I strong agree that if you are writing code by hand you can and should most certainly see what you can generate to aid you.
if your code is that important, why not create as much automation as possible around it for validation? Seems like a very simple argument.
Also I think its LLMs current best use case. Its what they are the best at right now. "I just got done doing 'mansplain what you did' and I want you to review it and tell me what I have missed, what could be a logic flaw."
Even that alone will surface 1 or 2 things I have done wrong almost with every single change I make.
Today we introduce OASIS 1. The smart ring built for private dictation. Whisper to write. Touch to edit. A first step beyond the keyboard toward a world where your intent follows you across every device. Order at https://t.co/gZieZw6vYJ first batch is limited.
How does this work technically? Well, I usually have a “project manager” thread pinned for each project I’m working on. It means the output (the PR) becomes almost the only thing that matters.