Ronny Fernandez

Lighthaven Se­quences Read­ing Group #7 (Tues­day 10/​22)

Lighthaven Se­quences Read­ing Group #6 (Tues­day 10/​15)

Lighthaven Se­quences Read­ing Group #5 (Tues­day 10/​08)

Lighthaven Se­quences Read­ing Group #4 (Tues­day 10/​01)

Lighthaven Se­quences Read­ing Group #2 (Tues­day 09/​17)

First Lighthaven Se­quences Read­ing Group

Ronny Fer­nan­dez’s Shortform

MATS AI Safety Strat­egy Curriculum

Ronny and Nate dis­cuss what sorts of minds hu­man­ity is likely to find by Ma­chine Learning

High school­ers can ap­ply to the At­las Fel­low­ship: $10k schol­ar­ship + 11-day program

Aligned Be­hav­ior is not Ev­i­dence of Align­ment Past a Cer­tain Level of Intelligence

Are We Right about How Effec­tive Mock­ery Is?

Ex­cus­ing a Failure to Adjust

Em­pa­thetic vs In­trin­sic Oof

[Question] What do you make of AGI:un­al­igned::space­ships:not enough food?

Com­ment on Co­her­ence ar­gu­ments do not im­ply goal di­rected behavior

Test­ing the Effi­cacy of Disagree­ment Re­s­olu­tion Tech­niques (and a Pro­posal for Test­ing Dou­ble Crux)

Off the Cuff Bran­gus Stuff

[Question] Is the sum in­di­vi­d­ual in­for­ma­tive­ness of two in­de­pen­dent vari­ables no more than their joint in­for­ma­tive­ness?

The Prin­ci­ple of Pre­dicted Improvement