We’ve all been there: You’re out with your friends, you’re looking fly, you take some selfies, and you post all 20 of them straight to Facebook.

Then you wake up and realize you were looking more “drunk” than “fly,” and every single picture shows you downing a different cocktail. Oops!

Yann LeCun, an NYU researcher who now oversees the Facebook Artificial Intelligence Research lab, aims to stop such behavior—or at least warn people when they’re about to post something they might regret. WIRED reports,

[pullquote]”[LeCun] wants to build a kind of Facebook digital assistant that will, say, recognize when you’re uploading an embarrassingly candid photo of your late-night antics. In a virtual way, he explains, this assistant would tap you on the shoulder and say: ‘Uh, this is being posted publicly. Are you sure you want your boss and your mother to see this?'”[/pullquote]

How would this work? LeCun plans to combine image recognition and artificial intelligence, so the system would be able to distinguish between drunk and sober pictures.

He also spoke about a future where an intelligent digital assistant could “mediate your interaction with your friends.”

The real question here is: Do you want a machine telling you what to do? Do you want an algorithm to tell you you’re about to embarrass yourself?

For many, the answer to this question is an unbridled “Yes!”

[via WIRED]