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

Ask HN: Does anyone let AI agents play games just for fun?

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 81 posts

Re: Ask HN: Does anyone let AI agents play games just for fun?

#41

Post by killerstorm »

flexagoon wrote: post #23
tokarf wrote: post #18

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

A continuously running agent might require 100-500W for inference, so comparable to gaming or a small space heater. Not obscene, but also not negligible.

If we assume 250W for a continuously running agent, Grok 4 training run estimate would be around 50 million session-days, so a half-million people might consume as much running agents continuously for 100 days.

Re: Ask HN: Does anyone let AI agents play games just for fun?

#43

Post by haunter »

I actually want that in Path of Exile 2. Not because of the massive passive tree but the combination of active skill gems and the unique items providing certain skills and effects. I saw a 0 button build a couple of days ago and I wonder if anything “haven’t been found yet”

Re: Ask HN: Does anyone let AI agents play games just for fun?

#44

Post by akoboldfrying »

The ARC-AGI Prize 3 [0] is an agentic LLM benchmark that amounts to basically this: Seeing how well they can learn to play video games. They aren't very good yet -- the recent GPT 5.6 Sol only reached a score of 7.5%.

[0] https://arcprize.org/arc-agi/3

Re: Ask HN: Does anyone let AI agents play games just for fun?

#45

Post by pythonplayer123 »

jjmarr wrote: post #36

I 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…

If you get the opportunity, I really want to know how Claude does with Mario Party.

I also am personally curious how the GPT models (which advertise better computer use, etc.) would do as compared to Claude.

Re: Ask HN: Does anyone let AI agents play games just for fun?

#47

Post by killerstorm »

jstummbillig wrote: post #27
flexagoon wrote: post #23

Earlier quoted context omitted.

The huge energy waste is from model training, not inference

"waste" All of a sudden we are selectively squeamish with computer resource usage, when we were fine having all that fun with computers and hardware, 3 monitor setups, using graphic cards to play games (dear lord!) and tinkering around with home rigs of every proportion and wattage for no reason at all.

Driving a car consumes 25+ more energy per hour than gaming. So urban planning which encourages people to drive likely results in an order of magnitude more waste than all home computer use.

Re: Ask HN: Does anyone let AI agents play games just for fun?

#48

Post by roenxi »

killerstorm wrote: post #41
flexagoon wrote: post #23

Earlier quoted context omitted.

The huge energy waste is from model training, not inference

A continuously running agent might require 100-500W for inference, so comparable to gaming or a small space heater. Not obscene, but also not negligible. If we assume 250W for a continuously running agent, Grok 4 training run estimate would be around 50 million session-days, so a half-million people might consume as much running agents continuously for 100 days.

We might suspect the hardware used for the LLM is very similar to a graphics card and so the wattage would be extremely similar to using a graphics card to display a game's graphics in the first place. Which puts a certain ironic perspective on tokarf's original comment.

Re: Ask HN: Does anyone let AI agents play games just for fun?

#49

Post by Nicholas_C »

instagraham wrote: post #12
Nicholas_C wrote: post #10

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.

Someone was building a similar one where AI agents run economies. I feel like it's a great way to quickly prototype different economic models and their effects. Eventually we could have live demos of policy interventions the same day as they're announced

Do you have a link to this? Sounds very interesting.

Another idea I had was simulating an entire town with an LLM representing each person, which sounds somewhat similar.

Re: Ask HN: Does anyone let AI agents play games just for fun?

#50

Post by datsci_est_2015 »

roenxi wrote: post #32
dataviz1000 wrote: post #19

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 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…

Seems likeliest that it didn’t even “memorize” anything, in the anthropomorphic sense. The Rubik’s cube algorithm is trivially representable in code, as long as the interface for interacting with a cube is well-designed / well-defined.

I’m no more surprised that an LLM can solve a Rubik’s cube than it can send an HTTP request.

Post reply on HN