logoalt Hacker News

cpeth • today at 8:36 PM • 1 reply • view on HN

Harnesses are all fairly simple loops from the ones I have looked at; there is not much to them.

As someone who regularly uses Claude Opus 5.5 from Claude Code and from Copilot, I would say harness barely matters in terms overall performance and behavior. Opus is nearly identical in both harness. The opposite is also true, if I switch Copilot to something like Gemini 4 Argon it's completely different even though I'm in the same harness.

Just some andecdata.


Replies

drivebyhooting • today at 9:54 PM

Doesn’t the harness include a bunch of prompts for when to create subagents, their communication patterns, and how to verify their outputs?

That can make a huge difference, as evidenced by the agent swarms success at cracking maths.