Nat McAleese
Source-listed: Researcher · Anthropic
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Red Teaming Language Models with Language ModelsSaved credit: Contributor · 2022Explore people connected to this work →
- Improving alignment of dialogue agents via targeted human judgementsSaved credit: Contributor · 2022Explore people connected to this work →
- Teaching language models to support answers with verified quotesSaved credit: Contributor · 2022Explore people connected to this work →
- LLM Critics Help Catch LLM BugsSaved credit: Contributor · 2024Explore people connected to this work →
- Prover-Verifier Games improve legibility of LLM outputsSaved credit: Contributor · 2024Explore people connected to this work →