OpenAI Podcast Episode 6 - The future of coding with AI
19 snips
Sep 15, 2025 
Greg Brockman, co-founder and president of OpenAI, and Thibault Sottiaux, Codex engineering lead at OpenAI, discuss the evolution of coding with AI. They dive into the journey from GPT-3 to the powerful GPT-5 Codex, exploring its capabilities in complex refactoring and coding assistance. The duo reveals insights on building AI harnesses, breakthroughs in code review, and the transformative potential of agentic coding. They also touch on the future landscape of AI in software development and the implications for learning to code in an automated world.
AI Snips
Chapters
Transcript
Episode notes
Optimize For Latency Then Interface
- Prioritize latency for autocomplete experiences: aim for ~1500 ms or users will abandon it.
- When you need deeper intelligence, redesign the harness rather than discarding slower models.
Internal 10x Terminal Prototype
- Thibault describes internal prototypes: a terminal-based agent called "10x" that ran remotely and boosted productivity.
- They kept iterating form factors and chose async remote agents before reintroducing local/IDE experiences.
Agentic Engineer As A Company Goal
- OpenAI set an explicit company goal: an agentic software engineer by year-end, focusing investment and compute.
- They view coding agents as a high-leverage path to advance capabilities and practical usefulness.