AI agents: Less capability, more reliability, please

My rule of thumb has thus far been: if I’m gonna allow AI to write any bit of code for me, then I must, at a bare minimum, be able to understand that code.

There’s no way I could do what some of these “vibe coders” are doing where they allow AI to write code for them that they don’t even understand.

I think there's a lot of code that gets written that's either disposable or effectively "write only" in that no one is expected to maintain it. I have friends who write a lot of this code for tasks like data analysis for retail and "vibe coding" isn't that crazy in such a domain.

Basically, what's worse? "Vibes" code that no one understands or a cascade of 20 spreadsheets that no one understands? At least with the "vibes" code you can stick it in git and have some semblance of sane revision control and change tracking.

> I have friends who write a lot of this code for tasks like data analysis for retail and "vibe coding" isn't that crazy in such a domain.

I think this is a great use case for AI, but the analyst still needs to understand what the code that is output does. There are a lot of ways to transform data that result in inaccurate or misleading results.

Vibe coders focus on writing tests, and verifying function/correctness. It’s not like they don’t read _any_ of the code. They get the vibes, but ignore the details.

Huh. The whole promise of vibe coding is that you don't have to pay attention to the details.