[dvt]

To me, this is a cute toy, but I highly doubt the AI can generate anything actually useful. Plus, I already have a code editor open, so context-switching to the browser to do "coding" feels a bit non-ergonomic.

I'd also like to see what the failure state looks like ("no, AI, not like that") because that's the main pain point when using tools like Copilot. The amount of time spent tweaking the AI prompt (or multi-shot re-prompting) ends up being comparable to just writing the thing yourself.

Like @IceDane and @ssijak, I'm also a bit shocked at what YC is funding these days.

[solias99]

I'll chime in with my personal experience: I spend about 50-60% of my time in GPT-4 just pasting code, prompting for what I want and then pasting it back into my code editor.

If this is my workflow most of the time, then surely this can be more streamlined. The way to streamline it would be:

1. Can I tell GPT-4 about my components (and always be up to date)

2. Can I ask GPT-4 to write to the file directly

3. If the output has an error, can I ask GPT to look at the compile time error and auto fix it?

The 3 things I mentioned above is something I do every single day. We're just looking to make it easier.

[jondwillis]

Cursor.sh, Continue, and (probably? i dunno) Copilot do those things well.