Which has applications in human society. Using it for an attempt at AI safety, h... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Filligree on March 17, 2017 \| parent \| context \| favorite \| on: Building Safe AI: A Tutorial on Homomorphically En... Which has applications in human society. Using it for an attempt at AI safety, however, seems... A tad optimistic. It's basically just a fancy AI-box, and there's little reason to trust those.

williamtrask on March 17, 2017 [–]

I agree. IP protection and data privacy issues are a better short-term use case... and fortunately we have some time to make better HE algos before any of our AIs are really getting that smart. :)

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact