You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I’d like to kick off a discussion on some of the key challenges related to LLM usage in UnscriptedAdventures. While there's great potential to create an engaging storytelling experience, it’s important that we remain focused on the LLM-exploration aspect of the project.
One major challenge, as I see it, is ensuring that the LLM, or Game Master (GM), can maintain and recall the context of the story across multiple turns or interactions. LLMs traditionally struggle with handling long-term dependencies and retaining key details over extended exchanges.
Another challenge involves the GM's ability to dynamically adjust the difficulty of challenges or story elements based on the user's emotional state or level of engagement. This might involve using sentiment analysis or emotion detection techniques to interpret emotional cues from user input, such as frustration or excitement.
I’d love to hear your thoughts on these challenges or any other aspects you think are important to explore. What are your ideas?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hi everyone,
I’d like to kick off a discussion on some of the key challenges related to LLM usage in UnscriptedAdventures. While there's great potential to create an engaging storytelling experience, it’s important that we remain focused on the LLM-exploration aspect of the project.
One major challenge, as I see it, is ensuring that the LLM, or Game Master (GM), can maintain and recall the context of the story across multiple turns or interactions. LLMs traditionally struggle with handling long-term dependencies and retaining key details over extended exchanges.
Another challenge involves the GM's ability to dynamically adjust the difficulty of challenges or story elements based on the user's emotional state or level of engagement. This might involve using sentiment analysis or emotion detection techniques to interpret emotional cues from user input, such as frustration or excitement.
I’d love to hear your thoughts on these challenges or any other aspects you think are important to explore. What are your ideas?
Beta Was this translation helpful? Give feedback.
All reactions