Highly reliable agent designs

From Issawiki
Revision as of 06:21, 27 May 2020 by Issa (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Highly reliable agent designs is the kind of pure-math research related to agency, decision theory, etc. that is done at MIRI. (there is more nuance than this that I am too lazy to describe right now; see the MIRI research agenda for details)

List of disagreements in AI safety#Highly reliable agent designs