So.. running a LLM is next on my list. What I am currently running though is a self hosted AI Image Generator.

But the issue @gadrian is talking about is something I went through A LOT with various AI's when it came to setting up my Hive Witness Node.

I learned a few tricks that may help (if you don't already know).

1. check the model you are using. Usually the default model for ChatGPT or Gemini is not for coding but for conversational type chat. So switch the model.

1. Try out Google Gemini and that 2.5 Pro. I had better luck with coding questions with Gemini than ChatGPT.

2. If using ChatGPT make sure 'Temporary' is turned OFF. And start a conversation and add bits of code. So what I did was like on day 1 explained what I was trying to build. Then I would copy and paste like 30 lines of code and tell it this is my fist section of code. Then copy past another 30 lines and tell it that it is my second section of code. rinse and repeat until all your code is in that chat.

Then if you come back to it the next day make sure to select that SAME chat and continue to conversation. It will have your chat history to pull from.

But keep in mind each AI uses 'Tokens' for Inference so if you code is MASSIVE you will use a ton of tokens (it comes out to like 1 token is something like 2/3 of 1 word give or take).

But if you are trying to build a application or something similiar.. try Google Firebase Studio

https://studio.firebase.google.com/
https://gemini.google.com/
https://chatgpt.com/