News for hackers. Stuff that matters.

A comment on Vibe Code Warning – from 1k to 10k lines, a personal casestudy. Parent comment

Re:Vibe Code Warning – from 1k to 10k lines, a personal case... by verdverm on Monday November 10, 2025 @03:57PM (#45880827)
If we're talking about emulating users, sure, but this is supposed to be a tool that helps me get my job done.

If (i.e.) you dig into how something like copilot works, they do dumb things like ask^ the LLM to do glob matching after a file read (to pull in more instructions)... just use a damn glob library instead of a non-deterministic and known to be unreliable method

^ it's just a table in the overall context, so "asking" is a bit anthropomorphizing

[ Parent | on HN ]
Re:Vibe Code Warning – from 1k to 10k lines, a personal case... by cluckindan on Monday November 10, 2025 @04:07PM (#45880945)
I would consider a bunch of ”dumb/power user” agents more useful than coding agents. The more they fail to use my software, the better!
[ Parent | on HN ]
Re:Vibe Code Warning – from 1k to 10k lines, a personal case... by zahlman on Monday November 10, 2025 @05:00PM (#45881514)
> ^ it's just a table in the overall context, so "asking" is a bit anthropomorphizing

I interpreted GP as just saying that you are already anthropomorphizing too much by supposing that the models "find" new ways to fail (as if trying to defy you).

[ Parent | on HN ]
Re:Vibe Code Warning – from 1k to 10k lines, a personal case... by verdverm on Monday November 10, 2025 @05:03PM (#45881548)
most humans do not seek out ways to defy after a certain age

I did not mean to imply active choice by "find", more that they are reliably non-deterministic and have a hard time sticking to, or easy time ignoring, the instructions I did write

[ Parent | on HN ]