Hacker News Reader

In your analysis, do you account for the time taken to type a detailed specification with which to prompt the LLM?

Or the time to review the code - whether by manual fixes, or iterating with the prompt, or both?

No, just the time spent typing the code.

I'm sure curiousity will get the better of me eventually, but as it stands I'm still unconvinced. Over the years I've ingrained a strong sense that just fixing things myself is easier than clearly explaining in text what needs to be done.

Time to first iteration is a huge metric that no one is tracking.

Could you explain this please?

Reply on news.ycombinator.com