This is why you should always selfhost your AI girlfriend.
I ain’t got that kinda GPU to spare. If it’s the games or my AI girlfriend…
you dont need that much power. something like a rx 6600xt/rtx 3060/rx580 is plenty
I’d only date someone fully independent, so my AI joyfriend operates their own cloud cluster through a combination of a crypto wallet and findom
I think my wife is cheating on me with my self hosted AI girlfriend’s boyfriend that lives in the same database file. What do I do?
Now consider the number of normal people in the world who do not have a server rack in their closet, and how much they are about to be defrauded and blackmailed
You need a little gpu server farm for proper models & context sizes though. Single consumer gpus don’t have enough vram for that.
Are there any Open Source girlfriends that we can download and compile?
Hey now, I don’t want anyone looking at my girlfriend’s source code. That’s personal!
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!
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.
Hmm, if only there was some hardware analogue for long-term memory.
Pretty easy to roll your own with Kobold.cpp and various open model weights found on HuggingFace.
I tried oobabooga and it basically always crashes when I try to generate anything, no matter what model I try. But honestly, as far as I can tell all the good models require absurd amounts of vram, much more than consumer cards have, so you’d need at least like a small gpu server farm to local host them reliably yourself. Unless of course you want like practically nonexistent context sizes.
Hey Sugar, which of these pics have traffic lights on them?
bots gotta help each other
Yeah. Saw that one coming.
Isn’t this what every app on your phone is already doing? Why would “AI Girlfriend App” be any better than Facebook or Google?
It’s even more insidious because these apps ask for the data upfront under the guise of “getting to know you better”
How can your AI girlfriend truly love you back unless you give it your real name, age, photos of your face, mother’s maiden name, social security number, and genetic material? /s
lol it’s not. That’s the point. It’s all the same sort of companies putting these fucking things out. Google and Facebook are both working on their own AI. It’s been shown over and over how they’re scraping all available data—public or private when available—so why the fuck would a newer tech company be any different? It’s the state of capitalism. The markets are focusing more on hyper focused data, so that’s what any profitable tech company is doing. Invading your fucking privacy.
That’s why it’s not a surprise. Because Facebook and google helped set the trend and determine the current tech market. And that’s the world these new “AI girlfriends” are existing in.