Cursor

Harry Partridge, an engineer building large-scale agent tooling at Parsed, and Charlie O'Neill, a researcher specializing in open-source model specialization, discuss running dozens to hundreds of coding agents. They cover agent coordination, agent-to-agent messaging, automated QA and adversarial code reviews, mixing models for implementation versus critique, and reusable skills and workflows for scaling agent systems.

Simon Eskildsen, CEO of turbopuffer and former long-time Shopify production engineer, shares war stories from scaling Shopify and building resilient infra. He talks about surviving flash sales, MySQL and caching tricks, and the origins of his Napkin Math thinking. Simon also explores why new database companies appear, turbopuffer’s path to extreme scale, and how AI tools change engineering and hiring.

Join John Schulman, co-founder and leading researcher in reinforcement learning, as he delves into the early days of OpenAI and the potential for rapid advancements in AI like ChatGPT. He discusses the evolution of research management styles and the importance of effective team structures in fostering innovation. Schulman also tackles pressing issues like the future of reinforcement learning, the impact of continual learning, and how AI tools enhance daily researcher workflows. Plus, his insights on AGI timelines are sure to spark debate!

Michael Truell chats with Patrick Collison, CEO of Stripe and tech visionary, about his journey in programming. They explore the early days of Smalltalk in startups and the evolution of AI in coding. Patrick shares insights on using LISP for chatbots and highlights the importance of rich development environments. He discusses Stripe's critical tech decisions, including the impact of MongoDB. The conversation also touches on programming human biology and the unexpected beneficiaries of AI, providing a forward-looking perspective on technology's future.

In a lively roundtable, technical experts from Cursor delve into the intricacies of training superhuman AI coding agents. They discuss the unique challenges of coding's large action space and the complexity of ground-truth signals. Highlights include debates on the effectiveness of reinforcement learning rewards, the importance of real-world developer feedback, and advancements in hardware to support longer contexts. The conversation reveals fascinating insights into potential future developments in AI-assisted coding and how these innovations could transform the field.