News for hackers. Stuff that matters.
Re:How I use LLMs to learn complex topics by northern-lights on Monday August 10, 2026 @03:54AM (#49240647)
I had the same problem - Opus models past 4.7 tend to inflate output tokens for no good reasons, introduce innumerable jargons and is a pain to read. Then, I cam across this: https://github.com/ayghri/i-have-adhd/blob/main/skills/i-hav...

You can either install that skill or put the Rules section directly in your Global CLAUDE.md for Claude or Personalization setting for Codex and it should cut down the output verbosity by quite a fair bit.

There are no comments on this comment yet.