Why The Harness Matters More Than The Model | YC Paper Club

Francois Chaubard, Seth Karten, Jon Saad-Falcon, Josh France, Regan Bell

Talks worth your time · Y Combinator · 2026-10-05 · 60 min · 11 pages

Harnesses get dismissed as just scaffolding, just prompt engineering, and not real research. But that couldn't be farther from the truth. The same model weights that score 30% on ARC-AGI score 95% with a better harness. So we gathered a group of researchers and founders working at the frontier to do a deep dive into the state of harnesses. We'll cover how we got to this point, the case for making your harness as expressive as possible, and what YC learned building an agent for every employee in the company. Sign up for the next Paper Club: Alternative Compute Paradigms https://events.ycombinator.com/yc-paperclub-Sep23 Chapters: 00:00 - Why harnesses matter 04:27 - Building an auto-researcher by accident 07:13 - A five minute history of harnesses 13:56 - Self-improving harnesses 17:22 - Tonight's speakers 18:35 - Seth Karten: Prime Agent, a self-improving RLM harness 21:50 - Context as an L1, L2, L3 cache 24:51 - From Turing machine to von Neumann computer 28:33 - Messaging between agents 30:04 - ARC-AGI results 33:09 - Emulator Bench and GPU kernels 37:30 - Jon Saad-Falcon: OpenJarvis, personal AI on personal devices 38:26 - How far behind are local models 39:21 - The five primitives of a personal AI stack 42:47 - Letting cloud models optimize your local stack 43:53 - 800x cheaper than the cloud 45:58 - Josh France and Regan Bell: QM, YC's agent harness for work 47:29 - A history of YC's internal agents 49:24 - OpenClaw and a fleet of 50 agents 51:04 - Pulling the brain

Generated automatically from the recording's transcript. It's meant to replace re-watching, not the recording itself — verify against the video at the timestamp before quoting formally. Slides belong to the speakers and organisers. Produced with recording-to-pdf.