Zac Hatfield-Dodds
Anthropic researcher / AI security; previously Australian National University; maintainer of Hypothesis.
- Role
- researcher
- Currently at
- Anthropic
- twitter.com/zachatfielddodds
- GitHub
- github.com/Zac-HD
- Scholar
- scholar.google.com/scholar
- 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
Toy Models of Superposition
arXiv 2022
Constitutional AI: Harmlessness from AI Feedback
arXiv 2022
Affiliations
Frequent co-authors
10from 6 papers
Jared Kaplan
co-founder / Chief Science Officer
Sam McCandlish
founder
Anna Chen
researcher
Catherine Olsson
researcher
Danny Hernandez
researcher
Dario Amodei
CEO
Dawn Drain
researcher
Jackson Kernion
researcher
Nelson Elhage
researcher
Nicholas Joseph
researcher