David Udell

HCH and Ad­ver­sar­ial Questions

Your Fu­ture Self’s Cre­dences Should Be Un­pre­dictable to You

On Defect­ing On Yourself

Agency and Coherence

The Ir­re­sistible At­trac­tion of De­sign­ing Your Own Utopia

De­cep­tive Agents are a Good Way to Do Things

Why No *In­ter­est­ing* Unal­igned Sin­gu­lar­ity?

EU Max­i­miz­ing in a Gloomy World

Dath Ilan vs. Sid Meier’s Alpha Cen­tauri: Pareto Improvements

Ne­go­ti­at­ing Up and Down the Si­mu­la­tion Hier­ar­chy: Why We Might Sur­vive the Unal­igned Singularity

Your Utility Func­tion is Your Utility Function

But What’s Your *New Align­ment In­sight,* out of a Fu­ture-Text­book Para­graph?

Dath Ilani Rule of Law

Gato as the Dawn of Early AGI

The “Adults in the Room”

In­fer­nal Cor­rigi­bil­ity, Fiendishly Difficult

Ra­tion­al­ism in an Age of Egregores

The STEM Attractor

[Question] Longter­mist Con­se­quences of a New Dark Age?

How to Vi­su­al­ize Bayesianism