Hacker News Reader

Comment by arkensaw | Hacker News Reader

It's worse than that, someone else generated it using and then put it on a static page. We just have to take their word for it that GPT6 can do this. It probably can. It's not really an impressive test anymore. Claude Fable can do it. Opus can do it. I've been making one-shotted games with models for a while now, to test out their capabilities, and they all pretty much come out like this - generic bland and basic, using three.js with rudimentary controls and zero gameplay other than collecting points.

Here's a one-shotted submarine game I made with Fable a few weeks back - https://roryok.com/games/deepdive3d.html. One prompt, and I think it's deeper than this (if you'll pardon the pun)

View on HN

Interesting concept, but the controls disappeared after a few seconds and I still hadn't read all of them

well, its a one prompt POS so I'm not surprised

I love your game. It's wonderful and exactly the sort of thing that would showcase something interesting as opposed to just copying what's already out there. It is something I could share with my kids, and exactly the right note of fun and exploratory in a unique and even natural way. It could be extended and played with.

I usually roll my eyes when I see a comment like this because rarely do they make the points they claim to make, but I see what you're getting at. They just chose to clone someone elses work and do it in a boring way. I like OpenAI's models a lot, but they should do better.

edit - just a sidenote that I hadn't looked at the games, I just took the comment about "super-mario cart" at face value. I stand by my points 110% (even moreso perhaps), what they're showing is more polished than I expected, I assume they spent a lot of tokens on it. It is a legit shame they couldn't have spent time thinking of a better idea to illustrate something just as polished, but more interesting.

You sound like an AI.

Funny since no, but I really did like it and for those reasons. Don’t see a lot of post first comment edits anymore, so I’ve got that going for me.

Thanks. But even my game is a piece of shit. It shows LLMs can make a working 3d world start to finish from a single prompt, but with no soul. I wasn't excited to play it anymore than I was excited to play the shitty mariokart clone (that you don't even need to turn for)

LLMs produce games that look right but feel all wrong, because they're generalising and imitating. This is also why AI video tools can make an astonishingly authentic looking "GTA 5-but in Roman Times" or whatever, but they couldn't conjure up anything original. Only imitations of what people have already thought up.

By their very nature, they predict from a large set of data what the most likely thing is, and as humans, we crave the less likely thing.

My submarine game is generic tripe. Sure, it checks the boxes of what I asked for. You explore an undersea world in a tiny sub. Hooray. LLMs can build this kind of thing that nobody wants to play in minutes. But if you asked LLMs to make a thousand different undersea games you'd never get Dave The Diver, or Barotrauma, or Subnautica, or Sunless Sea, or Aquanox. You'd just get something that looks like it was released for Kinect but never charted.

Reply on news.ycombinator.com