Matthew Rahtz
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Gemma 2: Improving Open Language Models at a Practical SizeSaved credit: Contributor · 2024Explore people connected to this work →
- Evaluating Frontier Models for Dangerous CapabilitiesSaved credit: Contributor · 2024Explore people connected to this work →
- Tracr: Compiled Transformers as a Laboratory for InterpretabilitySaved credit: Contributor · 2023Explore people connected to this work →
- Safe Deep RL in 3D Environments using Human FeedbackSaved credit: First author · 2022Explore people connected to this work →
- Specification gaming: the flip side of AI ingenuitySaved credit: Contributor · 2020Explore people connected to this work →