21–30 of 64 posts
I wonder if you paired a few different types of AI together, an LLM agent might be good at strategizing -. E.g. building a strategy on how to handle a scenario. But, it would need to know the entire game manual basically. Then it would pass the stratrgy to a better AI in some way. But it might not be needed if the better gaming AI can just do that part too already. I admit I know nothing about this though.
Choose another “AI” technology and give another go.
There was good progress in training neural networks to play video games. Unfortunately it doesn't seem to fit in some people's context because it was a few years ago. Kind reminder: there is "AI" beyond LLMs.
> This brings us to what seems like a contradiction. LLMs are bad at playing games. Yet at the same time, they’re improving rapidly at coding, a skill set that can be used to create a game. How do these facts fit together? > Togelius: It’s super weird. ...No, it's really not. They're language models. Code is a language. "Playing a game well" is not. One can, hypothetically, encode game inputs in such a way that it se…
Yet LLMs can play chess and have a "mental" representation of the chessboard. If LLMs get better but do not progress at playing games when not specifically trained on it it seems to point to a generalisation failure, a limitation that would prevent LLMs to ever achieve AGI, I do not know if that is weird but it seems that for now nobody really knows if they can achieve AGI or not. Perhaps some emergent behavior will…
There was good progress in training neural networks to play video games. Unfortunately it doesn't seem to fit in some people's context because it was a few years ago. Kind reminder: there is "AI" beyond LLMs.
There was good progress in training neural networks to play video games. Unfortunately it doesn't seem to fit in some people's context because it was a few years ago. Kind reminder: there is "AI" beyond LLMs.
OpenAI's Dota 2 adventures were super hype back in the days.
There was good progress in training neural networks to play video games. Unfortunately it doesn't seem to fit in some people's context because it was a few years ago. Kind reminder: there is "AI" beyond LLMs.
I was really proud of it at the time because I had to do a decent amount of reading and research since I wrote all of the NN code from scratch and wanted to add some more advanced algorithm optimisations which I hadn't done in previous projects.
I suspect a coding agent could spit the entire project out in 20 minutes now, but it was very cool at the time to build a game then watch my computer learn how to play it in real time.
Personally, I think this is a really hard problem, and it may turn out to be one of the first big walls we hit on the road to AGI.