[State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor

A researcher who worked on o3 and now on Cursor Composer discusses how RL shapes reasoning and coding models, which informs how engineers should expect coding agents to improve.

• videoWhy Every Agent needs Open Source Cloud Sandboxes
• videoTerminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders
• video[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI
• video⚡️ Reverse Engineering OpenAI's Training Data — Pratyush Maini, Datology

• videoThe RLVR Revolution — with Nathan Lambert (AI2, Interconnects.ai)Latent Space
• video⚡️Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime IntellectLatent Space
• video[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAILatent Space

Checking sign-in…

Loading comments…