News for hackers. Stuff that matters.

farza

Re:Show HN: Turning books into chatbots with GPT-3 on Tuesday January 24, 2023 @10:11PM (#34513919)
10/10

Ask HN: If you had unlimited money for 30 minutes, what would you do?

For the sake of this question assume:- you don't have time to prepare and you only have access to a laptop w/ an internet connection.- the money is in dollars so if you somehow spend $1000 trillion you'll likely crash the world economy b/c of inflation.- all the money is coming from a magical bank that will disappear when the 30 minutes are up.- you can't access it in cash.- everyone (banks,...

( Read More... | 14 comments | 14 points | on HN )
Nice
Re:Show HN: Basilica – word2vec for anything on Wednesday October 31, 2018 @04:26PM (#18349004)
Hi there Lucy!

So, I don't know a ton about Word2Vec which probably doesn't help, but I do understand that it makes tasks, like NLP, much easier since you're going from this massive space (the english language) into a smaller embedding that you learn.

That being said, how are you embedding images? Is it based on how similar they are, if so what does "similarity" mean? Also, what dataset was leveraged?

Any more info on how you do this task would be awesome :).