The "confident idiot" problem: Why AI needs hard rules, not vibe checks

I’ve found after about 3 prompts to edit an image with Gemini, it will respond randomly with an entirely new image. Another quirk is it will respond “here’s the image with those edits” with no edits made. It’s like a toaster that will catch on fire every eighth or ninth time.

I am not sure how to mitigate this behavior. I think maybe an LLM as a judge step with vision to evaluate the output before passing it on to the poor user.