Andrew_Critch(Andrew Critch)

Karma: 122

This is Dr. An­drew Critch’s pro­fes­sional LessWrong ac­count. An­drew is cur­rently a full-time Re­search Scien­tist at CHAI, and spends around a ½ day per week vol­un­teer­ing for the Berkeley Ex­is­ten­tial Risk ini­ti­a­tive. He earned his Ph.D. in math­e­mat­ics at UC Berkeley study­ing ap­pli­ca­tions of alge­braic ge­om­e­try to ma­chine learn­ing mod­els. Dur­ing that time, he cofounded the Cen­ter for Ap­plied Ra­tion­al­ity and SPARC. Dr. Critch has been offered uni­ver­sity fac­ulty and re­search po­si­tions in math­e­mat­ics, math­e­mat­i­cal bio­sciences, and philos­o­phy, worked as an al­gorith­mic stock trader at Jane Street Cap­i­tal’s New York City office, and as a Re­search Fel­low at the Ma­chine In­tel­li­gence Re­search In­sti­tute. His cur­rent re­search in­ter­ests in­clude log­i­cal un­cer­tainty, open source game the­ory, and miti­gat­ing race dy­nam­ics be­tween com­pa­nies and na­tions in AI de­vel­op­ment.

Some AI re­search ar­eas and their rele­vance to ex­is­ten­tial safety

Andrew_Critch19 Nov 2020 3:18 UTC
128 points
28 comments43 min readLW link