What works nice also is the text to speech. I find it easier and faster to give more context by talking rather than typing, and the extra content helps the AI to do its job.

And even though the speech recognition fails a lot on some of the technical terms or weirdly named packages, software, etc, it still does a good job overall (if I don’t feel like correcting the wrong stuff).

It’s great and has become somewhat of a party trick at work. Some people don’t even use AI to code that often, and when I show them “hey have you tried this?” And just tell the computer what I want? Most folks are blown away.

Does the Cursor have text-to-speech functionality?

you mean speech to text right?

Not for me. I first ask Advanced Voice to read me some code and have Siri listen and email it to an API I wrote which uses Claude to estimate the best cloud provider to run that code based on its requirements and then a n8n script deploys it and send me the results via twilio.

Sorry! Yes, speech to text.

My point was that a prompt that simple could be held and executed very well by sonnet, but all other models (especially reasoning models) crash and burn.

It's a 15 line tsx file so context shouldn't be an issue.

Makes me wonder if reasoning models are really proper models for coding in existing codebases

Your last point matches what I’ve seen some people (simonw?) say they’re doing currently: using aider to work with two models—one reasoning model as an architect, and one standard LLM as the actual coder. Surprisingly, the results seem pretty good vs. putting everything on one model.

This is probably the right way to think about it. O1-pro is an absolute monster when it comes to architecture. It is staggering the breadth and depth that it sees. Ask it to actually implement though, and it trips over its shoelaces almost immediately.

Can you give an example of this monstrous capability you speak of? What have you used it for professionally w.r.t. architecture.

The biggest delta over regular o1 that I've seen is asking it to make a PRD of an app that I define as a stream-of-consciousness with bullet points.

It's fantastic at finding needles in the haystack, so the contradictions are nonexistent. In other words, it seems to identify which objects would interrelate and builds around those nodes, where o1 seems to think more in "columns."

To sum it up, where o1 feels like "5 human minute thinking," o1-pro feels like "1 human hour thinking"

Yes this works good for me too rather take your time and do the first prompt right

If have to write a prompt that long, it'll be faster to just write the code.

Shocking to see this because this was essentially the reason most of the previous no code solutions never took off...

That sounds exhausting. Wouldn't it be faster to include you package.json in the context?

I sometimes do this (using Cline), plus create a .cline file at project root which I refine over time and which describes both the high level project overview, details of the stack I'm using, and technical details I want each prompt to follow.

Then each actual prompt can be quite short: read files x, y, and z, and make the following changes... where I keep the changes concise and logically connected - basically what I might do for a single pull request.

You’re basically saying you write 15x the prompt for the same result they get with sonnet.