jpe90

I recently wrote a blog post exploring the idea of interfacing with local LLMs for ambiguous tasks like this. Doesn't that make more sense than coding the neural network yourself? Using something like llama.cpp and evaluating whether a small model solves your problem out of the box, and fine-tuning if not, then programmatically interfacing with llama.cpp via a wrapper of your choice seems more pragmatic to me.

I started blogging about stuff I've learned about that I am likely to forget down the road. It feels so good when you throw up a post, never share it, and still manage to get a thank you email for writing it years later. If you have a folder full of notes, I would recommend turning them into a blog on a rainy day.

Out of curiosity, what is your development setup for that?

These are awesome hobby devices to hack on. I’m not very experienced with graphics programming but I had a ton of fun developing with the SDK, wrote a blog post on it recently if anyone is interested in learning more about it.

https://jeskin.net/blog/meta-quest-sdk/

Since this is Kotlin there's not really a sane way to call this from Clojure, right?

I only read the headline, so I'm going all-in on Clojure/Datomic off the bat at a new job. Half kidding.

I recently learned Fennel and cranked out a Love2D game as well. Not only that, but I discovered it’s trivial to run the game on some spare nintendo consoles I have lying around, because Lua is insanely portable.

In contrast, I spent a ton of time trying to build other lisps that are designed to be embeddable on those consoles and got nowhere.

Fennel rocks. Such a pragmatic and well designed mini-language.

I don't think CAPI works on mobile runtimes, unfortunately

I’ve been exploring this project recently, I’m having a great time with it so far. The many examples and great documentation are much appreciated. I’m very tempted to try it for some upcoming projects building workflow systems at work.

I've really enjoyed reading (and playing with) kons-9's codebase in Common Lisp. It lets you do exploratory 3D modeling via the program's GUI or the repl. The source is very neatly structured and readable. I don't see many CL projects that do 3D rendering, so it's nice to see!

Quick demo:

https://www.youtube.com/watch?v=i0CwhEDAXB0

Repo:

https://github.com/kaveh808/kons-9

Would it be feasible to fine-tune a large, capable model (like the recent LIMA) on the source code (and maybe a few high quality libraries) of a niche language, such that it's much better at helping you write and understand it?

Imagine how many doors it would open if you could fine-tune models capable of writing language bindings for you and keeping them up to date.

> The OpenAI chat completion endpoint encourages the second-person prompting you describe, so that could be why you see it a lot.

You're talking about system prompts specifically right? And I'm assuming the "encouragement" you're referring to is coming from the conventions used in their examples rather than an explicit instruction to use second person?

Or does second person improve responses to user messages as well?

The excellent backwards compatibility rocks too. This weekend I wanted a library to diagram the class hierarchy of a Java project I put together.

I found a 10 year old library that worked with no issues, I was done in minutes even though I rarely use Java or Clojure so my familiarity is low. There are very few languages where I would have a similar experience.

https://github.com/stuartsierra/class-diagram

Oh that’s clever! Thanks for answering!

This sounds super cool, I’m very curious how you implemented it.

I’m only vaguely familiar with the API.. if I had to guess I would say you send system instruction that its job is to filter unwanted content. And you mentioned you give few examples of unwanted content, so maybe those are additional messages along with an instruction like “filter the following html:”

For every web request you want to filter, you would re-send all of those messages followed by the page HTML as the final message. Is that close?

Since you mentioned sourcehut, I’ll point out that their static hosting is excellent. I host my blog on there and have had no issues.

I would be curious to see how it compares to similar tools: https://github.com/sharkdp/bat/blob/master/doc/alternatives....

if anyone is interested, here's a blog post about using fzf's file preview feature to preview grep results: https://jeskin.net/blog/grep-fzf-clp/

Yeah I think people are reading this the wrong way. Software was originally considered unpatentable under 35 U.S.C. § 101, but language was developed to allow them to be effectively patented by narrowing the scope of the claimed invention to a physical processor which contains an algorithm.

I don't think this is a showstopper in terms of copyright registration of A.I. works, but rather a first step in a back-and-forth process of figuring out the legal structure of how to makes rules and enforcement work.

I came back to Emacs after trying alternatives for a while. I ripped out most of my config and found it much more pleasant to run close to stock.

I'm having better luck using my web browser for email, sublime merge for Git, debuggers in external programs, etc. If I need to do some edits with multiple selections I open up Kakoune, and if I have a burning need for LSP I switch to VS code.

that was an interesting read, i really need to learn more about compilers!

by the way, the expanding hamburger in the navbar is a little buggy on mobile safari. it only expands at the top of the page, so if you press it while you’re midway scrolled it just pushes the content down a bit.

are you using an ios device by any chance?

author probably needs this: https://github.com/adityatelange/hugo-PaperMod/issues/828#is...

i got bit by this on my blog as well

I actually just finally tried out plan 9 in a VM and liked it so much that I’ve been using acme for almost all my development on mac via plan9port for a few weeks now.

I never bothered checking it out before because I had always seen it described as unusable so I figured it would be a waste of time.

There’s a related project that’s really cool called scintillua that lets you use lpeg lexers for scintilla. It supports over 120 languages and it’s super easy to add new ones.

https://github.com/orbitalquark/scintillua

You can also use it as a standalone lua library. I packaged it up to make a faster (but much less feature full) alternative to bat.

https://github.com/jpe90/clp

I'm a big fan of Janet so far. I was surprised by how easy it was to embed in iOS and I appreciate that it's permissively licensed. Great docs, great tooling, clean source code, the author nailed it.

How can I not click on a link about lisp and turtles?

What a cool project, thanks so much for putting it together.

oh awesome thanks for sharing! shfmt works very well so far. i've been using acme for a few weeks and need every formatter i can get :)

https://9fans.github.io/plan9port/man/man1/acme.html

will definitely be putting this in my curriculum to teach my son programming :)

Before I read SICP I had used OOP, functional programming, and lazy evaluation to varying degrees.

In school and independent study I learned how to use those concepts to write programs, but I didn’t really have a clear conceptual understanding of what they really are or how they work under the hood.

I read SICP to learn more about lisp and was surprised to learn a lot about all of those concepts as well. It’s all explained very clearly and there are code examples you can toy with to wrap your head them.

I found it such a gratifying book to read through. And I really regret spending time learning Haskell before reading it, so much needless head scratching.