This is very much what dspy aims to address. Learning the incantations necessary to prompt well can be replaced by an algorithmic loop and example labelled cases.
This paper is always useful to remember when someone tells you to just use the cosine similarity: https://arxiv.org/abs/2403.05440
Sure, it’s useful but make sure it’s appropriate for your embeddings and remember to run evals to check that things are ‘similar’ in the way that you want them to appear similar.
Eg is red similar to green just because they are colors
Created by Steve Ruiz, his timeline is full of little interesting thoughts played out in the development of this, a fascinating insight into the minutiae that users take for granted but that make the difference: https://twitter.com/steveruizok
Transformers suffer from a quadratic bottleneck when calculating attention. Much work has been done investigating where memory can be saved by being more explicit on which attentions to calculate. This repo implements transformers with noted improvements
for all common models (GloVe, fastText, word2vec) the means across word embeddings are tightly concentrated around zero (relative to their dimensions), thus making the widely used cosine similarity practically equivalent to Pearson correlation https://www.aclweb.org/anthology/N19-1100/
You can train programmers because there is time and there aren’t often lives at stake. Nurses have to hit the ground running in specialist areas where there is (I’d assume) often little time to acquire all necessary skills in order to perform at the required level
This is what the mypersonality dataset collected on Facebook was. The 5 axes of OCEAN - Openness, Conscientiousness, Extroversion, Agreeableness and Neuroticism for all those who took the test.
Thanks for opps daily, i was a subscriber and enjoyed thinking through the problems posted but as with others here was too busy to commit pen to paper on any of them. good luck with topstonks.com