[sarmadgulzar]

Can relate. I've also shifted towards generating small snippets of code using LLMs, giving them a glance, and asking to write unit tests for them. And then I review the unit tests carefully. But integrating the snippets together into the bigger system, I always do that myself. LLMs can do it sometimes but when it becomes big enough that it can't fit into the context window, then it's a real issue because now LLMs doesn't know what's going on and neither do you. So, I'll advise you to use LLMs to generate tedious bits of code but you must have the overall architecture committed into your memory as well so that when AI messes up, at least you have some clue about how to fix it.

[causal]

What's it called when you choose a task because it's easy, even if it's not what you need to do at all? I think that's what LLMs have activated in a lot of us: writing code used to be kinda hard, but now it's super easy, so let's just write more code.

The hard parts of engineering have always been decision making, socializing, and validating ideas against cold hard reality. But writing code just got easier so let's do that instead.

Prior to LLMs writing 10 lines of code might have been a really productive day, especially if we were able to thoughtfully avoid writing 1,000 unnecessary lines. LLMs do not change this.

[Velorivox]

I'm not sure if there's a name for that specifically, but it seems strongly related to the streetlight effect. [0]

[0] https://en.wikipedia.org/wiki/Streetlight_effect