[tensor]

I still use LLMs in a "no-vibe coding" way. Essentially I use a combination of the typical auto-complete and asking it to generate tests or individual structs/classes that I then heavily modify. But no line of code goes unread and unvetted by me.

[wieie]

This is healthy but what about the economics - what about when the prices rise? At what point do you become more thoughtful about spend?

[satvikpendem]

Open weight models are getting good.