Introduction

This is an audio version of Deep Deceptiveness by Nate Suarez, or User SO8-RS, posted on the 21st of March 2023. Cross-posted from the AI Alignment Forum may contain more technical jargon than usual. Heading, matter. This post is an attempt to gesture at a class of AI not kill everyoneism, or alignment, problem that seems to me to go largely unrecognised. It's important that AGI faithfully explain all of its thoughts to us in a way that highlights features we'd find relevant. See Footnote 4 for a conversation between me and Mark Shue about this. Attempted a short version with the caveat that I think it's apparently