I have two kinds of hobby code projects; 1) where I enjoy choosing my tools and writing everything as perfect and beautiful as I can, and 2) where I’m just enjoying hacking or learning something, and also the fact that I can write as much spaghetti as I want. I love both 😅

I used to write small Windows apps with Delphi as a teenager. Left Win and native apps decades ago but LLMs have gotten me to dabble with native macOS and iOS apps jus for my own use. Full-on slop vibecoding is fun when you really don't need to care about the code at all.

TIL: the Claude banked "full reset" does *not* change your weekly cutoff at all nor does it remove the 5h limits. So it's effectively a single 5h reset 🤦‍♂️

I wonder if there's something seriously wrong with me as I just can't stop yelling and swearing at poor LLM models when they keep repeatedly failing. I mean, why does prompting better never really seem an option worth considering 🤔 I've never sworn to a human colleague!

I can't believe I built not one but TWO native apps (iOS+macOS) in an evening for my clanker using pi-durable and my old clanker server. These have the same (remote) coding functionality than the ChatGPT apps -- except being lighter, and powered by Pi. What a time to be alive!

JS hippies ❤️

Claude: I recommend starting with steps 1 to 3. Me: Just do all the 20. Claude, in 25 minutes: All done. No matter how much I work with these, it still feels magical every time. Also, Opus 5.5 continues to be the Claude model I'd be waiting for so long 🙏

Sol 6.1 is such a bad model. It's hard to fathom how the tables turned so fast

Remember the times when we used scripts to concat a repo into one file that was easy to feed to a LLM conversation as context? And then Claude Code was released w API prices and no one saw the point bc "ls costs $0.1 - game over devs". What a ride!

Music-related LLM-tools are advancing fast in two oposite directions simultaneously; inspiring and exciting like here, but also to sad and heartbreaking (hello Suno)

Sol 6.1 working at 9 tok/s matches kind of well with its insufferable take on .. well, everything. It's so interesting that these models have similar quirks and rough edges like most brilliant developers do. And, learning to work w new ones every other week is equally taxing.

Pretty sure I've yet to have a conversation w Sol 6.1 that didn't include "FOR FUCKS SAKE". So far hands down the most annoying SOTA model to work with. ..but on a positive note, it's no longer 14 tok/s, the prommised 50% speedup seems to be legit. 28 tok/s ftw 🫠

Wired: seeing models select code mode in Pi for appropriate tasks and succeed so easily is *cheff's kiss* Tired: asking for code mode and realizing you're not in Pi bc Anthropic is still forcing you to use their shitty tools.