
researcher
Danny Hernandez
researcher
Dario Amodei
CEO
Jackson Kernion
researcher
Sheer El Showk
researcher
Zac Hatfield-Dodds
researcher
Amanda Askell
researcher
Andy Jones
researcher