Stuart_Armstrong(Stuart Armstrong)

Large lan­guage mod­els can provide “nor­ma­tive as­sump­tions” for learn­ing hu­man preferences

Con­cept ex­trap­o­la­tion for hy­poth­e­sis generation

Us­ing GPT-Eliezer against ChatGPT Jailbreaking

Bench­mark for suc­cess­ful con­cept ex­trap­o­la­tion/​avoid­ing goal misgeneralization

Value ex­trap­o­la­tion vs Wireheading

Ge­or­gism, in theory

How to get into AI safety research

GPT-3 and con­cept extrapolation

Con­cept ex­trap­o­la­tion: key posts

AIs should learn hu­man prefer­ences, not biases

Differ­ent per­spec­tives on con­cept extrapolation

Value ex­trap­o­la­tion, con­cept ex­trap­o­la­tion, model splintering

[Link] Aligned AI AMA

More GPT-3 and sym­bol grounding

Why I’m co-found­ing Aligned AI

Differ­ent way clas­sifiers can be diverse

Value ex­trap­o­la­tion par­tially re­solves sym­bol grounding

How an alien the­ory of mind might be unlearnable

Find­ing the mul­ti­ple ground truths of CoinRun and image classification

Declus­ter­ing, reclus­ter­ing, and filling in thingspace