Post #3110176
2026-02-27 21:02 UTC
@hugo@social.treehouse.systems most vibe coders are not reviewing the code. If they're at all concerned about quality they're having other models review it. I suspect this puts upper bounds on what they can build, even ignoring quality. But, a theme that comes up a lot when people talk about it is "trust" and how much code one can write with LLMs is determined by how much trust you can put in them.
I don't trust them all that much, but I can still offload a lot of boring stuff.
Replies (1)
-
@hugo@social.treehouse.systems 2026-02-27 21:25
@swelljoe@mas.to and that's the thrust of it, right? You either decrease your engagement with and understanding of the code, or you still bottleneck on that engagement (review). And you can juice "output" by dropping the review requirement in the report that's supposed to show "productivity gains," and then backpedal it with loading up more review and human engagement on the other report that's put out to try to counter the drop in quality from the first method.