@fasterthanlimeamos I find that using LLMs for thinking about design is (surprisingly) useful. Giving enough context to the LLM makes the problem clear in my head. And they tend to produce really bad designs, but reflecting on *why* the design is bad helps me understand the problem better as well.
@tawhakiHenrique Pinto Yep, one of the top LLMs workflow is to keep giving them context until you're so pissed off at the output that you end up making all the decisions yourself.
I hear people have been doing that with humans for millennia.
If you have a fediverse account, you can quote this note from your own instance. Search https://hachyderm.io/users/fasterthanlime/statuses/115610824011539496 on your instance and quote it. (Note that quoting is not supported in Mastodon.)