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

> Agree that it feels hacky at first, but once the whitelist dataset gets huge, it becomes unique training data for Tesla (and hopefully their machine learning will be able to generalize from it).

I guess. But then you still have to deal with rollout in other countries. And maintenance of sign locations which can change over time, get removed, etc. Still hacky IMHO.

How would machine learning make use of white-listed data? I doubt they could use that data to predict the GPS location of unknown signs.

If you mean image recognition, I assume if machine learning could properly identify the signs with accuracy, then they wouldn't need the whitelist. Then again, maybe they truly haven't collected a full overhead-sign dataset yet. I'd be shocked though if they don't by now. Anyway, you could be right. It would be fun to learn more about these setups.



Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: