Paul Christiano
Source-listed: Executive director; President (officer) · Alignment Research Center (ARC)
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Deep reinforcement learning from human preferencesSaved credit: Contributor · 2017Explore people connected to this work →
- Concrete Problems in AI SafetySaved credit: Contributor · 2016Explore people connected to this work →
- AI safety via debateSaved credit: Contributor · 2018Explore people connected to this work →
- Fine-Tuning Language Models from Human PreferencesSaved credit: Contributor · 2019Explore people connected to this work →
- Learning to summarize from human feedbackSaved credit: Contributor · 2020Explore people connected to this work →