[steve_adams_86]

You're touching on something I've been thinking about a lot lately. There's this notion that LLMs only increase volume and there's an inevitable intrinsic decline in quality. In reality, it's more like an amplifier as you mentioned; people interested in good engineering can iterate more deeply and focus more intently on specific problems than they could, and they aren't inherently forced to output more garbage.

It's one of the ways in which I find people overwhelmingly misunderstand how LLMs will impact our field. The glut of awful garbage is no different from when people started selling startup 'starter packs' and such; it's just even more accessible and more widespread. There's still no easy or immediate replacement for curiosity, a need for quality, domain knowledge, etc.

I agree that the Deno team exemplifies that and it's why I trust their work for my own work.