[furyofantares]

There was a snarky comment earlier saying, try implementing something that's too hard for you, THEN try going back to writing code by hand - implying agents are indispensable.

And I thought to myself that the most memorable parts of my career, the most rewarding parts, were when I took some task that was too hard for me, then, with great effort, became a developer for whom that task was no longer too hard for me.

[CuriouslyC]

All the times I told someone I could do something I didn't know how to do but believed was possible then had to figure it out filled me with existential dread. There was a good feeling after I succeeded, but I get a good feeling from just building something big and functional with AI, as long as I feel like I was the driving force behind the ideas in the thing, so maybe I don't need the stress?

[bitwize]

That kind of stress is how you grow. It's good for you. None of that stress means no growth.

[CuriouslyC]

There's an inverted U curve with stress benefit, and I think you can still find the optimum by reaching higher on the shoulders of giants.

[bitwize]

Newton studied his forebears and understood their findings before contributing his own. He was stressed with the knowledge of his own ignorance, but then he learned and set himself up to make more profound discoveries. That's what it means to "stand on the shoulders of giants". Not to be a perpetual idea guy, outsource the hard part to someone else's computer with little to no effort or learning on your part, and roll on HN like "bitches mad 'cause I found the royal road to geometry".

[furyofantares]

Yeah, but LLMs are not giants in terms of capabilities (depth). They are medium sized at best, despite being superhuman in other ways (breadth, speed).

You can use these to help you learn but, at least if you're a developer, letting it stunt your growth seems like a mistake.