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: Best cheap decent LLM for handling code, social media profiles?

3 pointsby throwawayadvsecalmost 2 years ago
Hi, I&#x27;m looking for a LLM that can be used to have decent answers to stuff like: &quot;what libraries do this code import?&quot; &quot;does this code follow this design pattern?&quot; &quot;do the variables used in this code have a meaningful name?&quot;<p>GPT 3.5 turbo can do it pretty well, but it&#x27;s out of my budget, as I would need to make a LOT of requests.<p>I have about 8,000$ in AWS credits for self hosting<p>Is there any LLM you&#x27;d recommend for this?<p>I was thinking of reverse engineering copilot and using its internal API directly, do you know if there is a big rate limit?<p>thanks

2 comments

i_have_an_ideaalmost 2 years ago
I like this one: <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;junelee&#x2F;wizard-vicuna-13b" rel="nofollow noreferrer">https:&#x2F;&#x2F;huggingface.co&#x2F;junelee&#x2F;wizard-vicuna-13b</a><p>I am not affiliated with the project. I like that LLM because it runs on my Mac and it performs fairly close to GPT 3.5
extasiaalmost 2 years ago
What&#x27;s your expected usage, volume wise?
评论 #37019559 未加载