Comment by Amekedl

anyone who seriously attempted vibing an entire app something knows that after the oneshots it's always death by a thousand prompts:

Tweaking everything, because any agent/model can only "interpolate" so much "resolution and detail" out of your written prompt.

This isn't really a problem, this is the nature of work, and hence I feel this product only accomplishes two things:

1. users spending more on inference

2. creating busywork with less direction than other surfaces such as a IDE, which is hard to review and will often lack meaning.