Don’t even need to make it about code. I once asked what a term meant in a page full of a certain well known FOSS application’s benchmarks page. It gave me a lot of garbage that was unrelated because it made an assumption about the term, exactly the assumption I was trying to avoid. I try to deviate it away from that, and it fails to say anything coherent and then loops back and gives that initial attempt as the answer again. I was stuck unable from stopping it from hallucinating.
How? Why?
Basically, it was information you could only find by looking at the github code, and it was pretty straightforward - but the LLM sees “benchmark” and it must therefore make a bajillion assumptions.
Even if asked not to.
I have a conclusion to make. It does do the code thing too, and it is directly related. Once asked about a library, and it found a post where someone was ASKING if XYZ was what a piece of code was for - and it gave it out as if it was the answer. It wasn’t. And this is the root of the problem:
AI’s never say “I don’t know”.
It must ALWAYS know. It must ALWAYS assume something, anything, because not knowing is a crime and it won’t commit it.
And that makes them shit.
That one is a special case. Yes, it got completely annihilated in numbers by even the goose goose duck clone, but, the thing is, the majority of its userbase just started playing on Mobile (where the game is free) well before the game left its popularity peak. So, the steam numbers are hardly representative of its playerbase, and the app’s download count shows it.
PUBG did not have a similar story at the time of its release, but does right now. It’s one of the most played games in the world… On chinese phones, so, uh, kind of invisible depending where we’re looking for. To put it into perspective: PUBG straight up dethroned the biggest, most profitable shooter in the world Crossfire, by splitting the population, and the takeaway there most people would have is “What the hell is a Crossfire???”.