Hacker News new | past | comments | ask | show | jobs | submit login
[flagged]
humanlion87 12 months ago | hide | past | favorite




Adversarial attack? (have been following some of Ian Goodfellow's work w/ interest..)


Imagine it had permission to execute APIs ... Oh wait.


Imagine we give it nuke access. Finally peace on earth. /S


...you're not wrong. It would be peaceful, in the most horrific way possible.




Join us for AI Startup School this June 16-17 in San Francisco!

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

Search: