Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why are large language models so terrible at video games?

spectrum.ieee.org

Post reply on HN
Print view View original

41–50 of 64 posts

Re: Why are large language models so terrible at video games?

#41

Post by croes »

ceheaaf wrote: post #19

It feels like they're really focusing on overstating how confusing and weird it is that an LLM can write code but not play games very well, rather than just explaining it. Code is text. LLMs are text input/output machines. Game input/output is not at all text. LLMs can certainly reason about games with a simple/explicit enough domain (try a risk tournament where models can talk to each other between turns!)

LLMs are used for OpenClaw and similar to do tasks for their user.

Games are a bunch of tasks too.

So if they fail at game tasks maybe it’s a bad idea to advertise those LLMs as task doing assistants.

Re: Why are large language models so terrible at video games?

#42

Post by cubefox »

ceheaaf wrote: post #19

It feels like they're really focusing on overstating how confusing and weird it is that an LLM can write code but not play games very well, rather than just explaining it. Code is text. LLMs are text input/output machines. Game input/output is not at all text. LLMs can certainly reason about games with a simple/explicit enough domain (try a risk tournament where models can talk to each other between turns!)

The other reason is lack of continual learning, especially for long games like RPGs.

Re: Why are large language models so terrible at video games?

#44

Post by scott_w »

dsabanin wrote: post #20

Why is a language model bad at video games? I think the answer is stated in the question itself.

I think it’s good to remember that, just 2 years ago, we were having conversations with people convinced LLMs were intelligent and possibly sentient. It’s really good to a) point out that they’re not demonstrating general intelligence and b) why they aren’t a good fit for this type of problem.

Re: Why are large language models so terrible at video games?

#45

Post by haffi112 »

kqr wrote: post #39
ceheaaf wrote: post #19

It feels like they're really focusing on overstating how confusing and weird it is that an LLM can write code but not play games very well, rather than just explaining it. Code is text. LLMs are text input/output machines. Game input/output is not at all text. LLMs can certainly reason about games with a simple/explicit enough domain (try a risk tournament where models can talk to each other between turns!)

But LLMs are terrible at text adventures too. See e.g. https://entropicthoughts.com/updated-llm-benchmark and previous articles referenced in there. I have yet to see any sort of harness that lets a frontier LLM interact with a text adventure and make meaningful progress on its own.

They are also pretty bad at navigating mazes (which can be somewhat similar in spirit to text adventures where you need to navigate through text): https://arxiv.org/abs/2507.20395

Re: Why are large language models so terrible at video games?

#48

Post by new_account_103 »

pmontra wrote: post #46

I don't know what to save from this article. Maybe only "[LLMs are] very bad at spatial reasoning. Which shouldn’t be surprising, because that’s also not in the training data."

Frankly, Claude has been unbelievably proficient at spatial design since Opus 4.6. I think a lot of the people commenting here are relying on outdated assumptions. Simply put, LLMs have crossed a threshold and can now produce professional, shippable visual designs, similar to the way they became good enough to produce shippable code in 2024.

Re: Why are large language models so terrible at video games?

#50

Post by lou1306 »

Zobat wrote: post #26

As others have hinted at LLMs aren't really made in a way that makes them likely to play video games (CS/Halo and such) well. I wonder how they'd fare "against" text based adventures like Zork (which they'll no doubt have ample knowledge about) and newer text based adventure games (which they'll know less about).

To be honest, Zork at times makes precious little sense: you are supposed to die over and over before you figure stuff out. For instance, you have to grab the endless-light-source treasure very early on, or you mathematically cannot win. And the game does not spell anything out for you, you just have to "get it" by watching closely at how/why you die.

This is a tall order for an LLM: it needs a lot of context but most of the context will be just noise.

Post reply on HN