How are AI responses generated?

How are AI responses generated?

Playing AI Dungeon

Getting StartedGetting StartedAI Dungeon 101AI Dungeon 101Adventure AwaitsAdventure Awaits

Common Questions

AI Model DifferencesAI Model DifferencesAbout the AIAbout the AIAccount QuestionsAccount QuestionsMemberships & BenefitsMemberships & BenefitsPrivacy & SecurityPrivacy & SecurityTerms of ServiceTerms of ServiceOther QuestionsOther QuestionsCommunity Community Feedback & BugsFeedback & BugsProduct UpdatesProduct UpdatesStatusStatusTable of ContentsTable of Contents

How are AI responses generated?

icon
You don’t need to understand this to use AI Dungeon. This article is intended to be a technical explanation, and may be a bit confusing for most people. We put this here to help users understand Advanced Settings, experiment with the AI, and do more advanced Troubleshooting.

The process of generating an AI output is complicated but can be broken down into a few distinct steps:

‣

Step 1: Interface sends the message.

‣

Step 2: Our server compiles it

‣

Step 3: The AI server Tokenizes the Text

‣

Step 4: The AI Does its Thing

‣

De-Tokenization, output, done!

On this page

  • How are AI responses generated?
  • Step 1: Interface sends the message.
  • Step 2: Our server compiles it
  • Step 3: The AI server Tokenizes the Text
  • Step 4: The AI Does its Thing
  • De-Tokenization, output, done!
icon
image

© Latitude 2024