Joshua Landau
Source-listed: Researcher · Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
4- Constitutional AI: Harmlessness from AI FeedbackSaved credit: Contributor · 2022Explore people connected to this work →
- Measuring Progress on Scalable Oversight for Large Language ModelsSaved credit: Contributor · 2022Explore people connected to this work →
- Discovering Language Model Behaviors with Model-Written EvaluationsSaved credit: Contributor · 2022Explore people connected to this work →
- The Capacity for Moral Self-Correction in Large Language ModelsSaved credit: Contributor · 2023Explore people connected to this work →