Show HN: 9 agent harnesses, same model — cost per pass varies 17x
shiqimei · hn · 2026-09-03
FrontierHarness is a new eval site comparing 9 agent harnesses running the same model. Key finding: cost per pass varies up to 17x across harnesses, showing harness design dramatically changes real-world agent cost. Results are public at frontierharness.org.
More from coding & agent
- LLM one-shots a Minecraft 3x3 piston door by building its own Linux test infra — Vjeux · 2026-10-18
- Dev builds Mumbai-inspired 3D manga background generator from OpenStreetMap data — CurieuxExplorer · 2026-10-18
- Solo founder builds a money-printing data service on Claude's Pi Durable harness — MicahBerkley · 2026-10-18
- Dev builds Arch-based OS with custom desktop and browser using Claude Code — Snoo-10493 · 2026-10-18
- Five SaaS agent workflows fail the same way — and it's never model intelligence — usehive · 2026-10-18
- Claude skill generates hand-drawn interactive diagrams that teach kids how things work — CatAstro_Piyush · 2026-10-18