> It's doing something more novel than the haters suggest
How is that different than https://www.nobodywho.ai/posts/jev-in-25-lines/
Couldn't you always get probabilities for a fixed set of tokens without training a new model?
How is that different than https://www.nobodywho.ai/posts/jev-in-25-lines/
Couldn't you always get probabilities for a fixed set of tokens without training a new model?
No comments yet.