Reflective altruism
I’m a philosopher at Vanderbilt University (views my own). The purpose of this blog is to use academic research to drive positive change within and around the effective altruism movement. Discussions are long-form and structured around thematic series. Subscribe below for biweekly posts.
Home | Start Here | About Me | Navigation | Comment Policy | Stay in Touch
-
Revisiting the shutdown problem (Part 3: Thornley)
A leading shutdown theorem due to Elliott Thornley needs strong unmentioned assumptions to ground shutdown-resistance.
-
Revisiting the shutdown problem (Part 2: Informal arguments)
Informal arguments for Catastrophic Shutdown Difficulty include the Argument from Instrumental Convergence and the Empirical Argument.
-
Revisiting the shutdown problem (Part 1: Introduction)
The catastrophic shutdown problem is (roughly) the problem of designing AI systems that can be shut down when their acts would lead to existential catastrophe.
-
Fanaticism (Part 4: Problems for anti-fanatical decision theories)
Anti-fanatical decision theories have problems of their own.
-
Fanaticism (Part 3: Arguments for fanaticism)
There are several good arguments for fanaticism.
-
Fanaticism (Part 2: Further reasons for doubt)
There are many reasons to doubt the truth of fanaticism.
-
Fanaticism (Part 1: Introduction)
The case for longtermism is strongest on fanatical decision theories. They might be wrong.
-
If anyone builds it, everyone dies (Part 5: Solutions)
Yudkowsky and Soares have a simple solution to AI safety: Shut it down.
-
Getting it right (Part 4: Criticism)
Effective altruists often go to great lengths to engage with their critics.
