Agent Foundations

Why Agent Foun­da­tions? An Overly Ab­stract Explanation

The Rocket Align­ment Problem

Challenges with Break­ing into MIRI-Style Research

Some AI re­search ar­eas and their rele­vance to ex­is­ten­tial safety

AXRP Epi­sode 15 - Nat­u­ral Ab­strac­tions with John Wentworth

[Question] Cri­tiques of the Agent Foun­da­tions agenda?

My take on agent foun­da­tions: for­mal­iz­ing metaphilo­soph­i­cal competence

Another take on agent foun­da­tions: for­mal­iz­ing zero-shot reasoning

Ar­gu­ments about Highly Reli­able Agent De­signs as a Use­ful Path to Ar­tifi­cial In­tel­li­gence Safety

[Question] Choice := An­throp­ics un­cer­tainty? And po­ten­tial im­pli­ca­tions for agency

Un­der­stand­ing Selec­tion Theorems