• 3 Posts
  • 1.83K Comments
Joined 1 year ago
cake
Cake day: June 10th, 2023

help-circle




  • If they’re local they’d be basically useless due to a lack of computing power and potential lack of indexing for a search engine chatbot, so I doubt it. It would also have to be so polished that it wouldn’t require further user knowledge / input, and that’s just not a thing with any local LLM I’ve come across. Mozilla can gladly prove me wrong though. I certainly wouldn’t mind if they generally can make the whole process of local LLMs easier and more viable.









  • All of those could be terrible to be honest, because AI is a data tracking vacuum. An AI adblocker or content filter sounds cool at first, but it would mean it reads and analyzes your data, just like the shit you do with chatbots too. Reading your mails? That’s basically what Google does for years with gmail, that’s why they have such a good spam filter. I agree that a chatbot would be kinda useless though, even if privacy friendly, which in of itself would be great but I just don’t see the use. This could simply be outsourced to a website.






  • The bots (what the actual girlfriends or whatever other characters are) aren’t the problem. You can find them on chub.ai for example or write them yourself fairly easily. The issue the software, and even more so the hardware. You need something like the mentioned Kobold.ccp or oobabooga, and then you’d also need a trained LLM model that you can get on huggingface.co, which is already where it gets complicated (they’ll be loaded within kobold or oobabooga). You also need to understand how they work in regards to context sizes & bytes, because they need a lot, and I mean A LOT of vram to work properly. Basically, the more vram you have, the better the contextual understanding, their memory is. Otherwise you’d have a bot that maybe knows to only contextualize the last couple messages. For paid services like novelai.net you basically have your bots run through big ass server farms with lots of GPUs that bundle their vram and processing power, giving you “decent” context sizes (imo the greatest weak point of LLMs and it is deeply rooted in how they work) and decent speed. NovelAI also supports front-ends like SillyTavern which is great for local bot management and settings, regardless if you self host or use a paid service (NOT EVERY PAID SERVICE HAS AN API FOR THIS! OpenAI’s ChatGPT technically does too but they do not allow NSFW content and can ban you for that if caught).
    There’s a bunch of “free” online services too, like janitorai.com but most of them have slow speeds and the chat degrades significantly after just a few messages, because they have low context sizes. The better / paid models suffer from this degradation too but it is slower and less noticeable, at least at first. You can use that to get an idea of how LLMs work though.

    Edit: Should technically self explanatory / common sense, but I would advise not to share ANY personal information through online service chats that could identify you as a person!