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

See hutter prize. Best way to compress data is by understanding it. I am not exactly sure how it manifests in transformer architecture.


The future: You don't compress the movie frames, you supply a script and a list of actors and scenery and garb descriptions.


The Kolmogorov complexity, applied to entertainment. Yes, looks like we’re going there.


Looks eerily like the past, when cameras didn’t exist and people wrote plays to be acted in theaters…




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

Search: