Extreme Harness Engineering: 1M LOC, 1B toks/day, 0% human code or review — Ryan Lopopolo, OpenAI

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 REVIEWED code before merge. Ryan is admirably evangelical about this, calling it borderline “negligent” if you aren’t using 1B tokens a day (roughly $2-3k/day in token spend based on market rates and caching assumptions). Over the past five months, they ran an extreme experiment: building and shipping an internal beta product with zero manually written code. Through the experiment, they adopted a different model of engineering work: when the agent failed, instead of prompting it better or to “try harder,” the team would look at “what capability, context, or structure is missing?” The result was Symphony, “a ghost library” and reference Elixir implementation that sets up a massive system of Codex agents all extensively prompted with the specificity of a proper PRD spec, but without full implementation. See below: https://openai.com/index/harness-engi... https://github.com/openai/symphony/tr... Timestamps 00:00:00 Introduction: Harness Engineering and OpenAI Frontier 00:02:20 Ryan’s background and the “no human-written code” experiment 00:08:48 Humans as the bottleneck: systems thinking, observability, and agent workflows 00:12:24 Skills, scaffolds, and encoding engineering taste into context 00:17:17 What humans still do, what agents already own, and why software must be agent-legible 00:24:27 Delegating the PR lifecycle: worktrees, merge conflicts, and non-functional requirements 00:31:57 Spec-driven software, “ghost libraries,” and the path to Symphony 00:35:20 Symphony: orchestrating large numbers of coding agents 00:43:42 Skill distillation, self-improving workflows, and team-wide learning 00:50:04 CLI design, policy layers, and building token-efficient tools for agents 00:59:43 What current models still struggle with: zero-to-one products and gnarly refactors 01:02:05 Frontier’s vision for enterprise AI deployment 01:08:15 Culture, humor, and teaching agents how the company works 01:12:29 Harness vs. training, Codex model progress, and “you can just do things” 01:15:09 Bellevue, hiring, and OpenAI’s expansion beyond San Francisco