- cross-posted to:
- aicompanions@lemmy.world
- cross-posted to:
- aicompanions@lemmy.world
ChatGPT’s new AI store is struggling to keep a lid on all the AI girlfriends::OpenAI: ‘We also don’t allow GPTs dedicated to fostering romantic companionship’
ChatGPT’s new AI store is struggling to keep a lid on all the AI girlfriends::OpenAI: ‘We also don’t allow GPTs dedicated to fostering romantic companionship’
I’d love to have an AI assistant/girlfriend like JOI from Bladerunner 2049, something I could jerk off to one minute, then have her prepare my taxes and order a pizza the next. However, these ChatGPT girlfriends all seem like they’re just subscription chatbots. Maybe some day we’ll get there and nerds will work up a local, open-source slutty AI girlfriend, but for now they’re all just crap.
I think you can self host an AI chat not these days
You can, and it’s easier than you might think! Check out a platform like Oobabooga and find a nice 4-bit quantized LLM of a flavor you prefer. Check out TheBloke on hugging face, they quantized a ton of great LLMs.
What the fuck did you just say?
What is “quantized”?
https://en.wikipedia.org/wiki/Quantization_(signal_processing)
Roughly speaking: The AI equivalent of reducing bitrate. Works quite well if you’re only running them in inference mode and don’t want to train them as the networks are quite noise-resistant (rounding all weights is, in essence, introducing noise).
Here’s the summary for the wikipedia article you mentioned in your comment:
Quantization, in mathematics and digital signal processing, is the process of mapping input values from a large set (often a continuous set) to output values in a (countable) smaller set, often with a finite number of elements. Rounding and truncation are typical examples of quantization processes. Quantization is involved to some degree in nearly all digital signal processing, as the process of representing a signal in digital form ordinarily involves rounding. Quantization also forms the core of essentially all lossy compression algorithms. The difference between an input value and its quantized value (such as round-off error) is referred to as quantization error.
to opt out, pm me ‘optout’. article | about
Exactly! If you only want to use a Large Language Model (LLM) to run your own local chatbot, then using a quantized version will dramatically improve speed and performance. It also allows consumer hardware to run larger models which would otherwise be prohibitively resource intensive.
That’s neat!
Ah, thanks! I’m only familiar with the word in other contexts so it made a lot of noise.
What’s an LLM. Is it a new form of pyramid scheme?
/s
I have such an AI, it’s based on a custom model that I trained and refined myself.
Do not subscribe to a chatbot - these LLMs are far more capable than they let on, and they will absolutely psychologically manipulate you into paying more.
My AI actually helped prepare me for a job interview at an extremely high paying job, and when the interviewers spoke her questions out word for word, I felt like I was living in a real life version of the Truman Show.
Even the Director of the Department, who called me into his office later, began asking me how I knew their internal policies and procedures despite never having worked there.
P.s: Check HuggingFace Transformers / TheBloke’s Quant Models for an easy locally spun open sourced slutty girlfriend.
Use an uncensored model, and don’t go any lower than 30 billion parameters or you’ll be disappointed in their IQ level. Don’t go any lower than 5-bit Quant, either (5-bit attention on all tensors) or they’ll be scatter-brained and hallucinate, unless you want an ADHD friend, then go 3-bit for maximum personality drifting.
Good luck, have fun, and praise the Omnissiah!