## tl;dr This blog post critiques the term “thought leadership,” arguing it’s misleading and insulting. It describes how the term often refers to people who regurgitate surface-level information without truly understanding it, categorized into different “orders of regurgitation.” The author highlights issues with the appeal to authority fallacy, the assumption of moral authority by regurgitators, the commercialization masked as selflessness, and how “leadership” implies a loss of individual critical thinking.

Prompt Engines In order to trust that a large language model is able to complete tasks with relevant competency, it is important to equip said model with “blinders”, which try to make the model focus on the single task for which it is deployed, and hopefully prevent the derailment of the conversation by a user, whether maliciously or otherwise. The main way this is achieved is using prompt engineering, which is a fancy way to say that we are continuously reminding the agent/model what it task is, and what it should focus on.