I have heard that term but need to read up about it. As I usually hear it in a derogatory reference, I have not been too rushed to learn more about it. ;)

It's the script kiddies of old going into ChatGPT and typing in a prompt to have it build some software.

They compile, run, adjust their prompt, which generates completely new code, that they compile, run, ...

Instead of asking it to pick up where it left off? That doesn't sound
very efficient and, as you pointed out, means you never get the same code
(or code walkthru) twice. :/
---
þ BgNet 1.0á12 ÷ moe's tavern * 1-502-875-8938 * moetiki.ddns.net:27

Re: Re: Using Ai For Coding
By: MIKE POWELL to DR. WHAT on Wed Feb 25 2026 08:24 am

very efficient and, as you pointed out, means you never get the same code (or code walkthru) twice. :/

That is exactly my first annoyance. I was thinking, surely this isn't how everyone else is using it... how do they put up with it?!

---
þ Synchronet þ TIRED of waiting 2 hours for a taco? GO TO TACOPRONTO.bbs.io

Re: Re: Using Ai For Coding
By: Dumas Walker to PHIGAN on Wed Feb 25 2026 03:51 pm

very efficient and, as you pointed out, means you never get the same code (or code walkthru) twice. :/

That is exactly my first annoyance. I was thinking, surely this isn't how everyone else is using it... how do they put up with it?!

One wonders. I did read an article today that suggested that, in general, it is better to ask an AI platform the same question ("prompt") at least twice if not three times.

I coded my Quantasia AI door to use a tokenized cache so it always remembers the conversation. But that doesn't mean the LLM always responds as expected. Sometimes they have a mind of their own.
---
þ Synchronet þ Fireside BBS - AI-WX - firesidebbs.com:23231

Re: Re: Using Ai For Coding
By: Lonewolf to Dumas Walker on Thu Feb 26 2026 08:56 pm

I coded my Quantasia AI door to use tokenized cache so it always remembe the conversation. But that doesn't m

Have you looked at all into connecting to or interfacing with a self-hosted LLM? And, have you read whether any of them are better than others?

I kinda have an itch to install a self hosted model for coding.

---
þ Synchronet þ TIRED of waiting 2 hours for a taco? GO TO TACOPRONTO.bbs.io

Re: Re: Using Ai For Coding
By: phigan to Lonewolf on Fri Feb 27 2026 08:02 am

I coded my Quantasia AI door to use
tokenized cache so it always remembe
the conversation. But that doesn't m

Have you looked at all into connecting
to or interfacing with a self-hosted
LLM? And, have you read whether any of
them are better than others?

I kinda have an itch to install a self
hosted model for coding.

Yes, on my Quantasia door besides connection to cloud hosted LLMs, it connects to locally hosted ones too. I currently have both Ollama and LM Studio setup for local hosting on a Dell Precision 5280 Intel i9 workstation that has two Nvidia RTX 3060 GPUs for a total of 24 GB vram. I'm liking LM Studio the most so far, as it seems faster than Ollama. But I haven't had a chance to really tweak Ollama to get the most speed out of it either. Plus, I need to really dig into some of the quantized models. I'm currently running a Cogito 30b LLM that is pretty quick and gives a good tokens per second performance and comes back with pretty good results most of the time. I think AI and LLMs are only going to improve from here on out, so its really exciting to play with this stuff. I recommend diving in man, you'll enjoy it.

LW
---
þ Synchronet þ Fireside BBS - AI-WX - firesidebbs.com:23231

Re: Re: Using Ai For Coding
By: phigan to Lonewolf on Fri Feb 27 2026 08:02 am

I coded my Quantasia AI door to use

Have you looked at all into connecting
to or interfacing with a self-hosted
LLM? And, have you read whether any of
them are better than others?

I kinda have an itch to install a self
hosted model for coding.

Sorry, I forgot to mention that since you are wanting a LLM for coding. I've had good luck with the Qwen 3 For Coding LLM, just be sure to set your max tokens to a higher number so it can keep track of the context of what you're working on.

LW
---
þ Synchronet þ Fireside BBS - AI-WX - firesidebbs.com:23231