Hacker News new | past | comments | ask | show | jobs | submit login

Judging from the comments section, Google needs to improve their ML for scam-detection.



It's a hard problem. One person's scam is another person's business opportunity. I, for one, want to learn more about this amazing spell-casting.


Consider that the Latin character set doesn't change when it realizes that a new convnet is doing a good job at recognizing it...

Machine learning is hard. Adversarial machine learning is much harder.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: