Gyrodiot

Karma: 662

I’m Jérémy Perret. Based in France. PhD in AI (NLP). AI Safety & EA meetup organizer. Information sponge. Mostly lurking since 2014. Seeking more experience, and eventually a position, in AI safety/governance.

Extremely annoyed by the lack of an explorable framework for AI risk/benefits. Working on that.

Review of “Learning Normativity: A Research Agenda”

Gyrodiot, adamShimi and Joe Collman

Jun 6, 2021, 1:33 PM

37 points

0 comments6 min readLW link

Review of “Fun with +12 OOMs of Compute”

adamShimi, Joe Collman and Gyrodiot

Mar 28, 2021, 2:55 PM

65 points

21 comments8 min readLW link 1 review

Learning from counterfactuals

GyrodiotNov 25, 2020, 11:07 PM

11 points

5 comments2 min readLW link

Mapping Out Alignment

Logan Riggs, adamShimi, Gurkenglas, AlexMennen and Gyrodiot

Aug 15, 2020, 1:02 AM

43 points

0 comments5 min readLW link

Resources for AI Alignment Cartography

GyrodiotApr 4, 2020, 2:20 PM

45 points

8 comments9 min readLW link

SSC Meetups Everywhere: Toulouse

GyrodiotSep 10, 2019, 7:17 PM

3 points

0 comments1 min readLW link

Layers of Expertise and the Curse of Curiosity

GyrodiotFeb 12, 2019, 11:41 PM

19 points

1 comment6 min readLW link

Willpower duality

GyrodiotJan 20, 2017, 9:56 AM

10 points

8 comments2 min readLW link

(www.jrmyp.net)

Open thread, Oct. 31 - Nov. 6, 2016

GyrodiotOct 31, 2016, 9:24 PM

7 points

83 comments1 min readLW link