Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Say Less – AI summarization tool in the Gmail compose window

sayless.email

Post reply on HN
Print view View original

31–40 of 58 posts

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#31

Post by filleokus »

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!

> {fluff}

> {general status}

>

> - Bullet points of things done that week

> {comment about things done}

>

> - Bullet points of things to do next week

> {comment about potential problems etc}

>

> {fluff}

> {annoyingly long footer}

Just by parsing the number of bulletpoints, and the length of each bullet point (and the first word) I would get a surprisingly good grasp on how things were going, and what was hard/complicated (longer bullet point -> more complex), and very easy to read about exactly I wanted to know.

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#32

Post by hdfhu »

filleokus wrote: post #31

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…

This is how the so called sutras are written: a page of text gets compressed into one short sentence, so you have to stop after each of them and spend an hour unpacking its meaning, but the entire book is often just 200 sentences.

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#33

Post by petercooper »

filleokus wrote: post #31

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…

I'm the same and agree with you, but at the same time I've encountered issues with staff who disagree and who feel slighted or depersonalized by less "fluffy" prose. I think you really have to know your audience and Postel's Law applies to an extent.

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#34

Post by czbond »

Can I use this in conversations with my wife? So much talking. ;)

Joking aside - this is a great tool in corporate settings. In technology, one works with two types: Very verbose (tend to be introvert or detail oriented) or Too abbreviated. I cannot stand reading detailed accounts - and this could add to many professionals comprehending more.

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#35

Post by contingencies »

Short 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 less like instant messaging and more like letters. Fully formed thoughts distributed less frequently and with more purpose.

In short, tax hassling others.

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#36

Post by generalizations »

Based 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

#37

Post by gavinray »

sna1l wrote: post #11

I think there is still a way to go here. For example, the "really" in "really appreciate" isn't useful. Also the last sentence in the "summarized" version reads: "If for any reason you haven't let, let me know..." I would also that that the "for any reason" is not useful, it is again implied. You don't need "by now", it is implied.

Why does it seem common for people to knock modifiers for degree/intensity with words.

The statements "That's nice." and "That's really, truly nice." give off very different messages.

One of them I'm not even sure if you're being short or dismissive/not interested, and I have to do mental gymnastics to figure out what the underlying tone is.

Just one or two words makes a massive (see what I did there) difference in tone + perception.

This is half the reason why it's hard working remotely. I put so much effort into being overly polite/nice with tone because you lose out on all other social cues and it's easy to mistake an ambiguous message.

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#38

Post by FillardMillmore »

cabaalis wrote: post #8
t_serpico wrote: post #3

I've never written an email that was too long and then later realized it should have been way more concise. I generally know my intentions prior to writing the email, so if it needs to be short, I'll write it short. The reverse situation probably happens more often though (i.e I write a short email, realize it doesn't make sense due to lack of details, then I elaborate).

I intentionally write short, concise emails. It has actually backfired on me in the past: because I didn't define and explain the entire space of the matter at hand, I was overcome by other arguments or ideas that I'd already considered and dismissed. That led to followup discussions that didn't need to occur. It seems that context matters, sometimes long-form is better.

I tend to write longer e-mails - but I agree with you, long-form and short-form e-mails are both optimal for different situations.

The problem seems to be that it's a judgement call - and I'm not exactly sure of all factors/variables that are involved in that judgement call. The subject at hand, the audience, the depth of the e-mail thread to which you're replying, time-sensitivity of the subject, etc. - they all play a role. But my default position tends to be that I'll save time explaining in future e-mails by providing all relevant details at hand now.

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#39

Post by manigandham »

GordonS wrote: post #20
tylermenezes wrote: post #14

I like the idea of this product but (1) sometimes a BIT of a personal touch goes a long way (2) even in the examples you give it misses potentially important context. Eg In the board message example, it removes a reminder of the topics. How could you know those weren't necessary? Why is the number of members what it included? Just doesn't seem ready for prime-time for this use. My preference would be having it sugges…

Agreed, some people really don't like terse emails. I actually got myself into trouble a couple of years back because of this. I've been working with Norwegians almost my whole working life, and am used to being terse, direct and honest. Aside from that, I'm an extrovert, and don't talk unless I have something to say. Anyway, then I got placed as tech lead for a UK project, working remotely. Within a week, the PM had…

Why do you have to change and not them? Especially if you sat down with them and discussed it?

Re: Show HN: Say Less – AI summarization tool in the Gmail compose window

#40

Post by GordonS »

manigandham wrote: post #39
GordonS wrote: post #20

Earlier quoted context omitted.

Agreed, some people really don't like terse emails. I actually got myself into trouble a couple of years back because of this. I've been working with Norwegians almost my whole working life, and am used to being terse, direct and honest. Aside from that, I'm an extrovert, and don't talk unless I have something to say. Anyway, then I got placed as tech lead for a UK project, working remotely. Within a week, the PM had…

Why do you have to change and not them? Especially if you sat down with them and discussed it?

Because unfortunately the world doesn't revolve around me :)

It wasn't only the PM, the AI lead apparently felt the same, although I think the AI lead was the one that kicked up a fuss in the first place.

At first I was really pissed off - I didn't think I'd done anything wrong, and was completely baffled about the complaint. I went over my emails myself, and thought about calls we'd had, and I just didn't get it. TBH, I still don't understand how it could have been misconstrued, but I have to accept that it was.

Anyway, I guess the point is that while I'm terse, open and honest, not everyone else is. Consider your recipients before sending that mail - who are they, where are they from, what approach are they likely to be receptive to.

Post reply on HN