Published June 10, 2021
On the unreasonable effectiveness of data "So, follow the data. Choose a representation that can use unsupervised learning on unlabeled data, which is so much more plentiful than labeled data. Represent all the data with a nonparametric model rather than trying to summarize it with a parametric model, because with very large data sources, the data holds a lot of detail. For natural language applications, trust that human language has already evolved words for the important concepts. See how far you can go by tying together the words that are already there, rather than by inventing new concepts with clusters of words. Now go out and gather some data, and see what it can do." https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/35179.pdf
Reminder to buy industrial/military/commercial, restaurant, or scientific equipment because they actually work, and there's real, human consequences if they don't "Consumer goods suck. You keep buying them." https://neil.computer/notes/overkill-objects-for-everyday-life/