sharegpt VS llm-workflow-engine

he also created cool projects like https://oneword.domains/, https://sharegpt.com/, https://novel.sh/ and https://extrapolate.app/

Vicuna is another instruction-focused LLM rooted in LLaMA, developed by researchers from UC Berkeley, Carnegie Mellon University, Stanford, and UC San Diego. They adapted Alpaca’s training code and incorporated 70,000 examples from ShareGPT, a platform for sharing ChatGPT interactions.

We can say that a 13B model per language is reasonable. Then it means we need to create a democratic way for teaching coding by examples and solutions and algorithms, that we create, curate and use open-source. Much like sharegpt.com but for coding tasks, solutions ways of thinking. We should be wary of 'enforcing' principles rather showing different approaches, as all approaches can have advantages and disadvantages.

You can see the url in the comment, https://sharegpt.com and if you go there it gives you the option for installing the chrome extension, after that it shouldn’t be hard to use it

ShareGPT - Share your prompts and your entire conversations

Or used https://sharegpt.com

you can gets lots of ideas here > https://sharegpt.com/ (180,000+ prompts)

I would love to read the whole conversation: Check out this cool little GPT sharing extension: https://sharegpt.com - that way the code snippets can be copied easily

> Cool, that’s really the only point I’m making.

To be clear, I'm saying that I don't know if they are, not that we know that it's not the same.

It's not at all clear that humans do much more than "that basic token sequence prediction" for our reasoning itself. There are glaringly obvious auxiliary differences, such as memory, but we just don't know how human reasoning works, so writing off a predictive mechanism like this is just as unjustified as assuming it's the same. It's highly likely there are differences, but whether they are significant remains to be seen.

> Not necessarily scaling limitations fundamental to the architecture as such, but limitations in our ability to develop sufficiently well developed training texts and strategies across so many problem domains.

I think there are several big issues with that thinking. One is that this constraint is an issue now in large part because GPT doesn't have "memory" or an ability to continue learning. Those two need to be overcome to let it truly scale, but once they are, the game fundamentally changes.

The second is that we're already at a stage where using LLMs to generate and validate training data works well for a whole lot of domains, and that will accelerate, especially when coupled with "plugins" and the ability to capture interactions with real-life users [1]

E.g. a large part of human ability to do maths with any kind of efficiency comes down to rote repetition and generating large sets of simple quizzes for such areas is near trivial if you combine an LLM at tools for it to validate its answers. And unlike with humans where we have to do this effort for billions of humans, once you have an ability to let these models continue learning you make this investment in training once (or once per major LLM effort).

A third is that GPT hasn't even scratched the surface in what is available in digital collections alone. E.g. GPT3 was trained on "only" about 200 million Norwegian words (I don't have data for GPT4). Norwegian is a tiny language - this was 0.1% of GPT3's total corpus. But the Norwegian National Library has 8.5m items, which includes something like 10-20 billion words in books alone, and many tens of billions more in newspapers, magazines and other data. That's one tiny language. We're many generations of LLM's away from even approaching exhausting the already available digital collections alone, and that's before we look at having the models trained on that data generate and judge training data.

[1] https://sharegpt.com/

I want to turn on my mic and see my words show up in my active terminal tab. App-agnostic is good but app-specific would work; this is for chatgpt input with https://github.com/mmabrouk/chatgpt-wrapper. right now i'm using chatgpt in browser with speech-to-text browser extension and I would prefer not to. advice regarding older hardware applies here, but also interested in cutting edge for powerful pcs. Any guidance, links to guides valued.

There are more popular Python projects for ChatGPT: https://github.com/mmabrouk/chatgpt-wrapper

Shameless plug here for those (like the author) who are using GPT in your projects and finding the costs to be too high.

I've built an open source wrapper around ChatGPT that lets you use it programmatically as an API or from Python or in CLI. Best of all, it's completely free! So it is great for testing the waters on a hobby project.

Check it out on GitHub: https://github.com/mmabrouk/chatgpt-wrapper

Never worry about exceeding hourly submit times, as the tool waits until it can run again. In short, the ChatGPT Batch Whipper tool is an efficient and user-friendly way to perform batch jobs with ChatGPT. We welcome any feedback or suggestions you may have, so give it a try and see how it can improve your workflow! Thanks to @mmabrouk some of codes were inspired and modified from his repo.

the wrapper I'm using is https://github.com/mmabrouk/chatgpt-wrapper, which is awesome (no credit to me). I just wrote a bash script to wrap around the wrapper :P.

chatgpt-wrapper: API for interacting with ChatGPT using Python and from Shell.

What is the best way to quickly install Python repos like chatgpt-wrapper using Nix?

You may have seen people write tools that use the chat gpt engine, but they all work by automating a browser connected to https://chat.openai.com/chat (e.g. chatgpt.py).