Mauve 👁💜 @mauve@mastodon.mauve.moe

Also! It ended up creating race conditions due to attaching listeners at the wrong point in the test (which didn't matter for this case) but I think I can modify the project's AGENTS.md to make sure it doesn't make the mistake a again.

I'm not sure how long it was chugging away at it, but I see in the logs that it did a few iterations and some bug fixing as it went along. The final code looks pretty much how I would have done it. I don't think this means I'll be using this feature daily, but I might give it another shot next time I have a concrete plan that I want to execute while I make dinner or whatever.

Last week I set my local LLM to do it's first mission where it vibe coded some integration tests for me. I added a "allow local file edits" mode to my harness a little while ago but I hadn't had time to actually give it a go. I spent some time as I was logging off work to go on a date to make a plan with the LLM to test some changes to our replication code and gave it some constraints on which shell tools it'd be auto-allowed to use and set it off.

Becoming the kind of asshole that asks for people to summarize what their AI chatlog is about instead of reading it myself.

New tattoo today. 🤤

Feels good to be back in the part of the codebase I can be more productive in.

We should just have Techaro's Anubis be an HTTP standard that browsers implement instead of all this captcha as a service BS.

https://anubis.techaro.lol/

Can we stop the "prove you're human" checks now that vision models can solve them better than some humans and standardize on a hashcash HTTP challenge/response so we can mitigate the scraping asymmetry while ditching the surveillance JS bloat? Please?

http://www.hashcash.org/

LOL. Someone made it so you could invite a person to a project with the "Blocked" role. Imagine.

ADHD meds are more effective when paired with old school gabber mixes. #ProTip

So pissed off I'm switching back to a regular keyboard so I can rage type faster.

Slop devs don't respect api stability

playing MORSE to learn how to write morse code. Seems fun so far.

Been revisiting local models again. The state of the art for it's size is apparently MiniCPM5 right now. It can do very basic code related tasks but it's still way too stupid to do actual tasks. Might be enough for my "speech to code to speech" idea though?

https://huggingface.co/openbmb/MiniCPM5-2B

The hardest part of software development is dependency management. Whatever funky language features you like or hate are secondary to being able to actually run the code.

Seriously, every dependency is a time bomb waiting to screw your builds. Forking a dependency for your project? Good luck keeping anything together after everything shifts in a year or two.

Debugging haskell dependency hell 💀

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.