Examining the conditions required for rogue AI behavior. Text version here: https://joecarlsmith.substack.com/p/when-should-we-worry-about-ai-power

Also: to avoid it? Handle it? Solve it forever? Solve it completely?Text version here: https://joecarlsmith.substack.com/p/what-is-it-to-solve-the-alignment

Introduction to a series of essays about paths to safe and useful superintelligence. Text version here: https://joecarlsmith.substack.com/p/how-do-we-solve-the-alignment-problem

When the line pulls at your hand. Text version here: https://joecarlsmith.com/2025/01/28/fake-thinking-and-real-thinking/. 

What can we learn from recent empirical demonstrations of scheming in frontier models? Text version here: https://joecarlsmith.com/2024/12/18/takes-on-alignment-faking-in-large-language-models/