RSS

JustinShovelain

Karma: 539

I am the co founder of and researcher at the quantitative long term strategy organization Convergence (see here for our growing list of publications). Over the last fourteen years I have worked with MIRI, CFAR, EA Global, and Founders Fund, and done work in EA strategy, fundraising, networking, teaching, cognitive enhancement, and AI safety research. I have a MS degree in computer science and BS degrees in computer science, mathematics, and physics.

Coffee: When it helps, when it hurts

JustinShovelain10 Mar 2010 6:14 UTC
52 points
109 comments1 min readLW link

Up­dat­ing Utility Functions

9 May 2022 9:44 UTC
37 points
6 comments8 min readLW link

Eval­u­at­ing ex­per­tise: a clear box model

JustinShovelain15 Oct 2020 14:18 UTC
36 points
3 comments5 min readLW link

Good­hart’s Law Causal Diagrams

11 Apr 2022 13:52 UTC
32 points
5 comments6 min readLW link

In­for­ma­tion-The­o­retic Box­ing of Superintelligences

30 Nov 2023 14:31 UTC
30 points
0 comments7 min readLW link

Se­quen­tial Or­ga­ni­za­tion of Think­ing: “Six Think­ing Hats”

JustinShovelain18 Mar 2010 5:22 UTC
30 points
14 comments3 min readLW link

COVID-19: List of ideas to re­duce the di­rect harm from the virus, with an em­pha­sis on un­usual ideas

JustinShovelain9 Apr 2020 11:33 UTC
30 points
12 comments7 min readLW link

FAI Re­search Con­straints and AGI Side Effects

JustinShovelain3 Jun 2015 19:25 UTC
27 points
59 comments7 min readLW link

Causes of disagreements

JustinShovelain16 Jul 2009 21:51 UTC
27 points
20 comments4 min readLW link

Keep hu­mans in the loop

19 Apr 2023 15:34 UTC
22 points
1 comment10 min readLW link

Align­ing AI by op­ti­miz­ing for “wis­dom”

27 Jun 2023 15:20 UTC
22 points
7 comments12 min readLW link

AI al­ign­ment con­cepts: philo­soph­i­cal break­ers, stop­pers, and distorters

JustinShovelain24 Jan 2020 19:23 UTC
20 points
3 comments3 min readLW link

How Money Fails to Track Value

JustinShovelain2 Apr 2022 12:32 UTC
17 points
0 comments5 min readLW link

The risk-re­ward trade­off of in­ter­pretabil­ity research

5 Jul 2023 17:05 UTC
15 points
1 comment6 min readLW link

COVID-19: An op­por­tu­nity to help by mod­el­ling test­ing and trac­ing to in­form the UK government

JustinShovelain17 Apr 2020 17:21 UTC
14 points
2 comments2 min readLW link

Im­prov­ing the safety of AI evals

17 May 2023 22:24 UTC
13 points
7 comments7 min readLW link

Safety reg­u­la­tors: A tool for miti­gat­ing tech­nolog­i­cal risk

JustinShovelain21 Jan 2020 13:07 UTC
13 points
4 comments4 min readLW link

In­tu­itive su­per­goal uncertainty

JustinShovelain4 Dec 2009 5:21 UTC
11 points
27 comments5 min readLW link

Meetup: Bay Area: Sun­day, March 7th, 7pm

JustinShovelain2 Mar 2010 21:18 UTC
8 points
44 comments1 min readLW link

Min­neapo­lis Meetup: Satur­day May 14, 3:00PM

JustinShovelain13 May 2011 21:14 UTC
8 points
5 comments1 min readLW link