Web dev (Python, Django, TypeScript, Vue), Founder, DJ. Working on https://teapawt.net/t.co/0Pk9gSmdKw
Turku, Finland
Joined January 2008
- Tweets3.1K
- Following499
- Followers438
- Likes2.2K
Pinned Tweet
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 😅
My existential dread over AI overlords lessen considerably when OpenAI APIs are responding at 14 tok/s
Sol "AGI" 6.1
Me: any code updates needed from our side after changing the perms?
Sol: no, except the checklist. Just reconnect the app.
Me: so yes or no?
Sol: no code changes needed.
Me: even in front?
Sol: front needs to be updated, same as the backend permission list.
💀
I'm guessing hands down the biggest percentage of total work time in this process was me thinking and typing. A person who understands the product can most likely see almost instantly if the issue is valid or not, rest is just process details (like coding guidelines etc).
The initial fix from the bot came so fast that I didn't even realize it myself until today when I saw it was already merged!
I'm testing out a similar process for @slipmatio where users can submit bug reports directly from the app UI, and then a bot takes over.
The @astrodotbuild LLM factory works great. Found a bug, clanker wrote a simple repro + short description, I then (manually) filed a ticket. Their bot wrote a fix in ~20 mins. Few days later, after @matthewcp approved the changes, fix was merged in ~3 h.
github.com/withastro/astro/i…
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!
Claude refuses a prompt to add "invisible comments" to documentation (to make it understand the context properly wo messing up the user instructions) but happily adds "code comments" 🤦♂️
Meta, apparently, doesn't have issues w Claude models 😅
redact.dev/blog/whatsapp-hel…
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!
ALT Native pi-durable powered iOS app connected to my Mac
ALT Native macOS app powered by pi-durable
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 🙏
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)
Teaching Sol to write.
Iteration 1:
"Use stable documentation entry points or local source references for durable guidance. Version-pinned release/tutorial URLs belong only in explicitly scoped research citations, not evergreen instructions."
Final text (by me, I gave up):
"Don’t use version-specific links as references in comments or documentation."
#notquiteagi