☕ How to apply Intel-Led Threat Modeling to AI safety

Welcome back decision-maker! Writing this newsletter for you every week has helped me over the last 2 years to structure my thinking, write/talk more concise, and force it into a actionable 'how to' format. This week I'm trying something different: sharing raw meditations instead of a finished how to. I found my skillset to be uniquely suitable for the AI safety domain, so I thought I'd share some working notes with all you. This article is not intended to be a complete how-to guide, but...