That's not a "fatal" flaw. It just means you have to manually review every output. It can still save you time and still be useful. It's just that vibe coding is stupid for anything that might ever touch production.
LLMs are ridiculously useful for tasks where false positives (and false negatives) are acceptable but where true positive are valuable.
I've gotten a lot of mileage with prompts like "find bugs in [file contents]" in my own side projects (using a CoT model; before, and in addition to, writing tests). It's also fairly useful for info search (as long as you fact-check afterwards).
Last weekend, I've also had o4-mini-high try for fun to make sense & find vulns in a Nintendo 3DS kernel function that I've reverse-engineered long ago but that is rife with stack location reuse. Turns out, it actually found a real 0day that I failed to spot, and which would have been worth multiple thousands dollars before 2021 when Nintendo still cared about security on the 3DS.
See also: https://www.theregister.com/2025/04/21/ai_models_can_generat...