I think a bit differently. The real problem with vibe coding is that it's hard to write a precise specification of the problem. But if the specification is accurate, running the AI dozens of times tends to make it much faster than a human (purely from experience). However, for most problems where vibe coding is actually useful, a human still has to set the initial framing.

"Vibe coded" and "supposed a lot faster than the competition" is becoming a smell to me. LLMs have a demonstrated capability to benchmarkmaxx that is even greater than human's already substantial capabilities to do so.

I'm not saying this isn't possible, I'm saying I'd wait a bit before I got too excited. That it seems to have held up to some other commenter's testing which was presumably not in the benchmark is an interesting sign, as a lot of time benchmarkmaxxed code falls over dead the instant you give it anything not in the benchmark. But I've still seen a whole bunch of projects "X times faster than what we told the AI to copy" that were less than met the eye to jump immediately to this must be awesome without more people trying it out seriously.