Not only do I type faster than I speak I'm also able to edit as I go along, correcting any mistakes or things I've stumbled over and can make clearer. Half my experience of using even basic voice assistants is starting to ask for something and then going "ugh, no cancel" because I stumbled over part of a sentence and I know I'll end up with some utter nonsense in my todo list.

I know what you mean. This new generation of speech recognition is different though. It's able to understand fairly technical terms, specialized product names and other stuff that previously would have been garbled text.

Even if it gets slightly garbled, I often will add a note in my context that I'm using speech recognition. Then Claude will handle the potentially garbled or unclear sections perfectly or ask follow-up questions if it's unclear.

Haha yeah, it does feel a bit weird.

I often work on large, complicated projects that span the whole codebase and multiple micro services. So it's often a blend of engineering, architectural, and product priorities. I can end up talking for paragraphs or multiple pages to fully explain the context. Then Claude typically has follow-up questions, things that aren't clear, or issues that I didn't catch.

Honestly, I just get sick of typing out "dissertations" every time. It's easier just to have a conversation, save it to a file, and then use that as context to start a new thread and do the work.