Maja Trębacz
Source-listed: Member of Technical Staff · OpenAI
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Auto-review of agent actions without synchronous human oversightSaved credit: Contributor · 2026Explore people connected to this work →
- LLM Critics Help Catch LLM BugsSaved credit: Contributor · 2024Explore people connected to this work →
- Gemini: A Family of Highly Capable Multimodal ModelsSaved credit: Contributor · 2023Explore 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 →