So two suggestions, the first would be a token counter or token percentage usage so the player can see how many tokens have been used by his current roleplay. Like it the player has an AI model that provides 10K tokens, if the player uses a hundred tokens, then he's used 1% of the available tokens.
I am quite ignorant of AI and how the system works so please ignore if this is impossible but when the AI reaches a certain point, it could create a kind of save file or data packet with the relevant data done so far. As an example, the player has a make shift spear, is weak to hypnotism, has stats A, B and C etc in a formalised file. If the data has already been generated, would the token use be lowered to check the created data packet for items etc, physical characteristics, statistics etc rather than using tickets to regenerate more tokens? Or would it be the same? A dynamic inventory/state file might be more efficient means of token usage? Being cheeky, I asked the AI first. Here's the question and response, hopefully it might help:
The following is in the context of running a game generated entirely by ai.
Is it possible for when the AI reaches a certain point, it could create a kind of save file or data packet with the relevant data done so far. As an example, the player has a make shift spear, is weak to hypnotism, has stats A, B and C etc in a formalised file. The aim of this is to minimise the use of tokens and generate files that can be created to add themes, statistics etc to the game so a horror game doesn't find itself with comedy elements, a pornographic game maintains details so the player character doesn't start sucking cock in a glory hole only to get a follow up scene that they're in a bed in a model
Assistant
mistral-nemo-instruct-2407Yes, it's possible for an AI like me to create save files or data packets containing relevant information about the game state, character attributes, and other pertinent data. This approach can help manage token usage more efficiently and maintain consistency in the generated content.
Here are some ways we could implement this:
- Structured data formats: We can use structured data formats like JSON, XML, or YAML to create save files that store relevant information about the game state, character statistics, items, and other objects.
- Key-value pairs: The save file could consist of key-value pairs, where keys represent attributes or properties (e.g.,
player_weapon,hypnotism_resistance,stat_strength,stat_intelligence,stat_endurance), and values store the corresponding data. - Checkpoints and updates: At specific intervals or based on certain events in the game, the AI could generate a save file containing the most recent and relevant information. These save files can then be loaded at the start of new sessions to resume gameplay with consistent character progression and attributes.
Here's an example of what a save file might look like using JSON:
{ "player": { "name": "John Doe", "weapon": "make-shift spear", "resistances": { "hypnotism": 0.3 }, "stats": { "strength": 5, "intelligence": 7, "endurance": 6 } }, "game_settings": { "genre": "horror" } }
With this approach, you could ensure that the generated game maintains consistent themes and attributes by loading appropriate save files at the start of new sessions. This can help minimize token usage and prevent unwanted or inconsistent elements from appearing in the generated content.
To facilitate this process, you can provide clear prompts and guidelines for the AI when creating save files, such as specifying which attributes to include, update, or prioritize.