Lucas Monteiro Paes (@lucas_mpaes) 's Twitter Profile
Lucas Monteiro Paes

@lucas_mpaes

PhD candidate @Harvard |
@Apple Scholar |
Trustworthy AI and Information Theory |
Prev: @GoogleDeepMind, @IBMResearch, @IMPAOficial

ID: 1633615518069317634

linkhttps://lucasmonteiropaes.github.io calendar_today08-03-2023 23:47:52

22 Tweet

74 Takipçi

166 Takip Edilen

Lucas Monteiro Paes (@lucas_mpaes) 's Twitter Profile Photo

AI is built to “be helpful” or “avoid harm”, but which principles should it prioritize and when? We call this alignment discretion. As Asimov's stories show: balancing principles for AI behavior is tricky. In fact, we find that AI has its own set of priorities (comic Randall Munroe)👇

AI is built to “be helpful” or “avoid harm”, but which principles should it prioritize and when? 

We call this alignment discretion. As Asimov's stories show: balancing principles for AI behavior is tricky.

In fact, we find that AI has its own set of priorities 
(comic <a href="/xkcd/">Randall Munroe</a>)👇