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.
- 2018 AI Alignment Literature Review and Charity Comparison by 18 Dec 2018 4:46 UTC; 190 points) (
- Radical Probabilism by 18 Aug 2020 21:14 UTC; 146 points) (
- 2018 Review: Voting Results! by 24 Jan 2020 2:00 UTC; 134 points) (
- 2018 Review: Voting Results! by 24 Jan 2020 2:00 UTC; 132 points) (
- 2018 AI Alignment Literature Review and Charity Comparison by 18 Dec 2018 4:48 UTC; 115 points) (EA Forum;
- Embedded Agency (full-text version) by 15 Nov 2018 19:49 UTC; 114 points) (
- Thinking About Filtered Evidence Is (Very!) Hard by 19 Mar 2020 23:20 UTC; 84 points) (
- MIRI’s 2018 Fundraiser by 27 Nov 2018 5:30 UTC; 60 points) (
- Review: LessWrong Best of 2018 – Epistemology by 28 Dec 2020 4:32 UTC; 47 points) (
- Gödel’s Legacy: A game without end by 28 Jun 2020 18:50 UTC; 29 points) (
- MIRI’s 2018 Fundraiser by 27 Nov 2018 6:22 UTC; 20 points) (EA Forum;
- 28 Jan 2020 2:33 UTC; 19 points) 's comment on 2018 Review: Voting Results! by (
- 11 Jun 2020 20:59 UTC; 10 points) 's comment on Failed Utopia #4-2 by (
- 30 Dec 2020 21:50 UTC; 6 points) 's comment on Review: LessWrong Best of 2018 – Epistemology by (
- 30 Aug 2020 12:10 UTC; 5 points) 's comment on Radical Probabilism by (
- 7 Apr 2020 19:24 UTC; 2 points) 's comment on Core Tag Examples [temporary] by (
- 29 Jun 2019 0:29 UTC; 1 point) 's comment on Subsystem Alignment by (
- 13 Feb 2019 23:54 UTC; 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.