[feastingonslop]

LLMs write superior code. Maybe they learned from humans, but they have seen further while standing on those shoulders.

[lelanthran]

> LLMs write superior code.

How would they know what superior code is? They're trained on all code. My expectation and experience has been that they write median code in the best-case scenario (small greenfields projects, deeply specified, etc).

[yoyohello13]

The AI maximalist are really out in force in this thread.

[pinkgolem]

Then you have access to better models then I do (4.6/5.3)

The code is mostly not bad, but most programmers i have worked with write far better code.