yoavz
Joined 13 years ago
Karma
323
Submissions
51
Member since
Jul 23
http://yoavz.com
View on Hacker NewsRecent submissions
Comment · 1 year ago
Excellent product, congrats on the launch guys!
Comment · 2 years ago
Correct, it's the inverse that requires disclosure by Youtube.
Still, I find it interesting. If you can't synthetically alter someone's performance to be "worse", is it OK that the NFL synthetically altered Alicia Key's performance to be "better"?
For a more consequential example, imagine Biden's marketing team "cleaning up" his speech after he has mumbled or trailed off a word, misleading the US public during an election year. Should that be disclosed?
Comment · 2 years ago
I am not envious of the policy folks at Youtube who will have to parse out all the edge cases over the next few years. They are up against a nearly impossible task.
Comment · 2 years ago
Most interesting example to me: "Digitally altering audio to make it sound as if a popular singer missed a note in their live performance".
This seems oddly specific to the inverse of what happened recently with Alicia Keys from the recent Superbowl. As Robert Komaniecki pointed out on X [1], Alicia Keys hit a "sour note" which was silently edited by the NFL to fix it.
[1] https://twitter.com/Komaniecki_R/status/1757074365102084464
Comment · 6 years ago
This looks excellent.
In my opinion, these kinds of apps are the future of data science / data analyst work. Forget no-code, just enable these professionals to work in a single programming language that they're familar with and give them visualization superpowers. The Python ecosystem has https://www.streamlit.io/ and https://gradio.app/ now. R has https://shiny.rstudio.com/. I think we'll see more.
Comment · 6 years ago
I love that fuzzy date search use-case, will try testing that out.
Comment · 6 years ago
Pretty cool. The embedding similarity approach makes a lot of sense. I actually this project by experimenting with computing cosine similarities of sentence embeddings [1]. But I wasn't very impressed with out-of-the-box results, and I found it difficult to set a similarity threshold for a match. QA was the second try, and the pretrained models worked better out of the box. I'm wondering if I should revisit the embedding approach now...
Comment · 6 years ago
Yep -- no calls to any API backend.
Comment · 6 years ago
The extension feeds it context data in chunks (e.g. only one <p> element at a time). I could see TensorFlowJS BERT struggling with a single sequence of 87 KB -- have you tried breaking them up?
Comment · 6 years ago
Thanks, really nice to hear :)
Comment · 6 years ago
I just got access to GPT3! Have only played around with it for a few hours so far, but haven't gotten it to reliably summarize.