
Lucas Monteiro Paes
@lucas_mpaes
PhD candidate @Harvard |
@Apple Scholar |
Trustworthy AI and Information Theory |
Prev: @GoogleDeepMind, @IBMResearch, @IMPAOficial
ID: 1633615518069317634
https://lucasmonteiropaes.github.io 08-03-2023 23:47:52
22 Tweet
74 Takipçi
166 Takip Edilen

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)👇
