Same model, very different performance: Dylan Patel on why the harness matters
MatthewBerman · x · 2026-10-08
Matthew Berman shares a ForwardFuture clip where SemiAnalysis's Dylan Patel explains why the exact same model can perform very differently across products: the harness around the AI model — prompting, tool wiring, and engineering scaffolding — materially changes its measured performance.
More from coding & agent
- ThePrimeagen admits agent-driven terminal workflow has taken over his coding — zeeg · 2026-10-08
- ezyang: types are good even for trivially testable things — no need to remember the tests — ezyang · 2026-10-08
- One engineer shipped web, desktop, iOS and Android apps in 6 months with AI — Yuchenj_UW · 2026-10-08
- Google Labs launches a 'GitHub for vibe coders' to store, share and remix AI-built apps — templecrash · 2026-10-08
- Keep coding agents sane: don't cram everything into one thread — msfeldstein · 2026-10-08
- Codex Cloud shipped with day-0 Tailscale support — and Tailscale didn't even know — pvncher · 2026-10-08