capy beats a major coding harness at half the cost and half the time, eval finds
garrytan · x · 2026-09-22
A developer ran an eval comparing capy against a major coding harness: capy performed better at half the cost and half the time. This follows Garry Tan's praise that capy handles multi-step workflows and large PRs faster than Codex or Claude Code.
Related event: YC CEO Garry Tan says Capy makes PRs 4x faster than raw Codex(3 posts)→
More from coding & agent
- User automates entire video clipping workflow with Nous Research's Hermes agent — Teknium · 2026-11-12
- As models improve, writing good evals gets harder and more important — amankhan · 2026-11-12
- Prime agent ships with day-one multi-agent communication, runs in Minecraft unmodified — sarahcat21 · 2026-11-12
- Autonomous agent edits just 1,024 weights to lift Qwen3.5 0.8B from 7.4% to 37.4% on MATH-500 — VictorSanh · 2026-11-12
- Free AI game jam in SF Nov 14–15 with teams from Anthropic, Google, Meshy, OpenAI — chrisfirst · 2026-11-12
- Omarchy 4.6 lets you share local AI models across your tailnet, says DHH — alexcovo_eth · 2026-11-12