I vibe code quite a bit and will plow through a lot of front end code despite being a backend engineer. In my case, it's on personal projects where I'm ambitious and asking the LLM to "replace an entire SaaS" sort of thing. At work most of the code is a couple lines here or there and trivial to review.
When I try the more complex things I will do multiple passes with AI, have 2-3 LLMs review it and delete deprecated code, refactor, interrogate it and ask it to fix bad patterns, etc. In an evening I can refactor a large code base this way. For example Gemini is meh compared to Claude Opus at new code, but somewhat decent for reviewing code that's already there, since the 1M context window allows it to tie things together Claude wouldn't be able to fit in 256k. I might then bounce a suggestion back from Gemini -> Claude -> Grok to fix something. It's kind of like managing a team of interns with different specialties and personalities.
When I try the more complex things I will do multiple passes with AI, have 2-3 LLMs review it and delete deprecated code, refactor, interrogate it and ask it to fix bad patterns, etc. In an evening I can refactor a large code base this way. For example Gemini is meh compared to Claude Opus at new code, but somewhat decent for reviewing code that's already there, since the 1M context window allows it to tie things together Claude wouldn't be able to fit in 256k. I might then bounce a suggestion back from Gemini -> Claude -> Grok to fix something. It's kind of like managing a team of interns with different specialties and personalities.