TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: Do AI code tools work well with your company's codebase?

8 pointsby prasoonds8 months ago
Hey HN, I&#x27;be been using Cursor a fair bit recently and I really enjoy it but it doesn&#x27;t work too well when I ask it questions that use the whole codebase.<p>Normally, I&#x27;m working in a small part of the codebase and I can give really concrete instructions and the right context to Cursor. Here, it works really well.<p>But, when I ask it questions are are more generic (where&#x27;s the code that does X&#x2F;how can I do X?&#x2F;Implement &lt;functionality&gt; by using X and Y), it often hallucinates or gives me wrong answers.<p>I can see that it tries to find the right context to send to the LLM. Sometimes, it does find the right context, other times it doesn&#x27;t. Even when it <i>does</i> find the right context, I&#x27;m guessing it&#x27;s just too much context that gets sent to the LLM so it just ends up hallucinating.<p>Have you had this same problem with whichever AI coding tool you use? I&#x27;m wondering if the problem is specific to the legacy + large codebase I&#x27;m working with or is it a more general thing with unseen code that the LLM hasn&#x27;t seen in it&#x27;s training data.

3 comments

dgosling567 months ago
It&#x27;s not that great at answering questions specific to my company&#x27;s code base - like where do I find another API method that does Y. However, we have a lot of guides internally which are usually scattered around in github readmes and usually those are what I fallback to when trying to find an answer. These github readmes and be quite long though and it can feel like a lot of manual work to scan through them, that&#x27;s where I&#x27;ll usually use this extension Rocky AI to quickly ask a question given the context of a webpage (helps avoid reading through the entire thing manually). After quickly browsing 2-3 and I&#x27;ll have what I need.<p><a href="https:&#x2F;&#x2F;chromewebstore.google.com&#x2F;detail&#x2F;rocky-ai&#x2F;fdjoklehjinbgibfgbncoljognjjpkna" rel="nofollow">https:&#x2F;&#x2F;chromewebstore.google.com&#x2F;detail&#x2F;rocky-ai&#x2F;fdjoklehji...</a>
skeptrune8 months ago
They don&#x27;t work well at all for us.<p>We have a relatively large Rust codebase and I would describe the LLM&#x27;s as actively harmful at making agentic-style, self-piloted changes.<p>Very pointed context management with split screens and explicit inclusion of relevant files in the context is sometimes useful though.<p>My biggest gripe is that AI can&#x27;t just generate a new SQL migration and CRUD routes for an additional resource we want to add without issue. I always have to punt and end up doing it myself.
评论 #41722062 未加载
prasoonds8 months ago
Also to add some more context:<p>- I&#x27;ve found LLM codegen working very well with standard React + TS code<p>- It sucks when using less knows languages or less popular frameworks (I tried reverse engineering github copilot lua code from the neovim extension in one instance and it really didn&#x27;t work well)<p>I&#x27;d be curious to hear people&#x27;s experience here.