Lopopolo: Standardizing codebase structure and skills maximizes AI agent effectiveness
Ryan Lopopolo · Extreme Harness Engineering: 1M LOC, 1B toks/day, 0% human code or review — Ryan Lopopolo, OpenAI · Apr 7, 2026 · at 42:35
Ryan Lopopolo, engineer on OpenAI's Frontier team, explains harness engineering principles and how code standardization optimizes agent performance.
0:00 / 0:37exact quote · 37.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“I do think that there is leverage to be had in making the code and the processes as much the same as possible. If you think that code is context, code is prompts, it's better from the agent behavior perspective to be able to look in a package in directory XYZ And it not to have to page so deeply into directory ABC because they have the same structure, use the same language, they have the same patterns internally. And that same like leverage comes from aligning on a single set of skills that you're pouring every engineer's taste into to make sure that the agent is effective.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Ryan Lopopolo
Lopopolo: Coding models and harnesses are now isomorphic to human engineering capability
“The models are there enough. The harnesses are there enough where they're isomorphic to me and capability and the ability to do the job.”
Lopopolo: Coding models have largely solved all tasks except hard and new
“And I think things that are hard and new is still something that the models need humans. Yeah. Drive. Yeah. But I think those other quadrants are largely solved, given the right scaffold and the right thing that's going to drive the agent to completion.”
Lopopolo: Bearish on MCP due to forced token injection and compaction issues
“MCPs I'm pretty bearish on because the harness forcibly injects all those tokens in the context and I don't really get a say over it. They mess with auto compaction. The agent can forget how to use the tool. There's probably only like, what, three calls in Pla…”
Lopopolo: Zero-code harness was 10x slower initially before outperforming any single engineer
“Honestly, the first month and a half was 10 times slower than I would be. But because we paid that cost, we ended up getting to something much more productive than any one engineer could be, because we built the tools, the assembly station for the agent to do …”
Lopopolo: OpenAI Frontier team operates with post-merge or zero human code review
“You know, we, we've moved beyond even the humans reviewing the code as well. Most of the human review is post merge at this point, but it's not even reviewed.”
Lopopolo: Reasoning models eliminate need for rigid state-machine scaffolding
“And this I think is like the fundamental difference between reasoning models and the four ones and four O's of the past where these models could not think. So you kind of had to put them in boxes with a predefined set of state transitions. Whereas here we have…”