You’re missing the point by bike shedding on “100x”
It’s probably higher tbh because there’s things I prototyped to test an assumption on, realized it was O(N^2) then dumped it and tried 4 more architecture simulations to get to one that was implementable with existing tool chains I know
So you’re doing exactly what i called out which is evaluating it as a magic oracle instead of what I said which is that it makes me personally something like 100x more productive as a support tool, which often means quickly ruling out bad ideas
Preventing a problem in architecture is worth way more than 100x
If what you meant by 100x more productive is that sometimes for very some specific things it made you 100x more productive, and that isn’t applicable to software development in general, I can see that.
I have many times delivered a year of value in a few days by figuring out that we didn’t actually need to build something instead of just building exactly what someone asked for.
>I have many times delivered a year of value in a few days by figuring out that we didn’t actually need to build something instead of just building exactly what someone asked for.
Knowing what not to do more of a superpower than knowing what to do - cause it’s possible to know
You can prototype by hand too. Personally I find it might take me 10 min to try a change with an LLM that would have taken me 30 min to 1hr by hand. It's a very nice gain but given the other things to do that aren't sped up by LLM all that much (thinking about the options, communicating with the team), it's not _that_ crazy.