douglaswlance

doesnt work with multiple monitors

you get better models with more compute.

its not just PoW at inference. It's PoW of inference + training.

does it input the text as soon as it hears it? or does it wait until the end?

unless someone shows their threads of prompts or an unedited stream of them working, it's pointless to put any weight into their opinions.

this is such an individualized technology that two people at the same starting point two years ago, could've developed wildly different workflows.

pay for another account to double your limit.

react nataive gets some design refreshes for free. its native.

Typing isn't what makes programming fun.

AI coding preserves flow more than legacy coding. You never have to go read documentation for an hour. You can continuously code.