← Back to context

Comment by mrkurt

6 days ago

PLEASE write your response. We'll publish it on the Fly.io blog. Unedited. If you want.

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?