Harrison Edwards
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Debate Training Reduces Reward Hacking in RLAIFSaved credit: Contributor · 2026Explore people connected to this work →
- Let's Verify Step by StepSaved credit: Contributor · 2023Explore people connected to this work →
- Grokking: Generalization Beyond Overfitting on Small Algorithmic DatasetsSaved credit: Contributor · 2022Explore people connected to this work →
- Evaluating Large Language Models Trained on CodeSaved credit: Contributor · 2021Explore people connected to this work →
- Exploration by Random Network DistillationSaved credit: Contributor · 2018Explore people connected to this work →