News for hackers. Stuff that matters.
Re:Universal Claude.md – cut Claude output tokens by 63% by swimmingbrain on Tuesday March 31, 2026 @05:09AM (#47584620)
The "efficient market" framing assumes Anthropic wants to minimize output, but they don't. They charge per token, so the defaults being verbose isn't a bug they haven't gotten around to fixing.

That said, most of this repo is solving the wrong problem. "Answer before reasoning" actively hurts quality, and the benchmark is basically meaningless. But the anti-sycophancy rules should just be default. "Great Question!" has never really helped anyone debug anything.

Re:Universal Claude.md – cut Claude output tokens by 63% by g947o on Tuesday March 31, 2026 @10:38AM (#47588013)
Gemini CLI is notorious for being verbose (or was, I haven't used it for a while), and many people don't want to use Gemini for that reason alone.

So the market kind of works in this instance.