News for hackers. Stuff that matters.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by jedisct1 on Tuesday November 17, 2026 @12:18PM (#50534751)
It would have been nice to see swival.dev in that list.

But unsurprisingly, Codex works pretty well, too (and not just with OpenAI models), and Claude Code is just a waste of tokens and money.

There are no comments on this comment yet.