The Problem

There’s No Fire Alarm for Artificial General Intelligence (2017)

A Reply to François Chollet on Intelligence Explosion – Eliezer Yudkowsky

There's No Fire Alarm for Artificial General Intelligence

New paper: "Logical induction"

Safely Interruptible Agents

A formal solution to the grain of truth problem

New papers dividing logical uncertainty into two subproblems

AI safety engineering, target selection, and alignment theory

Rationality: From AI to Zombies

MIRI's Approach – Machine Intelligence Research Institute

Scott Aaronson on Philosophical Progress (2013)

Timeless Decision Theory [pdf]

Rationality: From AI to Zombies

Benjamin Pierce on clean-slate security architectures