Alignment Newsletter #69: Stuart Russell's new book on why we need to replace the standard model of AI - https://mailchi.mp/59ddebcb3b9a/an-69-stuart-russells-new-book-on-why-we-need-to-replace-the-standard-model-of-ai …
-
-
Odgovor korisniku/ci @rohinmshah
Great summary! It’s exciting to see another AI safety researcher thinking along the lines of meta-preferences. I’m curious to know what stage that part of the theory is technically.
1 reply 0 proslijeđenih tweetova 0 korisnika označava da im se sviđa
Odgovor korisniku/ci @metaethical_ai
I don't really know, but there are others working on this as well. This podcast with Stuart Armstrong (not to be confused with Stuart Russell) talks about meta-preferences:https://futureoflife.org/2019/09/17/synthesizing-a-humans-preferences-into-a-utility-function-with-stuart-armstrong/ …
0 replies
0 proslijeđenih tweetova
2 korisnika označavaju da im se sviđa
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.