Aftermarket Harnesses
View original on tomtunguz.comOverview
The harness now moves the coding benchmark more than the model does. Endor Labs' Agent Security League found GPT-5.5 scored 61.5% functional correctness in Codex & 87.2% in Cursor, & Claude Opus 4.7 scored 87.2% in Claude Code & 91.1% in Cursor. Input tokens are 86-98% of OpenRouter volume, so the harness controls most of the bill through cache discipline. First-party co-design buys real cache hit rates, but a third-party harness can match them.
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from Tomasz Tunguz
View all →Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO