# Reliability of AI coding tools

**URL:** <https://discourse.julialang.org/t/reliability-of-ai-coding-tools/133975>\
**Category:** Offtopic\
**Tags:** llm\
**Created:** [November 17, 2025, 10:25am UTC](https://discourse.julialang.org/t/reliability-of-ai-coding-tools/133975 "2025-11-17T10:25:05Z")\
**Posts on this page:** 1\
**Showing post:** 26

<div class="post-metadata">

**Author:** ![goerz](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/goerz/32/3269_2.png) [@goerz](https://discourse.julialang.org/u/goerz)\
**Post date:** [November 19, 2025, 3:45am UTC](https://discourse.julialang.org/t/reliability-of-ai-coding-tools/133975/26 "2025-11-19T03:45:30Z")

</div>

“Inherently unreliable” depends on a lot of factors:

> [@cjdoris](#):
>
> it’s important to make a distinction between vibe coding […] and using AI “properly”

This was discussed extensively recently in [Should General have a guideline or rule preventing registration of vibe-coded packages?](https://discourse.julialang.org/t/should-general-have-a-guideline-or-rule-preventing-registration-of-vibe-coded-packages/133205/) (see also the [actual guidelines](https://github.com/JuliaRegistries/General?tab=readme-ov-file#is-there-any-policy-regarding-the-use-of-llms-in-registered-packages) that resulted from this).

Claude and similar tools definitely _can_ be used to positive effect, see [The use of Claude Code in SciML repos - #8 by ChrisRackauckas](https://discourse.julialang.org/t/the-use-of-claude-code-in-sciml-repos/131009/8)

---

_[View the full topic](https://discourse.julialang.org/t/reliability-of-ai-coding-tools/133975)._