[godelski]

> When I got into ML two years ago, I thought that knowledge would come from reading scientific papers. I was wrong.

I'm in the middle of a PhD and this is always an issue. It takes awhile to learn how to read papers and to gather enough background knowledge that you can read between the lines (publications are limited, you can't put everything in a paper. This is why having code is so great, it accelerates the process). You're two years into your journey, this is often when things _start_ turning the other direction. There's a reason PhDs take so long, and that's with experts (hopefully) helping you learn how to read papers, telling you which papers to read (which is a challenge in of itself), having the ability to spend full time on learning, and learning how to build background knowledge on a subject while learning the state of the art. There's a reason ML pays the big bucks. It takes a long time to learn/gather expertise, it is fucking difficult, and it has direct applications that can lead to useful products today (a big component of why you get paid big bucks). It is also easy to lose track of your progress. I remember the first research paper I read was complete gibberish to me. I'm 3 years into my PhD and now I can understand papers in my niche. But for a long time a lot of stuff didn't click. This is normal. It takes time to learn and 2 years isn't that much (especially when you have a full time job). Making contributions in your first year of a PhD is atypical, even in your second year. It only happens at top universities where people have a lot of help and resources.

Research it hard. It takes years to become an expert and learn how to read papers. Don't give up, but calm down and recognize that given more time things will make more sense.