RSS

Thomas Kwa

Karma: 964

Student at Caltech. Currently trying to get an AI safety inside view.

Deriv­ing Con­di­tional Ex­pected Utility from Pareto-Effi­cient Decisions

Thomas Kwa5 May 2022 3:21 UTC
22 points
0 comments6 min readLW link

Most prob­lems don’t differ dra­mat­i­cally in tractabil­ity (un­der cer­tain as­sump­tions)

Thomas Kwa4 May 2022 0:05 UTC
7 points
0 comments3 min readLW link