Flappy Bird is a well-known game by now, and it's simple enough that lots of people have produced tutorials online about how to write it. My guess is that it's mostly regurgitating code out of its training corpus.
It'd only be impressive if you asked it to create a novel game of similar complexity and it was also able to do that successfully.
Flappy bird is more complicated than pong, and GPT4 apparently did it in 'one shot'. I think there's improvement being made, even if it's not as impressive as you'd like it to be.
I don't know about that. Check out the other GPT-related thread on the front page right now. GPT-4 fails to solve programming problems that are much simpler than writing a whole game (even a relatively simple one). https://news.ycombinator.com/item?id=35193188
It's really not impressive to me. Humans are gullible and want to anthropomorphize computers. Every time someone claims a LLM like GPT-* can do something apparently amazing, we're seeing the ELIZA effect (https://en.wikipedia.org/wiki/ELIZA_effect) in action.
That's not what I'm saying. I'm not saying you should find it impressive or amazing. What I am saying is that things are visibly progressing (before: badly written pong, today: successful flappy bird clone), regardless of how impressive one finds it.
Of course, it's not an apples-to-apples comparison. But I don't have access to GPT4, so I can't check how it does on Pong written in PyGame.
>Any software developer can access GitHub and StackOverflow - can they do it in a single shot as quickly as GPT?
I think the answer to this question is yes? If the developer can find a working example that they can copy paste (which is what GP is saying GPT-4 is essentially doing).
It’s actually just as likely for GPT-4 to have pasted a broken code example than a working one; it doesn’t understand if the code is correct.
Bout to throw in the towel on this whole software developer career thing. Guess I'll go be a plumber or something. Maybe have GPT tutor me there too while I'm at an apprentice level.
GPT4 is impressive but all this is hype. It recreated it because some one else created it previously. Its not like it created a new game from scratch !
11 comments
[ 2.9 ms ] story [ 43.1 ms ] threadIt'd only be impressive if you asked it to create a novel game of similar complexity and it was also able to do that successfully.
Flappy bird is more complicated than pong, and GPT4 apparently did it in 'one shot'. I think there's improvement being made, even if it's not as impressive as you'd like it to be.
It's really not impressive to me. Humans are gullible and want to anthropomorphize computers. Every time someone claims a LLM like GPT-* can do something apparently amazing, we're seeing the ELIZA effect (https://en.wikipedia.org/wiki/ELIZA_effect) in action.
Of course, it's not an apples-to-apples comparison. But I don't have access to GPT4, so I can't check how it does on Pong written in PyGame.
So the more versions of Flappy Bird are online, the easier for ChatGPT to generate something that works. Difficulty of problem doesn't matter.
I'm amazed how much resistance there is to one of the biggest technological advancements in history. And this is JUST getting started.
I think the answer to this question is yes? If the developer can find a working example that they can copy paste (which is what GP is saying GPT-4 is essentially doing).
It’s actually just as likely for GPT-4 to have pasted a broken code example than a working one; it doesn’t understand if the code is correct.
Sounds familiar