They don’t seem to realize that doing vibe coding requires enough information to get the vibes.
There are no vibes in “I am looking at files and searching for things” so I have zero weight to assign to your decision quality up until the point where it tells me the evals passed at 100%.
Your agent is not good enough. I trust it like I trust a toddler not to fall into a swimming pool. It’s not trying to, but enough time around the pool and it is going to happen, so I am watching the whole time, and I might even let it fall in if I think it can get itself out.
the definition of vibe coding is that you never check what it's doing, you only check its output; eg the actual website/feature you're having it build.
I could accept that definition, but really that seems less like vibe coding and more like just not coding. Vibe coding for me is more like: yeah this doesn’t look insane and you got the interface from the right git repo. Like I wouldn’t put my name on it at work and defend it in a code review but I also didn’t just push the button and hope.
There are no vibes in “I am looking at files and searching for things” so I have zero weight to assign to your decision quality up until the point where it tells me the evals passed at 100%.
Your agent is not good enough. I trust it like I trust a toddler not to fall into a swimming pool. It’s not trying to, but enough time around the pool and it is going to happen, so I am watching the whole time, and I might even let it fall in if I think it can get itself out.