Are there any Open Source girlfriends that we can download and compile?
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.
You’ll want to use a quantised model on your GPU. You could also use the CPU and offload some parts to the GPU with llama.cpp (an option in oobabooga). Llama.cpp models are in the GGUF format.
Also for an interface, I’d recommend KoboldLite for writing or assistant and SillyTavern for chat/RP.
Hey now, I don’t want anyone looking at my girlfriend’s source code. That’s personal!
I don’t want anyone looking at my girlfriend’s source code
it’s okay, dude, we all already did…
i second this request. please
See my other reply for some basic info & pointers.
deleted by creator
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!
Does it make it faster if the GPU has waifu stickers on it?
I don’t know, I’m not a weeb.
itll do the opposite im afraid, OW! Hot… umm whats that awful smell of burning plastic.
Define “it”
Because waifu stickers may indeed speed up “it” for some definition of “it”
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.
What are you trying to say? Do you understand what the problem is?
I guess I’m wondering if there’s some way to bake the contextual understanding into the model instead of keeping it all in vram. Like if you’re talking to a person and you refer to something that happened a year ago, you might have to provide a little context and it might take them a minute, but eventually, they’ll usually remember. Same with AI, you could say, “hey remember when we talked about [x]?” and then it would recontextualize by bringing that conversation back into vram.
Seems like more or less what people do with Stable Diffusion by training custom models, or LORAs, or embeddings. It would just be interesting if it was a more automatic process as part of interacting with the AI - the model is always being updated with information about your preferences instead of having to be told explicitly.
But mostly it was just a joke.
Yes, databases (saved on a hard drive). SillyTavern has Smart Context but that seems not that easy to install so I have no idea how well that actually works in practice yet.
I thought this was a new Chuck Tingle novel.
He’s on social media. This could probably be arranged.
Fooled again, it’s Chuck Testa.
Pounded in the Butt by my Data Stealing AI Girlfriend
Like I could ever get an AI girlfriend. They’d never have me.
You need Lucy Lou bot.
It’s amazing the way you NOTICE TWO THINGS.
The entire internet is a data harvesting horror show. It’s good for the economy though, so we don’t do anything against it.
ROFL! There country be a more hilarious headline! I love it!
This is the best summary I could come up with:
According to a new study from Mozilla’s *Privacy Not Included project, AI girlfriends and boyfriends harvest shockingly personal information, and almost all of them sell or share the data they collect.
“Although they are marketed as something that will enhance your mental health and well-being, they specialize in delivering dependency, loneliness, and toxicity, all while prying as much data as possible from you.”
Every single one earned the Privacy Not Included label, putting these chatbots among the worst categories of products Mozilla has ever reviewed.
You’ve heard stories about data problems before, but according to Mozilla, AI girlfriends violate your privacy in “disturbing new ways.” For example, CrushOn.AI collects details including information about sexual health, use of medication, and gender-affirming care.
One of the more striking findings came when Mozilla counted the trackers in these apps, little bits of code that collect data and share them with other companies for advertising and other purposes.
EVA AI Chat Bot & Soulmate pushes users to “share all your secrets and desires,” and specifically asks for photos and voice recordings.
The original article contains 545 words, the summary contains 177 words. Saved 68%. I’m a bot and I’m open source!
24 thousand tracker calls in one minute.
That’s impressively gross.
I’m not sure what kind of use collecting all my most fucked up thoughts can be.
Making a better chat bot AI girlfriend, informing porn directors, leaking it to the Russians,
Making a better chat bot AI girlfriend
Cool.
informing porn directors
Neat.
leaking it to the Russians
My thoughts aren’t fucked up enough to be useful to them.
When a a NSFWICBM hits Kiev and every ukrainian starts masterbating furiously to our fucked up thoughts, we will know
“You see, Ivan, if you make them horny for feet, they will gladly lay down their arms at yours.”
Either advertisers or the cops, possibly both want that information very much
This is why you should always selfhost your AI girlfriend.
You need a little gpu server farm for proper models & context sizes though. Single consumer gpus don’t have enough vram for that.
Might as well just pay for a prostitute
Yeah, I heard they’re also very privacy friendly.
Unless you piss them off
I was being sarcastic. If you pay for a prostitute you might as well pay for an AI service such as novelai.
Locally hosted AI sucking down on our dick through usb plugged dildos. This is the future.
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’m interested. So you rent a cluster to run an instance instead of self hosting?
They sound fun
Let me go buy some milk.
Woah there, I’m not sure I’m ready for that level of commitment.
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
Is support for AMD cards better these days? Last time I checked it involved checking ROCM compatibility because CUDA needs nvidia cards exclusively.
gpt4all worked out of the box for me
🤣
I’d have to actually test my backup strategy
That’ll make you go blind
And give you hairy palms
You have to at least move out of your AI parents’ server rack before letting your AI girlfriend move in.
Nvidia^TM
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
- My Canadian Girlfriend
Broke, Busted, Burned Out
- My Canadian Server-Farm Girlfriend
Smart, Sexy, Superconductive
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?
For as long as everyone is using a virus checker, maybe you could try an open source relationship.
Delete system32 obviously
Sounds like a job for Little Bobby Tables
I didn’t realise they are that realistic.
You’re just jealous of our love.
damn someone else besides me figured this out I thought I was a genius or something
Why don’t these people do what perfectly mentally unhealthy people do and just abuse the super chat of your local vtuber?
Here is an alternative Piped link(s):
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I’m open-source; check me out at GitHub.
At least the VTuber is a real human behind an anime figure.
Can we please stop posting Gizmodo shit posts? It’s just pure garbage
deleted by creator
People panned the game but this was the whole point of the NG Resonance character in Deus Ex Invisible War. People would basically tell this AI pop star intimate details about their lives and then the data was used against them and their local communities.
I always wondered though, how many of those people were aware that it was an ai and not the real NG Resonance? (Have to admit, she did get me in trouble with the Omar. My bad. 😅)
The shit I do for a discount on non-PiezoChem functionality.
I think they knew and it didn’t matter to them which is oddly prophetic when I look at the state of the world today lol
