> You just say, "Go Build me x - it should have y,z features - and build it in golang for me" - and that's it - the 3-4 page Plan comes back - usually pretty credible - and then you click "build.".
What you're describing seems like a workflow for building toys only. There's currently no reality in which someone would actually know what the y,z features are before making them. A plan generated in 5min would likely suggest a suboptimal solution compared to what a good solution would look like (which might take a year or two to figure out, for a human, so still a week or so for SOTA models if at all possible). Building something in golang is cute, but hard to be convinced until more novel applications are being generated from prompts.
The data submitted by Cursor's users tho, that seems to be very valuable.
I have this line completion feature in koieditor.com as well, and it's hard to suggest "safe"/good completions at a low latency. Best approach I could think of is a second pass to verify first pass, but adds to latency, or change to better model, which often also impacts latency.
I think this approach is more common than the hype for actual work. I do something similar, many back and forth, then settle on something often with now known tradeoffs, written by hand to spot issues as a final guard/ keep consistent naming etc.
No telemetry, no tracking, and much faster than Zed: https://koieditor.com/benchmarks/
Dev solely focused on performance and bug fixing.