Alex_Altair

My first year in AI alignment

[Question] How can one liter­ally buy time (from x-risk) with money?

Con­sider us­ing re­versible au­tomata for al­ign­ment research

A dy­nam­i­cal sys­tems primer for en­tropy and optimization

[Question] How do finite fac­tored sets com­pare with phase space?

Alex_Al­tair’s Shortform

[Question] When do you vi­su­al­ize (or not) while do­ing math?

“Nor­mal” is the equil­ibrium state of past op­ti­miza­tion processes

In­tro­duc­tion to ab­stract entropy

[Question] De­liber­ate prac­tice for re­search?

How dan­ger­ous is hu­man-level AI?

I’m try­ing out “as­ter­oid mind­set”

[Question] Re­quest for small text­book recommendations

[Question] Why hasn’t deep learn­ing gen­er­ated sig­nifi­cant eco­nomic value yet?

[Question] Does the ra­tio­nal­ist com­mu­nity have a mem­ber­ship fun­nel?

When to use “meta” vs “self-refer­ence”, “re­cur­sive”, etc.

Giv­ing cal­ibrated time es­ti­mates can have so­cial costs

[Question] Ways to in­vest your wealth if you be­lieve in a high-var­i­ance fu­ture?

[Question] How can I see a daily count of all words I type?

[Question] Tag for AI al­ign­ment?