Hacker News new | ask | show | jobs
by jrmylee 1048 days ago
The short answer to this is to build evaluators for imperfections that our customers see as most pressing.

We have to balance that with our view of what we think will still be a problem in the future, as image generation models get better.

Eventually we want to build a vision model that's great at fine-grained details of images, while will take some time.