FinalFormal2

Fi­nalFor­mal2′s Shortform

[Question] Is there a CFAR hand­book au­dio op­tion?

[Question] En­deav­orOTC le­git?

[Question] When can I be nu­mer­ate?

[Question] Where should I look for in­for­ma­tion on gut health?

[Question] How do I get bet­ter at D&D Sci?

Short Post: Discern­ing Truth from Trash

[Question] When does an AI be­come in­tel­li­gent enough to be­come self-aware and power-seek­ing?

[Question] What are the ar­gu­ments for/​against FOOM?

[Question] What’s the con­sen­sus on porn?

[Question] How did LW up­date p(doom) af­ter LLMs blew up?

The Re­la­tion­ship be­tween RLHF and AI Psy­chol­ogy: De­bunk­ing the Shog­goth Argument

[Question] How does con­scious­ness in­ter­act with ar­chi­tec­ture?

[Question] Does GPT-4′s abil­ity to com­press text in a way that it can ac­tu­ally de­com­press in­di­cate self-aware­ness?

[Question] Steel­man­ning OpenAI’s Short-Timelines Slow-Take­off Goal

[Question] Just don’t make a util­ity max­i­mizer?

[Question] Why is in­creas­ing pub­lic aware­ness of AI safety not a pri­or­ity?

[Question] Could we set a re­s­olu­tion/​stop­per for the up­per bound of the util­ity func­tion of an AI?

[Question] What’s the prob­lem with hav­ing an AI al­ign it­self?

[Question] What’s the prob­lem with Orac­u­lar AIs?