Jonathan Bowman

A little confused by the association of "distillation" and "attack." Which individuals and companies are allowed to consider generated tokens their own for developing their product? If I develop a Typescript runtime or CLI Coding Assistant, am I allowed to use Claude outputs?

Started to use "droid" today, a very nice command-line agentic coding assistant by @FactoryAI. I used it to tune some complex LLM API calls in my code (looking at you, OpenAI /responses API!) The droid cli did a fabulous job! Without consuming tokens indiscriminately.

@msuiche My only helpful finding so far applies more to models in the 1B to 3B range. Sometimes one or two examples in the prompt (keeping it very concise) yields better structured output than simple one-shot, at least if I am after some JSON. But you have inspired me to utilize XML more

@jdbowman Feel free to share notes! I'm definitely going to spend more time on it too

just put some internal notes about small language models into a blogpost. nothing crazy, but I would love to find more hands-on people to talk with about it. msuiche.com/posts/building…

@msuiche Oh, nice. The Qwen3 line is certainly worth exploring. I will re-iterate that Qwen3 1.7b continues to amaze me for its size, too. And, yes... tools! I am slowly experimenting with this, too, but I haven't settled on best practices yet. So your article drew me in.

@jdbowman Very good point. tbk I completely missed 0.6B but I'm sure it performs great. One of the main thing I noticed (and something I want to dig more into) is the way they process tools

I have been very curious about very small LLMs lately, such as Gemma-3-270m, Qwen3-0.6b, LiquidAI/LFM2-1.2B, etc. So I truly loved reading this informative and practical article.

@msuiche When I read your article, I thought most often of Qwen3:0.6b. Qwen3:1.7b also, but it doesn't always require the same rigorous discipline outlined in your article (but it could benefit!) but 0.6b kinda does. And both perform so well for so many scenarios.

@jdbowman Thanks for spotting this! It’s Qwen1B not nano! Fixing this now

There are a nice array of tmux options in Nix Home Manager home-manager-options.extranix.com/?query=tmux&re…

Learning a little tmux with the excellent book _tmux 2: Productive Mouse-Free Development_ pragprog.com/titles/bhtmux2… by @bphogan

Keeping tabs on the very rapid development of sqruff by @quarylabs. Like sqlfluff, but Rusty and fast. We will see where this goes... github.com/quarylabs/sqru…

Learning the Rust configuration library Figment. Works well for my needs, and integrates with clap just fine. github.com/SergioBenitez/…

Found a password in my git repo. Need to replace it with placeholder or mask from current HEAD and history. github.com/newren/git-fil…

Really impressed with sli.dev @Slidevjs This is now my go-to presentation tool.

In the foot terminal, I frequently forget how to view URLs in the browser. Ctrl-shift-o to the rescue. #urls" target="_blank" rel="nofollow noopener">codeberg.org/dnkl/foot/src/…

@m_kunc I am glad you found it helpful!

Jonathan, thanks for your "Install Docker on Windows (WSL) without Docker Desktop", very comprehensive! @jdbowman #DEVCommunity dev.to/bowmanjd/insta…

When configuratin sway wm, keybinding codes can be found with the wonderful tool wev by Drew DeVault, as in "wev -f wl_keyboard:key" git.sr.ht/~sircmpwn/wev

@chainguard_dev I think the cost of ones will go way up due to demand vs. supply. Zeroes will be even more expensive, due to the controversy around them (google.com/books/edition/…)

What are your software supply chain predictions for 2023? 🤔

Using and exploring @SQLFluff for both linting and auto-formatting SQL. Very flexible and configurable. Honestly, can't find better in the open source space. Actively developed. docs.sqlfluff.com

Enjoying aiosqlite today. Does exactly what it is supposed to (async sqlite for Python), thanks to Amethyst Reese @n7cmdr and others. github.com/omnilib/aiosql…

@ibuildthecloud @aronchick Curious and my brain is slow this morning: what is the "it" here? Containers, maybe, but a container doesn't run browser-side. I doubt you mean transpiling to js... This is a great thread, by the way; thanks for initiating the conversation, @ibuildthecloud

@aronchick But why? You know you can already do that today :) I could say, maybe it's not as easy as WASM, but it's not easier because WASM is so immature.

I’m really not getting WASM these days. It’s a crappy experience to write, it’s a crappy experience to run. And in the end I get what?