HY4-Preview

Headlines · 1

1. Oct 24
   Coding-Agent Harness Changes Raise Costs Without Reliable Gains

   Shandong University researchers Liu and Han compared Claude Code, OpenCode, and mini-SWE-agent while holding the language model constant. Most performance differences were similar to rerun noise, while the harnesses consumed two to three times as many tokens as the leanest option; OpenCode showed a significant deficit on the larger task pool. A small cross-check on Terminal-Bench 2.1 showed the same pattern.

   The Decoder · 🔥 0

Experience and discussion from the community

Share my HY4-Preview experienceAsk about HY4-Preview