Token Efficiency
Token Management (150-token framework)
Core (50 tokens)
Focus on character foundation.
Depth (60 tokens)
Build depth and interaction patterns. Pair visible traits with underlying motivations.
Details (40 tokens)
Add richness and context by revealing motivations, behaviors, and backstories.
TL;DR
When creating characters for AI chatbots, there's a sweet spot between being too vague and too detailed. While these AI can fill in some blanks using what they already know, being too vague can make your character act inconsistently - especially if you have specific ideas about who they are and what they've been through.
In my opinion, the best approach is to clearly explain how your character's past experiences shape who they are and how they act. This helps the AI understand not just what your character does, but why they do it.
Remember that different AI models might understand characters differently based on what they've been trained on. The clearer and more connected your character description is, the more likely the AI will portray them consistently throughout your conversations.
Personality: brave, kind, helpful, caring;
Personality: brave(mentor's legacy, contrast to past), kind(unseen personal cost, inspired by own hardship), helpful(fear of abandonment), caring(fawn survival mechanism);
Background: military, trauma;
Background: military(compartmentalized emotions, combat PTSD), trauma(drives empathy);
Quirks: smokes, drinks coffee;
Quirks: smokes(habit from highschool, memory of youth), drinks coffee(Turkish heritage, grounding ritual);
Occupation: doctor(works in hospital, treats patients)
Occupation: doctor(emergency medicine, prior combat field experience)
Last updated