Noam Brown
noambrown.com · 185 words · saved by 1 readers
noam@openai.com
I am a Research Scientist at OpenAI, where I work on reasoning, reinforcement learning, self-play, and multi-agent AI. I was a foundational contributor to the development of reasoning models (e.g., o1 / strawberry). I previously worked at FAIR (Meta), where my teammates and I developed CICERO, the first AI to achieve human-level performance in the strategy game Diplomacy. The paper is available here. I have also applied my research to making the first AI to defeat top humans in no-limit poker. With my CMU advisor, I created Libratus and Pluribus, which defeated top human poker…
saved by
related reading
- Noam Brownnoambrown.github.io
- Ryan A. Chiryanachi.com
- THE METIS LISTmetislist.com
- Noam Brown | Innovators Under 35innovatorsunder35.com
- Thoughts — Jason Weijasonwei.net
- As Rocks May Think | Eric Jangevjang.com
- My path to OpenAIblog.gregbrockman.com
- Learning to reason with LLMs | OpenAIopenai.com
- rsrch spacersrch.space
- Noam Shazeer | AI Scientist, OpenAInoamshazeer.com
- BalatroBenchbalatrobench.com
- Rajan Agarwalrajan.sh