The best kind of programming is not when you get a lot done, but when you painstakingly spend extra time to arrive at something so simple and elegant that it ironically looks effortless and not worthy of any special regard.
As I'm sitting here, on question 31 of a /grill-me prompt, having asked GPT 5.5 to "make db path configurable", I can't help but marvel at the endless void of pedantic decisions we devs have been expected to make daily. Hard to imagine a non-dev surviving a /grill-me session.
I scan and shred lots of docs (kids' schoolwork, mail, etc), so wanted a simple way to let AI at them. Vibed this up and been using it happily for a couple months now. Maybe useful to someone else. Contrib welcome! https://t.co/Y7CMGYCnoF
Tried to have AI read my posts and codify the style, then made several different LLMs try to write as me. The result is unfortunately beyond cringe. Weirdly, simpler models (e.g. Qwen 3.6-plus) came the closest, but it's still painful to read. Hard nope.
A new way to recognize AI-built web frontends: they're broken in Safari. As a Safari user, this is getting old fast. I thought AI should help cover more ground?
Using plannotator with pi lately (liking it so far). Wrote a seeds file for my Rails app.
Code review from Claude: "here're a couple of nits".
Code review from Codex: "you're about to break production, because you're doing db:prepare which also runs your seeds".
Using plannotator with pi lately (liking it so far). Wrote a seeds file for my Rails app.
Code review from Claude: "here're a couple of nits".
Code review from Codex: "you're about to break production, because you're doing db:prepare which also runs your seeds".
Many think that code is not the goal, working software is the goal, so you don’t need to read code, but I hard disagree. Imo code is the only solid ground we have in all of this non-determinism. AI should produce great code first and foremost, and useful software second.
Also note that if you are doing good work with automatic programming, you likely can find a proxy on the number of lines of code of the project: the more lines of code compared to the actual output, the worse. 6k lines of code can be reviewed, 100k? I don't think so.
Something's missing in these gstack-style approaches to AI. Why reupload millions of tokens of its own slop back into it? It's in there already. All it needs is what it doesn't have: your data, and some steering to apply its knowledge according to your preferences.
Use pi too.
@cooperx86 One thing about LG is that sometimes their firmware is shit, but gets fixed later. I got the LG ultragear 5k2k OLED purely for gaming, and it had this awful habit of failing to turn on randomly, but after updates, been solid. At least there’s hope.
@jnunemaker Controversial thought. Optimize all workflows for one screen. 14” on the go, plugged in to 1 screen at home (laptop open, tucked behind ext display, brightness off). But I’ve been optimizing for this for many years.
@cooperx86 That’s a superpower. I’ve always been ok with sleeping itself, but could never bring myself to bed on time, so end up chronically with 5-6 hour nights, because kids have school.