![](https://lemmy.ml/pictrs/image/68d981c0-5b48-491b-adf4-4aa0cce1a676.jpeg)
![](https://lemmy.ml/pictrs/image/q98XK4sKtw.png)
https://arewereorganizedyet.com/ lol already updated
https://arewereorganizedyet.com/ lol already updated
I am thinking the meant the Icelandic Freyja chocolate instead? Spelling in the greentext doesn’t match either though.
Major Kovalyov: “Am I a joke to you?”
Don’t drive like my brother!
And now I’m wondering in the -ihkal suffix is known outside the Shulgin fanbase…
Toilet paper I have known and loved?
I think that is overly simplistic. Embeddings used for LLMs do definitely include a concept of what things mean and the relationship of things to other things.
E.g., compare the embeddings of Paris, Athens, and London to other cities and they will have small cosine distance between them. Compare France, Greece, and England and same. Then very interestingly, look at Paris - France, Athens - Greece, London - England and you’ll find the resulting vectors all align (fundamentally the vector operation seems to account for the relationship “is the capital of”). Then go a step further, compare those vector to Paris - US, Athens - US, London - Canada. You’ll see the previous set are not aligned with these nearly as much but these are aligned with each other (relationship being something like “is a smaller city in this countrry, named after a famous city in some other country”)
The way attention works there is a whole bunch of semantic meaning baked into embeddings, and by comparing embeddings you can get to pragmatic meaning as well.
One of the best parts of living in the SF bay area is literally anywhere you go isn’t particularly expensive per what you are used to. My wife and I went out to a particularly fancy restaurant on Santorini and the bill was less than we’ve often paid in Berkeley.