Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Could someone list the relevant papers on parrot vs. non-parrot? I would love to read more about this.

I generally lean toward the "parrot" perspective (mostly to avoid getting called an idiot by smarter people). But every now and then, an LLM surprises me.

I've been designing a moderately complex auto-battler game for a few months, with detailed design docs and working code. Until recently, I used agents to simulate players, and the game seemed well-balanced. But when I playtested it myself, it wasn’t fun—mainly due to poor pacing.

I go back to my LLM chat and just say, "I play tested the game, but there's a big problem - do you see it?" And, the LLM writes back, "The pacing is bad - here are the top 5 things you need to change and how to change it." And, it lists a bunch of things, I change the code, and playtest it again. And, it became fun.

How did it know that pacing was the core issue, despite thousands of lines of code and dozens of design pages?



I would assume because pacing is a critical issue in most forms of temporal art that does story telling. It’s written about constantly for video games, movies and music. Connect that probability to the subject matter and it gives a great impression of a “reasoned” answer when it didn’t reason at all just connected a likelihood based off its training data.


idk this is all irrelevant due to the huge data used in training...

I mean, what you think is "something new" is most likely to be something already discussed somewhere in the internet.

also, humans (including postdocs and professors) don't use THAT much data + watts for "training" to get "intelligent reasoning"


But there are many, many things that suck about my game. When I asked it the question, I just assumed it would pick out some of the obvious things.

Anyway, your reasoning makes sense, and I'll accept it. But, my homo sapien brain is hardwired to see the 'magic'.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: