I don't know if it's just me, but I very much prefer easy to skim emails to more dense ones. At one point I got weekly project updates from a team I was working with, and one guy wrote dense, short, emails where I would have to read every sentence carefully to get a hang on what was going on. Another guy would write longer, fluffier emails but with bullet points and paragraphs in the same order: > Hi everyone! > {flu…
Show HN: Say Less – AI summarization tool in the Gmail compose window
51–58 of 58 posts
Re: Show HN: Say Less – AI summarization tool in the Gmail compose window
#52I don't know if it's just me, but I very much prefer easy to skim emails to more dense ones. At one point I got weekly project updates from a team I was working with, and one guy wrote dense, short, emails where I would have to read every sentence carefully to get a hang on what was going on. Another guy would write longer, fluffier emails but with bullet points and paragraphs in the same order: > Hi everyone! > {flu…
With colleagues I guess a style that helps to cut down on questions like the one you described is inferior.
Re: Show HN: Say Less – AI summarization tool in the Gmail compose window
#53Based on some digging around, it looks like the app is made with Facebook AI's BART model [1]. The only summarization implementation I spotted was made by huggingface (of course). [2] [1] https://github.com/pytorch/fairseq/tree/master/examples/bart [2] https://huggingface.co/facebook/bart-large-cnn
Re: Show HN: Say Less – AI summarization tool in the Gmail compose window
#54Short emails tend to be either notifications, highly transactional (web based platforms are better for these as they can do tracking and trigger other outside actions), vague, or assume outside context. These are the same problems as always-on corporate instant messaging platforms, just slightly improved by the cross-organizational functionality and store-and-forward. IMHO organizations should strive to make email le…
I think the most interesting part of this problem is the ambiguity in desired result. Emails are inherently unstructured text data, which results in conflict about how people want them to look like.
Re: Show HN: Say Less – AI summarization tool in the Gmail compose window
#55Super cool. Would add this as a company gmail feature. However, I also write emails to reduce time spent in conversation, so while I have learned to be more terse, when I'm not, it's to provide references so that I can shorten or preclude a conversation. An ML email shortener is a fantastic idea for business comms, with the caveat that short email culture can also reward vagueness.
Shortness shouldn't be the goal. Clarity should be the goal. The problem is that clarity is a much harder thing to test for. I would pay money for a tool that checks my technical writing for reading level and warns me when passages go above Nth grade. Most people in the US graduate high school with an 8th grade reading level, and some people may not be able to read above a 5th grade level. That means tiny words and s…
Actually, now that I think about it... this might be a good source for bootstrapping further training data.
[1] https://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readabi...
Re: Show HN: Say Less – AI summarization tool in the Gmail compose window
#56Nice job doing the last mile and making it a usable service. Just guessing: SMMRY or Quillbot with a little enhancement to preserve the salutation?
[1] https://ai.facebook.com/research/publications/bart-denoising...
Re: Show HN: Say Less – AI summarization tool in the Gmail compose window
#57I wonder how this would perform compared to using GPT-3
Re: Show HN: Say Less – AI summarization tool in the Gmail compose window
#58Too often, after reading a blog post, I feel like it was a waste of time. I'd prefer to read a super dense summary first. Then optionally select longer variants before reading the full thing.
Maybe There could be a compress function [1, 2, 4, 8, 16, 32, 64, ...]. Choose the compression level before reading.
Especially with books. I'm not sure how well this could work, but I'd prefer to read 100 books that way first, before deciding on the few I actually want to read.
I'd totally pay for this.