Very neat explanation of solving these kinds of unique challenges, especially given how similar the illustrations were.

One question I had was, knowing how difficult it was to train the model with the base images, and given that the client didn’t have time to photograph them, did you consider flying someone out to the museum for a couple of days to photograph each illustration from several angles with the actual lighting throughout the day? Or potentially hiring a photographer near the museum to do that? It seems like a round trip ticket plus a couple nights in a hotel could have saved a lot of headache, providing more images to turn into synthetic training data. Even if you still had to resort to using 4o as a tiebreaker, it could be that you only present two candidates as the third might have a much lower similarity score to the second candidate. Good write up either way.

Assuming it’s on a computer (big assumption for kids) you can install this[0] extension and customize it to do things like remove shorts from appearing, disable autoplay, hide recommended videos, etc. it’s a good way to not let YouTube pull your focus away from you.

[0] https://unhook.app/

California at least is 15 days/year the first year, 20 to year 5, then 25/year after

15 days a year is awful!

Here in the UK for a full time employee the minimum by law, regardless of how long you've worked at a place, is 28 days. For all full time employees.

I think I'm on 32 now, and sick leave doesn't come out the holiday allowance, that's absurd!

Yep. The PTO policies of US companies are just terrible. Often even the ones with "unlimited" PTO have defacto limits that just happen to work out to typical US PTO policies. (What a coincidence!)

I’ll add that specially when it comes to playing go, professionals who are at the peak of their ability can often find the best move at a given point but be unable to explain why beyond “it feels right” or “it looks right”.