[State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor
Latent Space: The AI Engineer Podcast
- Published
- December 30, 2025
- Duration
- 45:12
- Summary source
- description
- Last updated
- May 24, 2026
Discusses openai.
Summary
From Berkeley robotics and OpenAI's 2017 Dota-era internship to shipping RL breakthroughs on GPT-4o, o1, and o3, and now leading model development at Cursor, Ashvin Nair has done it all. We caught up with Ashvin at NeurIPS 2025 to dig into the inside story of OpenAI's reasoning team (spoiler: it went from a dozen people to 300+), why IOI Gold felt reachab…
Intelligent report
Sign in to read teasers, or upgrade to Research Pro to commission a new dossier for this episode. Learn more →
Show notes
From Berkeley robotics and OpenAI's 2017 Dota-era internship to shipping RL breakthroughs on GPT-4o, o1, and o3, and now leading model development at Cursor, Ashvin Nair has done it all. We caught up with Ashvin at NeurIPS 2025 to dig into the inside story of OpenAI's reasoning team (spoiler: it went from a dozen people to 300+), why IOI Gold felt reachable in 2022 but somehow didn't change the world when o1 actually achieved it, how RL doesn't generalize beyond the training distribution (and wh
Themes
- openai