I largely agree. As a counterpoint, today I delivered a significant PR that was accepted easily by the lead dev with the following approach:

1. Create a branch and vibe code a solution until it works (I'm using codex cli)

2. Open new PR and slowly write the real PR myself using the vibe code as a reference, but cross referencing against existing code.

This involved a fair few concepts that were new to me, but had precedent in the existing code. Overall I think my solution was delivered faster and of at least the same quality as if I'd written it all by hand.

I think its disrespectful to PR a solution you don't understand yourself. But this process feels similar to my previous non-AI assisted approach where I would often code spaghetti until the feature worked, and then start again and do it 'properly' once I knew the rough shape of the solution

The best way I’ve found to use LLM’s for writing anything that matters is, after feeding it the right context, take its output and then retype it in your own words. Then the LLM has helped capture your brain dump and organize it but by forcing yourself to write it rather than copy and paste… you get to make it your own. This technique has worked quite well with domains I’m not the best at yet like marketing copy. I want my shit to have my own voice but I’m not sure what to cover… so let the LLM help me with what to cover and then I can rewrite its work.