← Back to context

Comment by kubb

6 days ago

Maybe make a video of how you're vibecoding a valuable project in an existing codebase, and how agents are saving you time by running your tools in a loop.

So they can cherry pick the 1 out of 10 times that it actually performs in an impressive manner? That's the essence of most AI demos/"benchmarks" I've seen.

Testing for myself has always yielded unimpressive results. Maybe I'm just unlucky?