An Untrollable Mathematician Illustrated
The following was a presentation I made for Sören Elverlin’s AI Safety Reading Group. I decided to draw everything by hand because powerpoint is boring. Thanks to Ben Pace for formatting it for LW! See also the IAF post detailing the research which this presentation is based on.
- Embedded Agency (full-text version) by Nov 15, 2018, 7:49 PM; 201 points) (
- 2018 AI Alignment Literature Review and Charity Comparison by Dec 18, 2018, 4:46 AM; 190 points) (
- Radical Probabilism by Aug 18, 2020, 9:14 PM; 182 points) (
- 2018 Review: Voting Results! by Jan 24, 2020, 2:00 AM; 135 points) (
- 2018 Review: Voting Results! by Jan 24, 2020, 2:00 AM; 135 points) (
- 2018 AI Alignment Literature Review and Charity Comparison by Dec 18, 2018, 4:48 AM; 118 points) (EA Forum;
- Thinking About Filtered Evidence Is (Very!) Hard by Mar 19, 2020, 11:20 PM; 97 points) (
- MIRI’s 2018 Fundraiser by Nov 27, 2018, 5:30 AM; 60 points) (
- Review: LessWrong Best of 2018 – Epistemology by Dec 28, 2020, 4:32 AM; 47 points) (
- Gödel’s Legacy: A game without end by Jun 28, 2020, 6:50 PM; 44 points) (
- When Arguing Definitions is Arguing Decisions by Jul 25, 2021, 4:45 PM; 28 points) (
- MIRI’s 2018 Fundraiser by Nov 27, 2018, 6:22 AM; 20 points) (EA Forum;
- Jun 11, 2020, 8:59 PM; 10 points) 's comment on Failed Utopia #4-2 by (
- Dec 21, 2021, 2:54 PM; 7 points) 's comment on Attainable Utility Preservation: Empirical Results by (
- Belief-conditional things—things that only exist when you believe in them by Dec 25, 2021, 10:49 AM; 7 points) (
- Coping with Undecidability by Jan 27, 2022, 10:31 AM; 6 points) (
- Dec 30, 2020, 9:50 PM; 6 points) 's comment on Review: LessWrong Best of 2018 – Epistemology by (
- Aug 30, 2020, 12:10 PM; 5 points) 's comment on Radical Probabilism by (
- Oct 10, 2022, 8:12 PM; 4 points) 's comment on Algon’s Shortform by (
- Apr 7, 2020, 7:24 PM; 2 points) 's comment on Core Tag Examples [temporary] by (
- Jun 29, 2019, 12:29 AM; 1 point) 's comment on Subsystem Alignment by (
- Feb 13, 2019, 11:54 PM; 1 point) 's comment on Three Kinds of Research Documents: Exploration, Explanation, Academic by (
I think this post, together with Abram’s other post “Towards a new technical explanation” actually convinced me that a bayesian approach to epistemology can’t work in an embedded context, which was a really big shift for me.
Abram’s writing and illustrations often distill technical insights into accessible, fun adventures. I’ve come to appreciate the importance and value of this expository style more and more over the last year, and this post is what first put me on this track. While more rigorous communication certainly has its place, clearly communicating the key conceptual insights behind a piece of work makes those insights available to the entire community.