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: If you use an LLM, which one do you use?

7 pointsby zopperalmost 2 years ago
It seems to me that most startups use one of the LLMs from OpenAI (ChatGPT &#x2F; GPT-4), other closed-source LLMs like Bard or Claude are not that popular and open-source LLMs are only really used by researchers or hobbyists who run them locally.<p>Curious to hear from others who are building something on top of an LLM, which one do you use? Has anyone fine-tuned and deployed their own LLM or do you just rely on ChatGPT?

4 comments

tlackalmost 2 years ago
I am experimenting with building software using the ReAct tool prompting pattern, using Llama derivative models like Manticore13B, Airoborous, etc. I script it all together using Microsoft Guidance with Llama.cpp and AutoGPTQ. Works pretty well for simple tasks and I know the costs are roughly fixed. Obviously their capabilities are far less than OpenAI&#x27;s products but when you have tens of thousands of conversations to have the costs of ChatGPT become a distraction. Haven&#x27;t tried finetuning yet.
mackopesalmost 2 years ago
I recently started using the ChatGPT via OpenAI api. It seems to perform reasonably well on all tasks I needed it for so far. But bear in mind I use it for hobby projects so far.<p>I have not tried the open source LLMs so far as there&#x27;s the additional hassle renting a server and deploying it there. Running it locally on a consumer GPU does not cut it yet as it is too slow. So to iterate faster, I prefer just using ChatGPT.
greenidoalmost 2 years ago
We are using both openAI and Google&#x27;s Bard. There are some aspects to each of them - but it&#x27;s still mostly &#x27;WIP&#x27;. The main challenge is how to &#x27;tune&#x27; these LLMs with our own data as another layer that can improve the overall performance (=quality of answers).
评论 #36121732 未加载
dserbanalmost 2 years ago
For a side project I&#x27;m using a fine-tuned vicuna-13b. I&#x27;m using to generate search queries from natural language, and it outperforms all other open-source models at deep intent recognition.
评论 #36121789 未加载