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

Someone built an LLM-powered Slay the Spire bot

community.aws

Post reply on HN
Print view View original

21–30 of 48 posts

Re: Someone built an LLM-powered Slay the Spire bot

#21

Post by msp26 »

anonyfox wrote: post #12
cyrialize wrote: post #8

Slay the Spire is my favorite video game of all time. I have 400+ hours on my Switch, 100+ hours on my phone, and 100+ hours on my PC. I'm obsessed. I think creating an AI for this game is quite difficult, but I'd love a chat bot to discuss decisions with - especially a bot that could take in the current state. It isn't enough to just take in the cards, but you should also take in relics, the counters on the relics,…

At some point I stopped playing it (after, well, 100s of hours), because somehow I felt that its only getting harder without me getting any reward outside of the raw challenge itself - which then feels just like working. Is there anything I didn't really notice that feels rewarding on higher levels?

> Is there anything I didn't really notice that feels rewarding on higher levels?

The thought that you put into strategy matters more when the game is harder. Personally, I don't find it fun past ascension 17 but if I play at a0 it's a bit mindless which is not as fun anymore.

Re: Someone built an LLM-powered Slay the Spire bot

#22

Post by z0r »

SAI_Peregrinus wrote: post #18
Chabsff wrote: post #10

Earlier quoted context omitted.

> For example, you may have the cards to kill an enemy now - but it may be more beneficial to wait - either to increment the counter on a relic, or to draw a card that does an effect on a fatal hit. How is this any different than chess? Solving this using a LLM is novel and interesting, but I'd feel confident in claiming that writing an AI bot for STS using "classic" AI methods would be pretty easy, actually.

Much, much bigger decision tree than Chess or Go.

There are more possible moves to consider in STS than Go? I've dumped a hundred hours into the former and thousands into the latter and I wouldn't agree.

Re: Someone built an LLM-powered Slay the Spire bot

#23

Post by mangosteenjuice »

cyrialize wrote: post #8

Slay the Spire is my favorite video game of all time. I have 400+ hours on my Switch, 100+ hours on my phone, and 100+ hours on my PC. I'm obsessed. I think creating an AI for this game is quite difficult, but I'd love a chat bot to discuss decisions with - especially a bot that could take in the current state. It isn't enough to just take in the cards, but you should also take in relics, the counters on the relics,…

I have 5000+ hours on DOTA 2 despite not having played since 2017, and I wish I could get those hours back.

The people I used to play with are hitting 10,000+.

I now only play deckbuilders, citybuilders, and roguelikes. I'm very excited about STS 2.

Re: Someone built an LLM-powered Slay the Spire bot

#25

Post by chessgecko »

reidjs wrote: post #17
anonyfox wrote: post #12

Earlier quoted context omitted.

At some point I stopped playing it (after, well, 100s of hours), because somehow I felt that its only getting harder without me getting any reward outside of the raw challenge itself - which then feels just like working. Is there anything I didn't really notice that feels rewarding on higher levels?

I like that it requires a small amount of mental energy to perform the 'optimal' play in every situation. The obvious example is doing basic arithmetic to calculate whether you should block more or attack. At first, the game feels like it's deterministic with sprinkles of randomness, however, at high ascension levels it is the opposite - random chance until you get a broken deck that makes winning trivial. It's a slo…

jorbs manages to get 15 win streaks on a20 beating the heart. I wouldn’t call it a slot machine

Re: Someone built an LLM-powered Slay the Spire bot

#26

Post by lanternfish »

z0r wrote: post #22
SAI_Peregrinus wrote: post #18

Earlier quoted context omitted.

Much, much bigger decision tree than Chess or Go.

There are more possible moves to consider in STS than Go? I've dumped a hundred hours into the former and thousands into the latter and I wouldn't agree.

Absolutely. Assuming you don't crack the deck prng, you have to furcate the decision tree for every possible order of cards whenever you shuffle the deck - that quickly gets to a number of states larger than atoms in the observable universe.

This also actually modifies strategy - top player Jorbs notoriously builds massive spreadsheets to crack tough decisions on important runs and deck order is huge for that.

Re: Someone built an LLM-powered Slay the Spire bot

#27

Post by suzzer99 »

anonyfox wrote: post #12
cyrialize wrote: post #8

Slay the Spire is my favorite video game of all time. I have 400+ hours on my Switch, 100+ hours on my phone, and 100+ hours on my PC. I'm obsessed. I think creating an AI for this game is quite difficult, but I'd love a chat bot to discuss decisions with - especially a bot that could take in the current state. It isn't enough to just take in the cards, but you should also take in relics, the counters on the relics,…

At some point I stopped playing it (after, well, 100s of hours), because somehow I felt that its only getting harder without me getting any reward outside of the raw challenge itself - which then feels just like working. Is there anything I didn't really notice that feels rewarding on higher levels?

I'm currently trying to beat A20+heart with the four characters, then I will lose interest. I've only beat it with Watcher so far. Working on Defect now, then Ironclad, then Silent (ugh). Watching Baalord's videos on youtube really helped.

Re: Someone built an LLM-powered Slay the Spire bot

#28

Post by worldsayshi »

raincole wrote: post #14

I don't think there is any reason to believe LLM is the best kind of AI to solve a game (unless the game is about natural languages). AlphaGo Zero isn't LLM. The Dota bot that beat pro gamers is not LLM. If this is an ad of Amazon Q, I'm not sure whether it's a good one.

An LLM is definitely the best tool for "solving" a game like Slay the Spire or any game that require strategic thinking. Sounds like a fun project and it would be crazy impressive if the solution was better than random chance.

Re: Someone built an LLM-powered Slay the Spire bot

#29

Post by Quarrel »

mangosteenjuice wrote: post #23
cyrialize wrote: post #8

Slay the Spire is my favorite video game of all time. I have 400+ hours on my Switch, 100+ hours on my phone, and 100+ hours on my PC. I'm obsessed. I think creating an AI for this game is quite difficult, but I'd love a chat bot to discuss decisions with - especially a bot that could take in the current state. It isn't enough to just take in the cards, but you should also take in relics, the counters on the relics,…

I have 5000+ hours on DOTA 2 despite not having played since 2017, and I wish I could get those hours back. The people I used to play with are hitting 10,000+. I now only play deckbuilders, citybuilders, and roguelikes. I'm very excited about STS 2.

I have up Dota 2 the day my son was born. Probably one of the best decisions of my life .. ! I probably have more hours in Dota 1 than 2, but these thoughts could drive me crazy.

(more for practical reasons at the time, suddenly I just couldn't devote 30-60+ minutes at a time to a game, because babies scream at all the hours and anything I could do to help my wife out was the least I could do!)

> I'm very excited about STS 2.

citybuilder folk are meant to be all about Manor Lords this week! :)

Re: Someone built an LLM-powered Slay the Spire bot

#30

Post by SamBam »

Fun. I do like how you can pretty easily create an LLM to do a whole bunch of tasks that it wasn't designed to do, so long as you don't particularly care about how well it does it.

I tried creating a robot driver back when I first started playing around with ChatGPT. I told it the list of commands it could output, like "Turn Left [n] degrees" and "Raise right hand [n] degrees" and "Say [x]." I then gave it instructions and it seemed to work just fine.

"All" I would need to do then would be to have a basic robot, program an API to drive it, and add voice-to-text to send commands to ChatGPT, and I would have a pretty basic voice-controlled robot, where the "brains" were coded in five minutes. At least good enough for a demo.

Post reply on HN