Live data from Hacker News

Claude Plays Pokémon

twitch.tv

11–20 of 28 posts

Re: Claude Plays Pokémon

#13

This is neat but watching a reasoning model that stops to consider "I have read half of a dialogue block, time to press A to get the rest of the text" gets old really quick. I think I'd rather watch a model try to play pokemon against human opponents on a simulator like pokemon showdown (which I understand is a bit further in an IP rights grey area than emulating a 30 year old game). In that case you would get to see…

> play pokemon against human opponents on a simulator like pokemon showdown

That's precisely the pet project I'd take on if/when I bother to take the time making some deep learning agent. There's a bot that plays one of the ladders already but it's just a decision tree and the best players know how to predict its moves. It's like ~1500 ELO in a ladder where the best players are 1800+. Still not bad, to be fair; it would probably beat me.

The bot has a pre-selected team, which I believe always starts with the same mon. I'd be more interested in an agent that fully played the game, start-to-finish, including making a team based on play data and selecting a starter based on the current opponent's team.

Re: Claude Plays Pokémon

#14

This is neat but watching a reasoning model that stops to consider "I have read half of a dialogue block, time to press A to get the rest of the text" gets old really quick. I think I'd rather watch a model try to play pokemon against human opponents on a simulator like pokemon showdown (which I understand is a bit further in an IP rights grey area than emulating a 30 year old game). In that case you would get to see…

A model doesn't need to play on visual simulators, it can very well do that on IRC (like the good old days of RS/GSBots), to show how it fares against humans.

One of the biggest challenge this Claude version faces is to read the visual data accurately. It was stuck in the Viridian forest and Pokemarts for a while because the overworld objects like trees and paths kept confusing it.

Re: Claude Plays Pokémon

#18
post #3

This is truly tremendous to watch. Eleven years from TPP, and we're watching the current best-in-class AI try its best at the same. Who'll get there first, the historical gestalt of Twitch users or the just-shy-of-10^26 FLOPS [0] AI model? Now here's a concept for anyone with more money than sense: ClaudePlaysTwitchPlaysPokemon, where it's TPP but every participant is Claude. Would hivemind AI consensus perform bette…

Or the converse, feed all of twitch chat to Claude and see if it can output the correct button presses.

Re: Claude Plays Pokémon

#19

This is neat but watching a reasoning model that stops to consider "I have read half of a dialogue block, time to press A to get the rest of the text" gets old really quick. I think I'd rather watch a model try to play pokemon against human opponents on a simulator like pokemon showdown (which I understand is a bit further in an IP rights grey area than emulating a 30 year old game). In that case you would get to see…

Haha yeah this is cool but the days of watching Twitch Plays Pokemon or RNG Plays Pokemon or things like that were much more entertaining

Re: Claude Plays Pokémon

#20
post #16

Earlier quoted context omitted.

What is the significance of this?

I think the “wa” prefix means “bad” in Japan

There's a bit of a... pun(?) in there with its apparent origin as a name in Waluigi: The word is "waru" (noun) or "warui" (adjective), and with the "l" / "r" thing with Japanese pronunciation, "warui" and "luigi" combine really well.

Granted Wario was first in that franchise.

Post reply on HN