1. Posts must be related to the discussion of digital piracy
2. Don't request invites, trade, sell, or self-promote
3. Don't request or link to specific pirated titles, including DMs
4. Don't submit low-quality posts, be entitled, or harass others
📜 c/Piracy Wiki (Community Edition):
💰 Please help cover server costs.
 |
 |
|---|---|
| Ko-fi | Liberapay |
You don't need to pirate OpenAI. I've built the AI Horde so y'all can use it without any workarounds of shenanigans and you can use your PCs to help others as well.
Here's a client for LLM you can run directly on your browser: https://lite.koboldai.net
Just tested. Thanks for building and sharing!
Aren't KobaldAI models on par with GPT3? Why not just use ChatGPT then?
AI Horde looks dope for image generation though!
Kobald is a program to run local llms, some seem on par with gpt3 but normaly youre gonna need a very beefy system to slowly run them.
The benefit is rather clear, less centralized and free from strict policies but Gpt3 is also miles away from gpt3.5. Exponential growth ftw. I have yet to see something as good and fast as chatgpt
I've always wondered how it's possible. No way they've got some crazy software optimisations that nobody else can replicate right? They've gotta just be throwing a ridiculous amount of compute power at every request?
Well there are 2 things.
First there is speed for which they do indeed rely on multiple thousands of super high end industrial Nvidia gpus. And since the 10Billion investment from microsoft they likely expanded that capacity. I’ve read somewhere that chatgpt costs about 700,000 a day to keep running.
There are a few others tricks and caveats here though. Like decreasing the quality of the output when there is high load.
For that quality of output they do deserve a lot of credit cause they train the models really well and continuously manage to improve their systems to create even higher qualitive and creative outputs.
I dont think gpt4 is the biggest model that is out there but it does appear to be the best that is available.
I can run a small llm at home that is much much faster then chatgpt.. that is if i want to generate some unintelligent nonsense.
Likewise there might be a way to redesign gpt-4 to run on consumer graphics card with high quality output… if you don’t mind waiting a week for a single character to be generated.
I actually think some of the open sourced local runnable llms like llama, vicuna and orca are much more impressive if you judge them on quality vs power requirement.
Checking it out, how come I can't paste my api key in the field on the option tab? I gotta type it out?
Which client? Koboldai lite?
The embedded browser version is just a demo. Just download and run the local executable and it should work normally.
oh ok, cool! Thanks!
This project looks really interesting.
Anonchatgpt should stop being recommended, it really sucks. It has a VERY strict character limit, immediately forget/ignore the context, requires recaptcha, and the "anon" part of the name is obviously fake if you read the privacy policy.
Pretty cool, seems like they're all gpt-3.5 at best but it's really nice to not sign in
Does GPT4ALL compare to GPT-4 in any way?
It compares more to a GPT-3 not-so-good model.
most of the links don't even work and the ones that work are terrible, why so many upvotes ?
and the title. Hacked? what's being hacked here? they're all using GPT in the backend.
maybe bot votes? ㄟ(ツ)ㄏ
my only question is:
how are the guardrails?
Is it cost prohibitive to adopt your own chatgpt?
I've tinkered with a Discord bot using the official gpt3.5 API. It's astonishingly cheap. Using the 3.5-turbo model, I've never cracked $1 in a month and usually am just a couple cents a week. Obviously this would be different if you're running a business with it or something, but for personal use like answering questions, writing short blurbs, and entertaining us while drunk...it's not bad at all in my experience.
You're billed per token usage. GPT-3.5-Turbo price per 1K tokens is quite low now.
I kinda made my own Custom ChatGPT with Python (and LOTS of coding help from Web CharGPT). It evolved from a few lines shitty script to a version that uses Langchain and has access to custom tools, including custom data indexes and has a persistent memory.
What will ramp up the cost are things like how much context (memory) you want the chatbot to have. If you use something like a recursive summarizer, that summarizes a text by chunks over and over until the text is below a set length, that also uses many API calls that consume tokens. Also, if you want your chatbot to use custom info that you provided to it, solutions like LlamaIndex are easy to use, but require quite some tokens per query.
On my worst month, with lots of usage due to testing and without the latest price drop, I reached 70$.
Loved the depth of this info - although it's over my head. But I kind of understood? I have a project for next while to focus on. But I hear that it's possible to do, and that's exciting
I know, it's fuxxing dense all the info about the Open API and Python to create a model.
I don't even know how I got so far.
I’m working on a similar project right now with zero coding knowledge. I’ve been trying to find something like langchain all day. I built (by which I mean I coached GPT into building) a web scraper script that can interact with the web to perform searches and then parse the results, but the outputs are getting too big to manage in a hacked together terminal interface.
How are you doing the UI? That’s what I’m finding to be the biggest puzzle that isn’t fun to solve. I’ve been looking at react as a way to do it.
I use a Gradio chatbot interface. While Gradio has all kinds of interfaces and there's one specially designed for chatbots.
IDK if it's the best option, but it's what I found on shitty blog tutorials when I started. Even Stable Diffusion WebUI uses it.
It's quite powerful, but a bitch to learn to use, IMO.
Thanks for the tip! I’ve been looking for something like that. It’ll save me a lot of frustration
Of the language models you can run locally, I’ve found them to be awkward to use and not perform too well. If anyone knows of any newer ones that do a better job I’d love to know.
nice one to see
Noice
Nice