Large Language Models (LLMs) are great when their needs are met: Need 1. Can consistently get relevant, well-formatted context for their inference Need 2. Can consistently output text w.r.t. an input schema Need 3. Are offered a sandboxed code execution environment Need 4. Are subject to human review;

He's so perfect! So why don't you text him? Well he doesn't text me! But he does, right? He texted you just as we sat down. He doesn't text me enough! I want him to want me! You know? No, I don&

The singular goal of government, implicit until now, is to design and protect a structure where there is no distinction between the rational and the hyper-rational. Definitions * Rational Action: A single agent's action that optimizes that agent's utility function under some policy. * Hyper-Rational Action: A single