More specifically, what he's saying is that in his experience so far the AI generated code is just as buggy as human generated code. Which seems perfectly reasonable to me. The point is that all code needs to be carefully reviewed.
The problem with vibe coding is that people who know nothing about coding get an AI to output code that they can't even read, let alone debug. Then they throw it straight into production. Using AI to quickly output blocks of code for software that is being designed, assembled and reviewed by an experienced programmer, using proper review and testing processes, is a very different beast.
Obviously if you regard any use of LLMs as immoral then it doesn't matter. But if that's why people are unhappy about this then they need to say so. If their concern is actually with the results, not some broader immorality of the process, then the dev is absolutely right; they need to actually look at the results.