I have an idea that we could use AI to host the IF. Recently, I have been studying the LangChain, which is a framework for using AI, and it provides a method for AI to understand documents. So I think maybe can write some opera. as an upload to AI, and let AI host the game?
This has been hashed out in several threads (including this one). I think the general consensus is that LLMs canât really maintain the story or world consistency to really run a game. At least thatâs my interpretation.
Agreed. Itâs been tried countless times before, and itâs not worked. Nothing adds up. Plus that takes out the point of making it yourself. People like me, I donât care too much for playing (thatâs a lie, but the main point is I much prefer making my own).
Itâs also just unethical. Weâve had too many conversations about this in the chats. And it takes up so many carbon emissions weâre heading for oblivion much faster than scientists predicted. So, yeah-
hmmm Actually, try recording the chat and go with a more detailed script, Iâm thinking with the help of RAG, which is still essentially getting information from text. Itâs similar to ai summarisation or something like that. and recently google claimed to have context free models, I wonder if that would be used to help?
I mean, sure, go ahead, but this has been tried so many times before. Donât worry, Iâm not stopping you, Iâm just telling the truth.
I think we could use more intelligent parsers (especially for new IF players), I mean the algorithm that tries to find out what the player wants to do. [You could call it input AI.] But I donât think this can be done with ChatGPT.
I donât think it would work to let AI decide what the game world does in reaction to the input. [This could be called game logic AI.]
Edit: Sorry I wasnât aware that this has been discussed excessively already.
For example read this post:
Iâll just say some of my thoughts here.
Iâm going to start by writing a script which should contain the plot of the game, the map of the game, and every item in the map, the more detailed it is the better, and then write a program through the framework of langchain to allow aiâs to interact with the player on this script, and the program should save model and userâs record, use to next play.
Iâm going to try out this idea, but itâs going to be next month because I have an important exam this month.
AH that topic is too old, I donât recover it.
From reading peopleâs experiences, my impression is many AI routines seem to include an element of random improvisation to make it seem more âaliveâ in conversational gambits when itâs a bit confused to prevent it from always saying the same thing over and over - which does help in casual stream-of-consciousness conversation. However, this coupled with a short-term memory about what has been established previously in a longer interaction crops up inconsistencies over time, which usually comes across as the AI lying to the human interlocutor as the AI argues that it remembers what it said three nodes back as the truth, but doesnât remember the other contradictory thing it said ten nodes ago.
AI doesnât have a concept of âyes, andâŚâ for improvisation and truly believes the most recent established facts in its short-term memory, so the behavior can be interpreted as if youâre speaking with a pathological liar or someone who is trying to gaslight you!
You make it sound almost human!
I think thatâs the goal with LLM AI!
Part of the âsounding humanâ part almost requires the AI to be given leeway to establish âopinionsâ and possibly get stuff wrong sometimes, which might make it more realistic to converse with, but not as useful as a source of information since it can also develop bias.