[HN Gopher] LLMs learn what programmers create, not how programm...
___________________________________________________________________
LLMs learn what programmers create, not how programmers work
I ran an experiment to see if CLI actually was the most intuitive
format for tool calling. (As claimed by a ex-Manus AI Backend
Engineer) I gave my model random scenarios and a single tool "run"
- i told it that it worked like a CLI. I told it to guess commands.
it guessed great commands, but it formatted it always with a colon
up front, like :help :browser :search :curl It was trained on how
terminals look, not what you actually type (you don't type the ":")
I have since updated my code in my agent tool to stop fighting
against this intuition. LLMs they learn what commands look like in
documentation/artifacts, not what the human actually typed on the
keyboard. Seems so obvious. This is why you have to test your LLM
and see how it naturally works, so you don't have to fight it with
your system prompt. This is Kimi K2.5 Btw.
Author : noemit
Score : 7 points
Date : 2026-03-23 20:31 UTC (2 hours ago)
___________________________________________________________________
(page generated 2026-03-23 23:01 UTC)