I’d like this offline. Why are all the good chatbots proprietary online-only software?
They need insane amounts of compute
So? OpenAI aren’t the only ones with large datacenters.
They want your data
Check out /r/localllama. Preferably you need a Nvidia you with >= 24 GB VRAM but it also works with a cpu and loads of normal RAM, if you can wait a minute or two for a lengthy answer. Loads of models to choose from, many with no censorship at all. Won’t be as good as chatgptv4, but many are close to gpt3.
Just played with it the other week, they have some models that run on less extreme hardware too https://ollama.ai/
If you have a high end GPU, or lots of RAM you can run some good quality LLMs offline. I recommend watching Matthew Berman for tutorials (there are some showing paid hosting aswell).
I think KoboldAI runs locally, but like many current AI tools it’s a pain in the ass to install, especially if you’re on Linux, especially if you’re using AMD GPUs. I wonder if we’ll see some specialized AI related cards to slot into our pci ports or something. Not a whole lot of necessary options to fill them nowadays anyway. I’d also be interested in local AI voice changers too. Maybe even packaged like a Roland VT-4 voice transformer that sits between your mic & whatever audio other audio interface you might be using, where you just throw the trained voice models onto the device and it does all the real time computing for you.
I’m sure things get more refined over the next years though.
It would actually be pretty cool to see TPUs you can just plug in. They come stock in a lot of Google products now, I think.
By design, because they don’t want some basement guy launching skynet.
I have to agree, I trust a handful of big shops, some of which could actually be killed by ethics people against the wishes of investors, far more than the entire internet. It still might not be enough, but there is no applying breaks whatsoever if anyone can take the next step.
It won’t take long until cheap special purpose chips hit the market. Then you’ll have your offline model. There are already models that run on consumer hardware, but it’s for enthusiasts at the moment and not the same quality (but almost). But if you want to spend thousands on a PC that can handle the largest models, go ahead.
ChatGPT 4 is estimated to use 700GB of “High Bandwidth Memory”.
… which will set you back about half a million dollars at current prices (which are high, because the manufacturers can’t keep up with demand). Or, you could just pay 20 bucks a month.
I highly doubt that, there are comparable models that are way smaller than that. No way they would waste that much money.
There are comparable models to GPT 3.5 “Turbo”, which is faster and 30x cheaper than GPT 4 (if you pay OpenAI’s regular API prices).
I suspect that’s because GPT-4 needs 30x more memory than 3.5.
I’m not aware of any other model that performs as well as GPT-4. In fact I suspect even 3.5 Turbo is the second best model.
Doesn’t that mean RAM?
To put some numbers on it - RAM runs at tens of gigabytes per second (bytes, not bits). High Bandwidth Memory runs at several hundred or sometimes terabytes per second (OpenAI is likely using the latter, and that memory isn’t just expensive it’s also supply constrained, so the prices are astronomically high right now).
You can buy HBM, and you can use it as your main system RAM, but it’s painfully expensive. The actual amount of bandwidth also scales linearly with with the amount of memory you buy as well. So a 500GB is 10x faster than 50GB - because it write to all of the chips simultaneously (and then read from all of them when you access the data back).
It’s pretty standard on high end GPUs these days. Apple also uses it on all their computers (if you buy a Mac with 64GB of RAM, it’ll run at 800MB/s - which isn’t quite as fast as a high end GPU but it’s close and it is HBM). It’s part of why Macs are so expensive (and also why the cheaper ones have very little RAM).
🤖 I’m a bot that provides automatic summaries for articles:
Click here to see the summary
According to The Decoder, leaked screenshots and videos show a custom chatbot creator with many of the same features already available in ChatGPT using GPT-4, like web browsing and data analysis.
This morning, SEO tools developer Tibor Blaho shared a video of the UI for the feature in action, showing a GPT Builder option that lets users enter a prompt — an example reads “make a creative who helps generate visuals for new products.” — to create a chatbot.
Users can also upload files for a bespoke knowledgebase and toggle capabilities like web browsing and image generation.
Choi shared a screenshot that breaks down the Team plan’s features, like unlimited high-speed GPT-4 and four times longer context.
Recent ChatGPT beta features include live web results, image generation, and voice chat.
OpenAI says it will preview new tools at the developer conference on Monday, so we probably won’t have to wait long to find out if these rumors are accurate.
Saved 55% of original text.
