Ask HN: How do I start to learn how ChatGPT works?
I’ve dabbled in NLP a couple times in my career for basic things like NER regexes, CoreNLP and Spacy but I feel a little bit lost on where to begin for the new generation models coming out. I know they are on the bleeding edge but I’d like to have some intuition around how they work and how the data is gathered.
Is anyone able to recommend a textbook, some white papers or online classes? Stanford CS224N: NLP with Deep Learning