Extreme Harness Engineering for the 1B token/day Dark Factory — Ryan Lopopolo, OpenAI Frontier

Latent Space · Beginner ·🧠 Large Language Models ·5h ago
We’re proud to release this ahead of Ryan’s keynote at AIE Europe. Hit the bell, get notified when it is live! Attendees: come prepped for Ryan’s AMA with Vibhu after. Move over, context engineering. Now it’s time for Harness engineering. Ryan Lopopolo of OpenAI is leading that charge, recently publishing a lengthy essay on that has become the talk of the town. In it, Ryan peeled back the curtains on how the recently announced OpenAI Frontier team have become OpenAI’s top Codex users, running a 1m LOC codebase with 0 human written code and, crucially for the Dark Factory fans, no human REVI…
Watch on YouTube ↗ (saves to browser)

Chapters (6)

Introduction: Harness Engineering and OpenAI Frontier
2:20 Ryan’s background and the “no human-written code” experiment
8:48 Humans as the bottleneck: systems thinking, observability, and agent workflows
12:24 Skills, scaffolds, and encoding engineering taste into context
17:17 What humans still do, what agents already own, and why software must be agent-le
24:27 Delegating the PR lifecycle: worktrees, merge conflicts, and non-functional
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Next Up
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)