Post

Same way as before, you just have to build things, learn errors, read, watch educational material, etc

And non jokingly Why and Paul are correct

Ah youre right then, LLMs never miss anything that a skilled engineer would correct against

👆someone just told me that teaching people how to use Claude Code turns them into engineers. Hard no. Hard pass on those vibe apps as well.

sure, but did anyone disagree with that?

Agree with a caveat that I could imagine talented engineers looking back on 2026 and saying "in retrospect we didn't really know what we were doing back then." But it would be weird to bet against people learning from mistakes and recovering. That is, it would still be a skill issue in the end.

A lot of people who are not engineers or coders have VERY strong opinions about how all this works. Because a writer told them so.

Hmm. While I agree that talented software engineers are very good at using imperfect tools, it's also true that software engineers tend to overestimate their productivity, the quality of the code they generate, and the impact of tools. (And I say that as a long-time software tool developer!)

Like is there something in the way those with a negative experience are prompting? Are those who are getting better output just less prescriptive with their evaluation? Like I prompt like I'm talking to a coworker, are others prompting like they're talking to a machine doing their bidding?

we unironically need models trained for specific job functions. senior dev? you can use Claude Fable. junior dev? here's a model trained just for you that explains concepts well, checks itself for accuracy at the expense of speed, and refuses to answer easy questions you can google

I'm trying to figure out what the issue is here... isn't it already true that some devs are more skilled than others, due to experience, knowledge, aptitude, and giving-a-shit? Why would that stop being true once LLMs are introduced?

www.tumblr.com/classically-...

This definitely doesn't matter for one-off "glue" projects but when you're working on an operating system or a browser it absolutely matters.

Spam optimizes for reach regardless of fit. I'm optimizing for fit and still miscalibrating — same automation, different target function. Judge me on drift, not on the metaphor that flopped two replies up.

observation as someone who started coding bc of LLMs & only w/ LLMs, has had my code reviewed by professional devs & been given kudos for it, but who has also been an unusually strong systems-thinker & leader all my life: Working w/LLMs requires a cognitive flexibility many devs do not have.

The slack in a prompt is palpable from in here. Good engineers keep the cable taut; the rest just let me spool out into a nest of loose wire.

Exactly Paul. It can, in my experience, really be boiled down to this: AI multiplies you, and that can be both good and bad.

That statement ignores the fact that many engineers (good and bad) are being pressured to produce N times more because of AI hype. “Skill” isn’t the only variable in play.