Mauve 👁💜 @mauve@mastodon.mauve.moe

I think my philosophy when making software is that it should work for people with zero money or no bank account / credit card.

I know it's not a popular mindset to be in since money and profit is everything in the tech world.

I think it comes from growing up as a kid with no disposable income or access to anything but my shitty computer.

I'd rather support people with almost nothing than people with latest and greatest tech gizmos and spare cash for subscription services. 😅

Thread of stuff I wanna buy. Will "like" my own toot if I get it.

I'm gonna use this yhread as a way to keep track of links to read and like my own posts when I get around to them.

I think of LLMs as tools that decompress a few words into more words. E.g. instructions into tool calls. My goal is to use as little power and as few words as possible to make it output the words I want faster than I can type it. It's like a keyboard / search tool but with a bunch more shortcut options.

With enough training on speech -> code, it might make it possible to have a model do code -> speech so that you could have n lines fed into the reader to get back a speech description. E.g. "for loop over users, call purge data on each". Maybe a "tranalate to grug" could work too. Again with like a 2b model it should be enough but fast as heck.

Using an LSP can help make it generic between languages, but regular text could be good enough. I just really like being able to "go to definition" and "list all call sites". Rename symbol is pretty convenient too.

Navigating could be the same but with a JEV style model. Trigger navigate action. Say "clear all users", Model gets passed all the var names in the file including clearAllUsers(). LLM choses option you most likely meant and you go to the next occurance.

Slop based audio coding: Describe change in English (select star from users where name equals bob). Editor passes few lines around cursor and file name to LLM. "Turn this into code", LLM outputs diff. With small models and small changes you could probably edit at the speed of speech.

Dang, meta's new #VR glasses would be so perfect if they weren't poisoned by facebook's bullshit 😭

My desktop environment is ultra minimal and high contrast primarily to conserve resources and to work better on translucent video glasses.

Lmao of course four repositories worth if CI infrastructure go busted right as I need to push out a prerelease to unblock another team. 😭

Any meaning is enough for it to be worthwhile.

I find it so funny when I have to convince my local llm that it can totally do something it thinks it can't because I understand how it's harness works better than it. 😅

Reading an immunology textbook. I love how information dense they are. 🤤

It feels so good to not have to wait for a bunch of ads and "Recommended" content to load every time I load my homescreen.

I had my local LLM use ADB to figure out how to connect over wifi and override the launcher when the default one kept taking over.

Just installed this open source launcher for my #android TV and it's SO much nicer than all the BS in the default launcher that Google made me use.

https://github.com/leanbitlab-org/LtvLauncher

Remember that the season is transitioning and your body is more likely to make you crave change. If you listen to it make sure to think through the tradeoffs.