Charles Foster
Source-listed: Policy Staff · METR (Model Evaluation and Threat Research)
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- The Pile: An 800GB Dataset of Diverse Text for Language ModelingSaved credit: Contributor · 2020Explore people connected to this work →
- The Language Model Evaluation HarnessSaved credit: Contributor · 2024Explore people connected to this work →
- Lessons from the Trenches on Reproducible Evaluation of Language ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- GPT-NeoX-20B: An Open-Source Autoregressive Language ModelSaved credit: Contributor · 2022Explore people connected to this work →
- Frontier Risk Report (February to March 2026)Saved credit: Contributor · 2026Explore people connected to this work →