Extensive notes to accompany this talk: simonwillison.net/2023/Oct/23...
Пікірлер: 22
@Clammer9998 күн бұрын
I’m totally new to embeddings and this video inspired me to want learn even more!
@nursenayeneredit72517 ай бұрын
These 38 minutes changed my next 38 years
@technicolourmyles7 ай бұрын
How so? I'm still at the beginning
@_ramenАй бұрын
very great demo, thanks for sharing! this is an excellent example of practical use of embeddings.
@zgintasz23 ай бұрын
"vibes-based search" lol. love the term you invented.
@martinjohnpeck7 ай бұрын
This has been a timely and really useful presentation. Thank you for posting it!
@thanhquachable7 ай бұрын
Thanks Simon for sharing your knowledge. This video is so underrated.
@sebastianwagner58432 ай бұрын
Things start to become magical.
@loicleray7 ай бұрын
That was awesome. Thank you for uploading it!
@donpark28327 ай бұрын
Great talk. Thoroughly enjoyed it. Thanks!
@brandonbennett78517 ай бұрын
Brilliant!!! (as always)
@user-yg3io9mu1m7 ай бұрын
A nice and very inspiring presentation! Thank you!
7 ай бұрын
Great talk. Very interesting subject.
@vmstanford7 ай бұрын
Great work! I will definitely follow up on your website. Some of the clustering results are really remarkable. Have you thought about hierarchal clustering on the embeddings to see if a sensible taxonomy emerges?
@curtisblake2615 ай бұрын
Impressive fast talking and fast scrolling. A lot of knowledge and experience for sure. I guess I'll have to do some digging if I want to really benefit from this lecture.
@rileydavidjesus5 ай бұрын
What a genius
@miikalewandowski77657 ай бұрын
How does the semantic vectorization of a word look like, in a mathematical sense ? Is it like every word has it’s spatial ID (coordinate) and gets kind of multiplied with a vector array of assoziatives IDs?