Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines
(1 edit)

You’d need a very smart (ChatGPT or Gemini stuff) AI to be able to manage that. But those AIs are censored and can’t do RP.

My planned solution is a bit more simple, to allow the AI to write notes about the gameplay so far, the AI will write in plaintext new entities or major events that happened. The player can also edit this note at anytime.

Alright, that'll be useful. Because it can be really disappointing when the AI invents an NPC who you end up getting attached to, only for the AI to forget important details about them and screw up the description, even when the NPC never left your side! Tends to derail plots that way.

try to increase the memory limit, default 2000 is too little. You can try to use your own AI or OpenRouter to use an AI with much higher memory

so what exactly do the memory and token settings in the endpoint menu do? I’ve noticed that, with meta-llama and a high amount of memory, I’ll be getting pretty good results, but then, after a while, the AI will lock up with an error message that it can’t connect and I’ll have to let it ‘cool down’ for a while before I can come back and keep going.

the free eta-llama from Open Router has a limit of number of requests per minute, and a total daily requests you can make.

The memory settings tell the game how much the AI can remember (in # of characters) from past events

oh, I see…well, that’s disappointing but good to know. Guess I should be more judicious with how I use rollbacks.


Ok. What’s the token thing?

the max tokens is how long the AI’s output can go, 2k characters by default

ah, I see. Thanks for explaining.

Do you know Meta-Llama Free's request limits?

And do you know any free AIs that have a similar level of power/intelligence, but don't have a request limit (or at least don't run out of requests as quickly)?