johnswentworth

Fol­low-up to “My Em­pa­thy Is Rarely Kind”

My Em­pa­thy Is Rarely Kind

Gen­er­al­ized Han­gri­ness: A Stan­dard Ra­tion­al­ist Stance Toward Emotions

Fic­tional Think­ing and Real Thinking

The Value Propo­si­tion of Ro­man­tic Relationships

That’s Not How Epi­ge­netic Mod­ifi­ca­tions Work

Ori­ent­ing Toward Wizard Power

$500 + $500 Bounty Prob­lem: Does An (Ap­prox­i­mately) Deter­minis­tic Max­i­mal Re­dund Always Ex­ist?

Mis­rep­re­sen­ta­tion as a Bar­rier for In­terp (Part I)

$500 Bounty Prob­lem: Are (Ap­prox­i­mately) Deter­minis­tic Nat­u­ral La­tents All You Need?

So You Want To Make Marginal Progress...

In­stru­men­tal Goals Are A Differ­ent And Friendlier Kind Of Thing Than Ter­mi­nal Goals

The Case Against AI Con­trol Research

What Is The Align­ment Prob­lem?

The Plan − 2024 Update

The Field of AI Align­ment: A Post­mortem, and What To Do About It

[Question] What Have Been Your Most Valuable Ca­sual Con­ver­sa­tions At Con­fer­ences?

The Me­dian Re­searcher Problem

Three No­tions of “Power”

In­for­ma­tion vs Assurance