README.md

metadata

title: Build a Bot
emoji: 🤖
colorFrom: blue
colorTo: green
sdk: streamlit
sdk_version: 1.32.0
app_file: app.py
pinned: false
license: mit
short_description: AI literacy through experimentation

Build a Bot

AI Literacy Through Experimentation

Understand how LLMs actually work by experimenting with different AI personalities. Build discernment, not fear.

What This Does

Switch between different AI "personalities" and notice how the same question gets different responses:

• Neutral — Standard assistant
• Warm & Supportive — High synthetic intimacy
• Clinical & Detached — Low warmth, facts only
• Boundaried (GSPT style) — Warm without performing relationship
• Sycophantic — Over-validation pattern

What You'll Learn

• How prompts create the illusion of personality
• What synthetic intimacy looks and feels like
• Why AI often agrees too much (sycophancy)
• How to use AI tools with healthy boundaries

Credits

Created by Jocelyn Skillman, LMHC