Cursor is probably a better client than Claude Code though

Hard disagree - the third party tooling client better than the native harness?

Claude’s native harness is pretty bad though relatively. Pretty sure at one point it was scoring last on harness related benchmarks using Opus at the time

	▲	lighthazard a day ago \| parent [-]
		TIL harness benching.. https://www.harness-bench.ai/leaderboard.html - is this legit? Never even heard of nanobot.

▲

lubujackson a day ago | parent | prev | next [-]

Yes. Cursor is significantly better at understanding context without needing a 5 page spec or burning a truckload of tokens. And it's debug mode is top tier if you haven't tried it - people sleep on Cursor.

	▲	try-working a day ago \| parent [-]
		I've been using Cursor on auto for the past five days while waiting for my Codex refresh. Yes, it works extremely well. Extremely.

▲

Uzazo a day ago | parent | prev [-]

The team training the model is not the team working on the harness.