Dan Oneață @doneata.bsky.social · 05/03/2026Thanks for the answers, Benno! That was really helpful! (Sorry for replying after so long, I just didn't log in on here for a while) 010
Dan Oneață @doneata.bsky.social · 14/02/20262. The variable j seems to index two different things: a. token position (in r_j^{(l)}, Sec. 3.2); b. descriptions (in d_j and r_j, Sec. 3.1; and d_j, Sec. 3.2). I don't know if I'm missing something obvious, or this is just ambiguous. 110
Dan Oneață @doneata.bsky.social · 14/02/2026Neat work! Congratulations! I am a bit confused by some notation from the paper: 1. In Sec. 3.1 each description is associated with a single vector, but in Sec. 3.2 it seems that each description is associated with a set of vectors (contextualized representations at each positions and layer). 210
Dan Oneață @doneata.bsky.social · 28/03/2025Nice! This may be more unconventional, but Bret Victor has been thinking for some time about how to neatly integrate computer interfaces into the physical world dynamicland.orgdynamicland.orgDynamiclandIncubating a humane dynamic medium. 010
