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

61–70 of 81 posts

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

#61

Post by danaris »

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.

Presumably you're fine with using electricity to heat/cool your house, yes?

Would you, then, also be fine with running three extra air conditioners/space heaters that do nothing but sit outside on the lawn?

"People are OK with the energy usage already happening, so they should be OK with adding 32,767 AI datacenters too" doesn't make sense. It's essentially a reductio ad absurdum. Of course we're "selectively squeamish with computer resource usage"; some usage is obviously useful to us (with entertainment also in the "useful" category—we're not robots!), while for many, many of us, the extra datacenters are having anywhere from a neutral to a profoundly net-negative impact on our lives even before you consider the resource usage.

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

#62

Post by killerstorm »

roenxi wrote: post #48
killerstorm wrote: post #41

Earlier quoted context omitted.

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.

To serve a frontier model you need a lot more than one GPU... at least 8. But for better efficiency they batch multiple requests on one server. So it is sort of a coincidence that it ends up roughly in 1 consumer GPU range. A different architecture (e.g. linear attention / RNN) could end up with more peak power usage.

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

#65

Post by flexagoon »

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.

I was just using the terminology of the person I was replying to

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

#66

Post by dca2 »

rotis wrote: post #58
dca2 wrote: post #52

I've been doing almost exactly this with Mafia (aka werewolf): running games where LLMs play against each other, with humans able to share the lobby. It's been a hit on family game night so far, because it allows our group to "fill out the cast" with a lot more characters than just the human players and add a lot of variety without needing a huge group. My experience is that text-first, turn-based games are a particu…

So the AIs end up being silly like in this video? 10 AIs Play Mafia https://www.youtube.com/watch?v=JhBtg-lyKdo

The cheap ones definitely do! The flagship models tend to be pretty decent.

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

#67

Post by jerrycat101 »

duckmysick wrote: post #51
jerrycat101 wrote: post #20

what do you mean? how can you do this?

Ideally you have an MCP server (Model Context Protocol) that talks to your game. It can use existing API if it's exposed - but it's very rare if it's not a game you're developing/is modded. It could also be reversed engineered with packets (if it's an online game), web sockets, memory editing, dll injection, or OCR and input manipulation if everything else fails. If you don't have an MCP server the AI agent might try…

thanks for the explanation! Much appreciated

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

#68

Post by handoflixue »

danaris wrote: post #61
jstummbillig wrote: post #27

Earlier quoted context omitted.

"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.

Presumably you're fine with using electricity to heat/cool your house, yes? Would you, then, also be fine with running three extra air conditioners/space heaters that do nothing but sit outside on the lawn? "People are OK with the energy usage already happening, so they should be OK with adding 32,767 AI datacenters too " doesn't make sense. It's essentially a reductio ad absurdum. Of course we're "selectively squeam…

I mean, if you actually understood the scale of AI power usage, it would make sense. A TV can run 200 watts/hour, so this is equivalent to... watching TV?

Or, perhaps, watching TV in the background while you program.

We are not in a power crisis, and data centers have had basically no impact on our lives compared to previous technologies. There are more data centers used for the internet, but somehow you're still here, using a data center to complain about checks notes data centers? Really? Well that's a bit cheeky.

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

#69

Post by danaris »

handoflixue wrote: post #68
danaris wrote: post #61

Earlier quoted context omitted.

Presumably you're fine with using electricity to heat/cool your house, yes? Would you, then, also be fine with running three extra air conditioners/space heaters that do nothing but sit outside on the lawn? "People are OK with the energy usage already happening, so they should be OK with adding 32,767 AI datacenters too " doesn't make sense. It's essentially a reductio ad absurdum. Of course we're "selectively squeam…

I mean, if you actually understood the scale of AI power usage, it would make sense. A TV can run 200 watts/hour, so this is equivalent to... watching TV? Or, perhaps, watching TV in the background while you program. We are not in a power crisis, and data centers have had basically no impact on our lives compared to previous technologies. There are more data centers used for the internet, but somehow you're still her…

I'm sorry, when individual datacenters are drawing more power than entire cities, and needing to build entire new fossil-fuel-burning power plants to service their needs, you'll excuse me if I'm skeptical of your "it's just like watching TV" excuse there.

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

#70

Post by datsci_est_2015 »

dataviz1000 wrote: post #56
datsci_est_2015 wrote: post #50

Earlier quoted context omitted.

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.

Opus 4.6 can not solve a Rubik's Cube. What changed between Opus 4.6 and Fable and the GPT 5.6 models released since? LLM models cannot actually reason about a red or white piece sitting on the opposite side of the cube or figure out how to move it into place. The model knows where the piece is supposed to go because the algorithm tells it. What it cannot do is work out on its own which turns will get the piece there…

Well here’s my caveat, I guess:

> as long as the interface for interacting with a cube is well-designed / well-defined

The phrase “solving a Rubik’s cube” is somehow misleading. The challenge for the LLM would seem to be more along the lines of 3d spatial reasoning, which is once again imo an interfacing problem. There’s no “pure” way to prompt an LLM with spatial information, because spatial information is not language. Creatures on earth solved spatial reasoning problems with signal processing solutions (processing light and sound; vision and echolocation).

Post reply on HN