I love AI training when it's like...
"AI can make mistakes and introduce security bugs..." yeah, cuz it's trained to do what people have already done.
"AI can count things wrong sometimes..." yeah, cuz it's trained on humans and they do that too.
"AI can... " yeah, it's trained on human data. It will do the same stupid things, we have to mitigate its mistakes just like we've mitigated our own mistakes. Use it as the tool that it is.
Why do folks keep treating LLMs like they're supposed to be deterministicly perfect like a deterministic app. Cut it out. Come on y'all, cut it out. Stop treating it human, get the movie tropes and ideas out of your mind, and strop attributing LLMs (and other AI *things*) these characteristics.
