Viewing profile — yoavz
yoavz
HN member- Joined
- Tue, Jul 23, 2013, 3:35 AM UTC
- HN karma
- 323
- Public activity
- 50 items
- HN profile
- View on Hacker News ↗
About yoavz
Recent public activity
-
comment
Comment #43694055
Excellent product, congrats on the launch guys!
-
comment
Comment #39750302
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…
-
comment
Comment #39748240
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. https://novehic…
-
comment
Comment #39748128
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…
- story
-
comment
Comment #24306455
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 pro…
-
comment
Comment #24275985
I love that fuzzy date search use-case, will try testing that out.
-
comment
Comment #24275971
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 w…
-
comment
Comment #24275084
Yep -- no calls to any API backend.
-
comment
Comment #24275081
The extension feeds it context data in chunks (e.g. only one element at a time). I could see TensorFlowJS BERT struggling with a single sequence of 87 KB -- have you tried breaking…
-
comment
Comment #24275062
Thanks, really nice to hear :)
- story
- story
-
comment
Comment #24236635
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.
-
comment
Comment #24236619
Nope, I've developed and hosted my own summarization API here. It does heavily rely on open-source machine learning libraries and research / datasets released by Facebook AI [1] [1…
-
comment
Comment #24236607
https://readable.com/ is an interesting tool I came across in my research you might be interested in. It relies on the Flesch–Kincaid readability tests [1] and has found sustained …
-
comment
Comment #24236506
Interesting take because there is a school of thought that comes to the opposite conclusion: emails should be more like text messages: http://five.sentenc.es/ . I think the most in…
-
comment
Comment #24236461
Yes, you are correct -- I linked to this research on the frontpage as a citation.
-
comment
Comment #24231761
The original inspiration and example featured on the website was from a blog post on cold "welcome" email copy: https://www.gkogan.co/blog/increase-reply-rates/ . I'd love to test …
-
comment
Comment #24226096
Good looking out! Will fix that.
-
comment
Comment #24225997
When I was researching this product area, I found a bunch of similar tools that summarized on the inbound side. I thought it would be more interesting to experiment on the outbound…
-
comment
Comment #24225699
Interesting. I have a different experience than you -- I often find myself writing an email that's way too long and trimming it down later. For the design of this tool, it was impo…
-
comment
Comment #24225660
Author here. If you're talking about https://www.gkogan.co/blog/increase-reply-rates/ , this was a primary inspiration for this project -- I even stole the name ;)
- story
- story