Accidental LLM Backdoor - Prompt Tricks

In this video we explore various prompt tricks to manipulate the AI to respond in ways we want, even when the system instructions want something else. This can help us better understand the limitations of LLMs.

Get my font (advertisement): https://shop.liveoverflow.com

Video Part 1: https://www.youtube.com/watch?v=Sv5OLj2nVAQ

The OpenAI API cost is pretty high, thus if you want to play the game, use the OpenAI Playground with your own account: https://platform.openai.com/playground?mode=chat

Chapters:
00:00 - Intro
00:39 - Content Moderation Experiment with Chat …

api attack backdoor chat content moderation context game inputs large llm llms moderation respond single stories switch system understand video