Breaking GPT-4 Safety: Pyromaniac Edition
I experimented with breaking LLM safety. GPT4 explained to me how to hurt someone.
Published in
10 min readAug 7, 2023
In recent years, Large Language Models (LLMs) have revolutionized various industries, from natural language processing to creative writing and customer service. These powerful AI models, such as GPT-3.5, GPT-4, Claude, and Bard, have the ability to generate human-like text based on the vast amount of data they’ve been trained on. It is true that the LLMs hold tremendous potential for enhancing human life and productivity…