uwbassist

Hey, you might want to consider bert-as-service[0] for deep feature extraction from a BERT model. It will give you a 768 dimensional representation of the description, then you can embed that in the 512-dim latent space? I've been thinking of something similar.

It's not that hard to do it yourself, but it's a really clean package, and it gives you nice CLI flags for most things like pooling strategy, and what layer you want to get the activations from.

[0] https://github.com/hanxiao/bert-as-service

I'm surprised to not see any reference to "Kids These Days: Human Capital and the Making of Millennials," a well-supported account of the interactions between parenting norms and the economy. In a sentence: there is more and more pressure on parents to train their kids, so they enter the workforce more valuable to employers.

I like 80,000 hours a lot, but I think it should be balanced with Yudkowski's advice to "Purchase Fuzzies and Utilons Separately" https://www.lesswrong.com/posts/3p3CYauiX8oLjmwRF/purchase-f...

Be honest with yourself, balance your desire to do good (utilons) with your need as a human to feel good and recharge your altruism batteries by feeling connected to your good work.