what research exists on computational morality? like: seed bot w/moral values, present it w/scenarios, elicit sentiments, iterate on values.
-
-
Replying to @chrisamaphone
@chrisamaphone Does deontic logic help here at all? At least as a formalism for phrasing the questions and answers…?1 reply 0 retweets 0 likes -
-
Replying to @chrisamaphone
@chrisamaphone I read smth that did model checking for social simulations… “do all agents have an acceptable policy?” kind of questions.2 replies 0 retweets 0 likes -
Replying to @JoeOsborn
@chrisamaphone Naïvely, I’d also expect game tree search to be suitable for non-rules-based (i.e. non-deontic), utilitarian ethics.1 reply 0 retweets 0 likes -
Replying to @JoeOsborn
@JoeOsborn yeah. but i'm thinking of something closer to human-like moral intuition & associations than "objective" value2 replies 0 retweets 0 likes -
Replying to @chrisamaphone
@chrisamaphone@JoeOsborn recent paper by Joe Blass and@ianhorswill might be on the right path https://www.semanticscholar.org/paper/Implementing-Injunctive-Social-Norms-Using-Blass-Horswill/51240fc49e8324a830471b7cb69d697c830c504f/abstract …4 replies 0 retweets 0 likes
@xfoml @chrisamaphone @JoeOsborn The stuff that tries to formalize tends to be the philosophical stuff, but it doesn't match human behavior.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.