davidkunz

I'm a bit concerned when library authors only test it with blocking Io and the consuming app with a different kind. Wouldn't this potentially lead to bugs?

Thank you! I found ast-grep to be really useful, I hope more people will discover it!

I wish companies would adhere to a consistent naming scheme, like <name>-<params>-<cut-off-month>.

I wouldn't exclude Lua, it's a simple language whose basics you can learn pretty quickly if you know JavaScript or comparable languages. I therefore would recommend Neovim.

Maybe if you can't precisely model your structure with (OpenAI's subset of) JSON schema.

Nothing new, we've been doing it like that for ages here in Germany. But it's a cool Hamburger phone.

The title is a bit misleading and readers might think he didn't know how to open files in C++. This is not the case, see https://x.com/Deor/status/1815563936671867315

I look forward to the day when Germany ends the use of fax machines.

Like in video games: Show the door before the key.

Advertisers: Great for product placement.

It doesn't yet have a plugin system but they're thinking of adding one for the Steel programming language (a lisp).

https://github.com/mattwparas/steel

I bet Sora can "run" Doom.

The experiment seems flawed because they might think the experimenter knows the right choice and tries to lead them to the wrong answer. If you're only interested in studying regret, I wouldn't let the experimenter know the right cup.

> Rocket 3b uses a slightly different prompt syntax.

Wouldn't it be better if llamafile were to standardize the prompt syntax across models?

Yes, I'm using them in my text editor with my plugin [1] and it's already useful for everyday tasks like summarization, fixing grammar or making text more concise.

[1]: https://github.com/David-Kunz/gen.nvim

Well done, Mistral! "Show, don't tell" par excellence.

I use them in my editor with my plugin https://github.com/David-Kunz/gen.nvim

> yank from visual mode, which has a similar show-explicitly-what-is-being-copied behavior.

Even better: vim.highlight.on_yank

Yes, it works with an Ollama server and the communication is done via HTTP. I know that someone configured my plugin to talk to OpenAI.

It should work on Linux and also with WSL. You could also try running it in Docker.

Out of personal experience, open source LLMs did not yet reach the quality of GPT 3.5, despite multiple claims with dubious benchmarks. That said, they are already useful as of today and can even run on your local machine. I regularly use them with my Neovim plugin gen.nvim [1] for simple tasks and they save me a lot of time. I'm excited about the future!

[1]: https://github.com/David-Kunz/gen.nvim

I got confused because I thought it would set a background color. For text it's inverted and hence correct.

Sorry, I misread your answer. You're right. I automatically assumed setting some background color for which `color: light-dark(white, black);` would be right.

But why is the order switched below?

Functional notation: light-dark(light-color, dark-color)

I think `black` and `white` should be switched here:

color: light-dark(black, white);

A demo video is in the README (I used Mistral-7b in there).

For smaller models, I'm impressed by Mistral-7b or fine-tuned variants like Zephyr. I use it regularly in Neovim[1] for mundane tasks (grammar correction, summaries, ...). I'm curious how Orca 2 performs, downloading it right now.

[1]: with https://github.com/David-Kunz/gen.nvim

Here's the plugin: https://github.com/David-Kunz/gen.nvim

Ollama is great, I recently integrated it into my text editor (Neovim), now I have local AI assistance when coding/writing text.

https://youtu.be/FIZt7MinpMY?si=fzcmKq5cw2bniH26

> Pages before are topics.

What if there's an important detail hidden in a topic?