Yeah let's make llm waste a whole city energy / water playing games just for fun !
The huge energy waste is from model training, not inference
if that was true tokens would be free
Ask HN: Does anyone let AI agents play games just for fun?
31–40 of 81 posts
Re: Ask HN: Does anyone let AI agents play games just for fun?
#32I 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 bet…
> 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.
Isn't it far more likely that the LLM has memorised the well known algorithms for solving a Rubik's Cube and has become intelligent enough to execute them? That seems like it'd be a lot easier than memorising millions of cube states. It doesn't even seem obvious that it could memorise next moves, it seems [0] there are more possible states of the cube than these models have parameters. It'd need to be a Large Rubik's Cube Model (LRCM? LRM?) rather than an LLM.
Re: Ask HN: Does anyone let AI agents play games just for fun?
#33That’s even sillier than watching another human play a videogame for entertainment (twitch streaming).
Even sillier than watching another human play soccer?
Like the World Cup.
Re: Ask HN: Does anyone let AI agents play games just for fun?
#34A few weeks ago I released wordit, a game where starting from a four letter word, you need to come up with as many other words you can, Changi one letter at a time. To make it more competitive I've created a leaderboard. The game starter with scores of 20s, then 100s and finally 1000s. The record right now is more than 6000. After a brief investigate I realize it was a bot. Several bots took a stab at my game. I then just split the leaderboard into humans and bots. I found it funny.
Re: Ask HN: Does anyone let AI agents play games just for fun?
#35Re: Ask HN: Does anyone let AI agents play games just for fun?
#36I made a general purpose harness integrated into MelonDS and got Claude to play Mario Kart by feeding it continuous video.
It made forward progress in the Figure 8 circuit after I helped it through a menu but kept slamming into a wall so it wasn't on track to win in less than an hour.
Also got it to play Age of Empires: Age of Kings using the same technique but it failed to click on anything.
DS specifically is very fun because it's touch based but the UI components aren't accessible. So it is extremely challenging for LLM's spatial reasoning skills.
I want to improve the harness more and have the LLM dynamically create its own tools based on drawing grid box overlays on a screen in a feedback loop, so it can say "click on the 'end turn'" button instead of "click 240,320" and it would 'just work' in any game.
I also want to eventually play games with it... I didn't really have friends to play my massive DS library with as a kid so it'd be nice to finally have someone that can roast me or react to my skills. And learn my playstyle enough to punish me.
Unfortunately haven't had the time due to work at my day job and needing to clean out my apartment.
Re: Ask HN: Does anyone let AI agents play games just for fun?
#37That’s even sillier than watching another human play a videogame for entertainment (twitch streaming).
I kinda agree that watching an LLM play videogames is a bit silly, but watching other humans play videogames has been entertainment ever since videogames have existed. I remember taking turns playing the Atari 2600, watching each other play. I remember standing around cabinets at the arcade, watching good players play through Golden Axe or Rastan.
Re: Ask HN: Does anyone let AI agents play games just for fun?
#38That’s even sillier than watching another human play a videogame for entertainment (twitch streaming).
Even sillier than watching another human play soccer? Like the World Cup.
I've always found that people's excitement around the sport gives me more much joy than the activity itself (watching another human play football).
Re: Ask HN: Does anyone let AI agents play games just for fun?
#39Seems absurd to run a COTS agent at token rates to "play" a game. Like watching the computer beat its meat.
Building your own models for it would be an eye-opener though. Learn a lot.
Re: Ask HN: Does anyone let AI agents play games just for fun?
#40I 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 bet…
> 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. Isn't it far more likely that the LLM has memorised the well known algorithms for solving a Rubik's Cube and has become intelligent enough to execute them? That seems like it'd be a lot easier than memorising millions of cube states. It doesn't eve…
Indeed, I suspect the approaches/algorithms for solving a Rubik's cube "compress" a lot better than trying to distill the entire search space in order to be able to predict the exact next move.
I see this trope fairly often, i.e. the assumption that an LLM would need to have been trained on . Now, while I do have a moderate amount of background in AI, I am definitely not an expert on LLMs as such. I would be interested to hear someone's take, who does work actively in LLM research. Can they generalise "well enough"? They certainly seem to be able to do so, from my anecdata, and I don't believe "training explicitly for every possible scenario" would have scaled even to today's state.