pumanoir

which engine?

59.5 t/s is really good. Which engine/quant are you using?

can you share ane example of one of your prompts? I have tried to convert some text into the socratic method and haven't succeeded yet.

There's app that allows you to do something quite similar in real time:

https://apps.apple.com/us/app/quikanimate/id6467067883

Mark Cuban has a neat startup to appeal health insurance denials www.getclaimable.com/

The example.py file says "it will run blazing fast on any GPU. But this example will run on CPU."

I couldn't locate how to run it on a GPU anywhere in the repo.

For office I'd recommend Softmaker's FreeOffice or Pro 2024. They've worked great in my linux and macs

Excellent, thanks! Just took a look at "TCP/IP Illustrated: Volume 1" and was exactly what I was looking for. Any book along those lines that is compressed/water down (just to get started over a weekend)?

Where can i learn to do this kind of things? Any book(s) that'd teach this kind of stuff?

thanks. it'd be great to have a quick tutorial on doing so. this is close to my dream of creating Frankenstein apps with the web platform instead of graal :)

https://www.graalvm.org/latest/reference-manual/polyglot-pro...

How would i use numpy from javascript using this?

If we want to stay in the older license? Do we just do `npm i tldraw@3` and work from there?

Why is Anthropic hiring developers? Amodei said that AI will be generating all the code by the end of the year.

(Honest question) Can you share how to use Dutch-US treaty to basically hire oneself?

The scammers in question use stolen US citizens' identities. Same thing happens in Europe to a lesser degree.

I've had great success to convert math pics to latex using qwen2-vl

which books will teach how to build your own computer algebra system? (I've only heard PAIP does)

I skimmed (ctrl-f) the paper and didn't see a comparison against gpt-4. Anybody knows how they'd compare?

Depends on the model and GPU. Here is an example of almost 2x on a 3060 for StableDiffusion: https://www.youtube.com/watch?v=_6BsUijOWoM

Optimization by gradient descent is used to do the learning in deep learning. For example, diff eqs are used to create optimizers that improve upon the classic 'adam' say, such as the new 'sophia' [1]. 1. https://arxiv.org/abs/2305.14342

Thanks!

Are there examples to use it for SGD using this? Like "Here is a tutorial on how to do a nanoGPT using DiffEqGPU.jl"?

That quote sounds like it could be explained by Dan Kahneman as a symptom of 'ego depletion'

I read and watched almost all the modules and for me it as it is, perfectly accomplishes the intention of the course as stated by the op.

Your suggestion may work for other intents (like having a Schaum's Outline of LLM's) and I would also love to have that additional material (maybe yourself could provide it as it seems you have a clear idea)

I've seen the same in many google pages (which I think is illegal under GDPR).Anyways, I use ublock origin to get rid of that.

This is great! Pattern matching (+tuples, records) is going to make conditional rendering, conditional styles and state management even nicer in Flutter. Thank you Dart team.

BTW, all the negative comments I see here seem to come from people who haven't worked with Dart and Flutter which is a cultish reactive showing of `google meh` `apple cool!` sentiment that permeates HN.

If you haven't tried Flutter and Dart give it a good try, it is really nice.

A great option but there is wonnx which seems to be more complete and mature. And the bonus is that it's implemented in Rust (if you are into it).

https://github.com/webonnx/wonnx

You mean like what's described in this blog post, correct?

https://adapterhub.ml/blog/2022/03/adapter-transformers-v3-u...

ChatGPT and Claude also get tripped by both questions

These examples are great, but the chess engine sounds specially interesting and can't think of how I'd do it with langchain. Do you have a git link or something written down, on how you accomplished this?