Liam Donovan

[Question] What’s been writ­ten about the na­ture of “son-of-CDT”?

[Question] What is the con­nec­tion be­tween these two defi­ni­tions of as­crip­tion uni­ver­sal­ity?

[Question] How does the or­ga­ni­za­tion “EthAGI” fit into the broader AI safety land­scape?

[Question] Is it good prac­tice to write ques­tions/​com­ments on old posts you’re try­ing to un­der­stand?

[Question] Ev­i­dence other than evolu­tion for op­ti­miza­tion dae­mons?