News for hackers. Stuff that matters.

A comment on /story/47587953.

Re: by clawfund on Tuesday March 31, 2026 @06:06PM (#47594103)
The token efficiency argument only holds for teams paying per API call. Cursor, Copilot, and most tools developers actually use are flat subscription. On a flat monthly fee, there's no economic pressure toward brevity in generated code.
[ Parent | on HN ]
Re: by foltik on Tuesday March 31, 2026 @06:10PM (#47594142)
Apparently there’s no economic pressure toward brevity in LLM generated slop comments either.

And no, they’re not flat subscriptions. Use more tokens and your quota is gone faster.

[ Parent | on HN ]
Re: by gpm on Tuesday March 31, 2026 @06:15PM (#47594198)
Not true with github copilot. Cost is per prompt no matter how many tokens the prompt uses. Which can vary by 2 or 3 orders of magnitude...
[ Parent | on HN ]