Codex
Loading…
Loading…
Improved coding-agent reliability via context, tools, delegation, and failure analysis; explored training lower-cost subagents with multi-agent RL.
Worked on early-stage model development behind initial product launches, including Writing Tools and Reply Suggestions.
working on Codex at OpenAI; previously worked at Augment Code, Apple and Salesforce AI Research; studied Statistics in Wuhan and Computer Science in Washington State.