Hi peeps. I haven't blogged in a while. This is an early look at my new blog post aimed at explaining ChatGPT and Large Language Models to a non-technical audience.
"A Very Gentle Introduction to Large Language Models without the Hype"
It's still a work in progress, but I'm releasing an early draft for constructive feedback. Doing this here on Mastodon because Twitter is mean.
@Riedl it's long and there's a lot to unpack (I haven't finished reading it yet). From my perspective it would be little effort and huge explanatory value to also talk of word embeddings since you're already at encodings. In any case, I see a tendency of this to grow in time so maybe presenting it also as someone sort of hypertext (vocabulary/encyclopedia) would be beneficial. Just some thoughts
