avturchin

The Bad­ness of Death in Differ­ent Me­taeth­i­cal Theories

Warn­ing Aliens About the Danger­ous AI We Might Create

Mess AI – de­liber­ate cor­rup­tion of the train­ing data to pre­vent superintelligence

Quan­tum im­mor­tal­ity and AI risk – the fate of a lonely survivor

A New Global Risk: Large Comet’s Im­pact on Sun Could Cause Fires on Earth

Biou­pload­ing: Pre­serv­ing My Liv­ing Neu­rons and Con­nec­tome as a Spa­tially Distributed Mesh

Evolu­tion fa­vors the abil­ity to change sub­jec­tive prob­a­bil­ities in MWI + Ex­per­i­men­tal test

Time Ma­chine as Ex­is­ten­tial Risk

Our Real­ity: A Si­mu­la­tion Run by a Paper­clip Maximizer

Ex­per­i­men­tal test­ing: can I treat my­self as a ran­dom sam­ple?

The Quan­tum Mars Tele­porter: An Em­piri­cal Test Of Per­sonal Iden­tity Theories

[Question] What would be the IQ and other bench­marks of o3 that uses $1 mil­lion worth of com­pute re­sources to an­swer one ques­tion?

Side­load­ing: cre­at­ing a model of a per­son via LLM with very large prompt

If I care about mea­sure, choices have ad­di­tional bur­den (+AI gen­er­ated LW-com­ments)

Quan­tum Im­mor­tal­ity: A Per­spec­tive if AI Doomers are Prob­a­bly Right

Bit­ter les­sons about lu­cid dreaming

Three main ar­gu­ments that AI will save hu­mans and one meta-argument

De­bates how to defeat ag­ing: Aubrey de Grey vs. Peter Fedichev.

Magic by forgetting

Strength­en­ing the Ar­gu­ment for In­trin­sic AI Safety: The S-Curves Per­spec­tive