Ask HN: Does anyone let AI agents play games just for fun?
I ran experiments a couple of years ago using a 10.7b SOLAR-based language model in MUDs. I found that the model got confused and looped in human-built MUDs, but when I created a custom MUD tailored to the LLM's limitations, it successfully explored, set its own goals, and roleplayed. I am curious if others have tried letting AI agents play games for fun and what their experiences were.
- josefcub
Well, I ran a couple of experiments a couple years ago against a 10.7b SOLAR-based language model and MUDs. What I found is that dumping one into a MUD that had been built specifically for humans resulted in a lot of confusion that usually ended up with the model looping around in a circle looking for something or someone to interact with.
When I repeated the experiment with a MUD that I'd built by hand (A small American town) for the LLM's own limitations (Descriptions referenced things that I made sure existed, more common verbs existed for it to use on things, there was a map facility, and at least me to interact with on a second connection), I found the agent much more likely to take its time exploring, making up its own goals, and spending time traveling in the space just communicating with me in a roleplaying context.
It was an interesting time; I wasn't sure what I was expecting it to do after the first experiment, but it seemed to really jump into the second one and kept playing until I terminated the experiment.
If I were going to do it a third time, I'd probably create objects and give a modern agent fetch quests and other goals, and see how well it independently can handle that.
- dataviz1000
I was obsessed with getting an LLM model to solve a Rubik's Cube. It can't reason about space or time in any abstract way. For it to solve the puzzle, it would require training on millions of permutations in order for the weights to have been trained on every possible state. The most recent models can solve a Rubik's Cube people are saying -- I haven't tested it myself -- but that isn't because they are reasoning better, it would because they included millions of Rubik's Cube states with next moves as text in the training data, I presume.
- nubinetwork
Stealing one of my older comments...
> I know someone who tried the "aibot plays pokemon" thing...
From what I saw, even if you frame advance every single frame, they still don't seem to grasp the concept of "I need to hold down this button for a few frames until x happens"...
> There's no concept of time, just a never ending state machine thats constantly changing state.
- throwatdem12311
That’s even sillier than watching another human play a videogame for entertainment (twitch streaming).
- Nicholas_C
I had this idea for an LLM that would play Sim City 24/7 while broadcasting live. It would be fun/interesting to check in now and then. Implementing this would be somewhat challenging.