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.
@samsaffron@OpenRouter True, but I’ve used expensive models (kimi k3) on go, and even with overuse, I think it’s slightly cheaper to exhaust go first vs going straight api. There might be some math behind which model is more efficient to exhaust go with however, not sure.
Opus just wrote me a script without using any of my coding, docs, and review procedures. I asked why, it said "I treated them as optional, even though it says _always_". This is in Claude Code. I don't think it ever did that in Pi via API. 🤔
Just loaded up my "dot" with a bunch of chores that I never got to tackle before. Let's see how it goes. The cool thing about a managed product is that I don't have to think about software updates and memory management.
@nateberkopec Try writing more subjective linters. I setup “rubocop-personal” as a global command outside of any repo. Its goal is not to enforce common rules, rather “program like I wrote it myself” rules. No additional instructions except “run it when writing ruby”.
Technical barriers are lowering now, so app-only businesses are losing value prop. However, there are still physical world, red tape, legal, regulatory barriers. If your business reaches into that, it is more likely to remain standing.
I wonder if the same people who never read code also never read their agent skills and configs, and end up with bigger and bigger mess that probably works worse than if they just removed all of it.
@garybernhardt I have similar feelings but still have to fight it because of 80/20 rule. You can’t entirely skip them, but you can’t entirely rely on them either. The answer is somewhere in between.
5% AI failure rate can feel worse than 20% human one. I think it's because the failures don't overlap.
For humans it feels extra super bad to see an AI fail where you wouldn't have.
Extra super duper bad when talking about self-driving cars.
Adding features (and complexity) makes your program less appealing, not more.
Software systems exist to solve a problem. Anything that's not laser-focused on the solution is an annoyance, and building that cruft is worse than money down a hole. It can lose us customers.
AI, when used in the six-month's-work-in-a-week feature-factory mode, adds nothing but undesirable features and complexity. Just sayin'.
One of the biggest insights I've picked up later in life: everything you own owns you back. It takes maintenance, and mental space. The more complex and obscure it is, the more it owns you. This is just as true of the software we build, especially now.
@garybernhardt One thing to check, make sure you don’t have skills that say “only do strictly minimal change and nothing else”. A bunch of skills floating out there (like karparthy) say that, I wonder if that’s part of the issue.
I don't want to build a million things with AI, because I'm not a solutions hoarder. I've grown to resist the urge to solve all perceived problems, because only a few of them are real, and almost never what they seem at first. Clutter taxes my mental well being.
"Stop bottlenecking development by reading code" say people who work on fun/convenience utilities and games. "We must review code" say people who work on finance, medical, low-level infra. Why so godddamn polarized? Read SOME code, use the right amount of due diligence per task.