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

Flowrite: Turn short lists of facts into well-written emails

flowrite.com

Post reply on HN
Print view View original

41–50 of 56 posts

Re: Flowrite: Turn short lists of facts into well-written emails

#41

Post by teucris »

pbronez wrote: post #5

This is an interesting interface for a sophisticated machine learning model. The user input is a moderately structured prompt (a line-delimited list of facts) and the output is text crafted for a particular medium (email). This could be extended to support output for other mediums, such as Blog posts or social media updates. It does drive me slightly crazy that this system JUST INJECTS NOISE. You provide it with conc…

> Paradoxically, I think Flowrite could improve communication by making authors and readers do MORE cognitive work rather than less.

I would love it if I could get recipients to actually devote cognitive work to my communications. Unfortunately, increasing cognitive load is a great way to ensure fewer people read what you write.

Every recipient of a message thinks differently than the writer. For communication to be effective, it must be designed for the recipients, to trigger the right sequence of ideas that will get the message across. I’ve written up the exact same content in 3 or more ways to target specific teams - bullet lists, email, slide deck, etc. It’s always worth my time. Before I did this, I would get several elaborate responses of “why didn’t you write this in X format”, arguing that X was a superior format. But everyone provided different versions of X. You may think conciseness is paramount; not only is it not, the definition of what is concise varies from person to person.

Re: Flowrite: Turn short lists of facts into well-written emails

#42

Post by pbronez »

crazypython wrote: post #17
tyingq wrote: post #11

Earlier quoted context omitted.

If the example is correct, it's injecting more than fluff and flourish. It injected "After weeks of hard work" , which doesn't seem supported by anything in the input, and probably sets the wrong tone. Certainly it was at least many months of work prior to launch.

Scroll up or go to https://www.flowrite.com/?ref=lbixer#examples to see more examples of what it can do.

The additional examples seem to integrate external knowledge. How does that work?

It expands "follow up" to "in person or via Skype / phone call" -- where did those platform preferences come from?

when asked "How about a Zoom call on the following Tuesday at 2PM?" it replies "I'll be in a Zoom meeting on Tuesday at 2PM, so let me know if that works for you." Does this mean Flowrite looked at a calendar and detected a conflicting zoom meeting? Or is it trying to accept the proposed meeting time & venue?

I do really like the Blog Outline example, where it expands a general question ("How to align your Marketing, Sales and Customer Success teams to maximize revenue?") to a list of six other questions to dig into the problem more. That might be a powerful way to push people to think more deeply and question assumptions.

Re: Flowrite: Turn short lists of facts into well-written emails

#43

Post by smallnamespace »

throwawaypls wrote: post #30
pbronez wrote: post #5

This is an interesting interface for a sophisticated machine learning model. The user input is a moderately structured prompt (a line-delimited list of facts) and the output is text crafted for a particular medium (email). This could be extended to support output for other mediums, such as Blog posts or social media updates. It does drive me slightly crazy that this system JUST INJECTS NOISE. You provide it with conc…

Isn’t this just GPT-3 under the hood? Other similar things do exist (eg: copy.ai). Not sure whether there’s much of a difference between all these GPT-3 powered services when all that distinguishes you from competition is some (slick) UI and the 500-1000 extra words of “training” you give to GPT-3.

Gwern [1], who has spent quite some time with GPT-3 and previous models, seems to think that coming up with the right 500-1000 words can be a subtle business.

Now, what's the prompt that will get GPT-3 to generate good prompts for us?

We'll call this technique Promptception.

[1] https://www.gwern.net/GPT-3#prompts-as-programming

Re: Flowrite: Turn short lists of facts into well-written emails

#44

Post by soheil »

yosito wrote: post #35
soheil wrote: post #25

Is there an API for this, I'd happily pay for that.

I'd guess this is just a little bit of training data piped into GPT-3. And yes, it's possible to pay for access to that API.

Do you have a link for access to the API? Also isn't GPT-3 invite only, not sure how to get access unless already have an invite.

Re: Flowrite: Turn short lists of facts into well-written emails

#45

Post by teucris »

soheil wrote: post #24

Yes, this is incredibly useful for customer service chats and emails. Many times people feel shortchanged if you send a concise email with the relevant facts, I guess not everyone is an engineer. Adding warmth and extra reassuring words will go a long way to keep customers happy.

I agree with this and will add that a similar thing can be said for non-technical colleagues. The humanness is critical for maintaining good relationships.

Re: Flowrite: Turn short lists of facts into well-written emails

#46

Post by chris_st »

ASalazarMX wrote: post #20
chris_st wrote: post #10

Do they have a solution to the (seemingly intractable) problem of people who only read up to the first question in an email, respond to that, and ignore the rest?

Proposal: include the short list of facts as the first paragraph.

Worth a try! I've also thought of adding, "There are three questions in this email, can you find them all?" but that seems a bit snarky.

Re: Flowrite: Turn short lists of facts into well-written emails

#47

Post by OliverJones »

Yikes! It seems to add "fluff" but it actually adds context. Where does it get the context? How is the context validated against ground truth?

How does it know it took "weeks" of work to do something?

How does it know to schedule a video call instead of, I dunno, an in-person meeting or a lunch date?

Does it learn if the human user corrects what it comes up with?

Somebody needs to rig this up like the old emacs "psychoanalyze-pinhead" hack and see whether two instances of this stuff can talk each other into some rhetorically wierd corner.

Re: Flowrite: Turn short lists of facts into well-written emails

#48

Post by gwern »

smallnamespace wrote: post #43
throwawaypls wrote: post #30

Earlier quoted context omitted.

Isn’t this just GPT-3 under the hood? Other similar things do exist (eg: copy.ai). Not sure whether there’s much of a difference between all these GPT-3 powered services when all that distinguishes you from competition is some (slick) UI and the 500-1000 extra words of “training” you give to GPT-3.

Gwern [1], who has spent quite some time with GPT-3 and previous models, seems to think that coming up with the right 500-1000 words can be a subtle business. Now, what's the prompt that will get GPT-3 to generate good prompts for us? We'll call this technique Promptception. [1] https://www.gwern.net/GPT-3#prompts-as-programming

https://arxiv.org/abs/2102.07350 already calls it "metaprompt" :) I gave it a quick stab a while ago but I think prompt programming is too new, and you can't easily cram demonstrations into an existing prompt, for it to really work well. It's more promising to train models on examples of tasks from instructions, or work on directly optimizing prompts for a goal (https://arxiv.org/abs/2101.00190) - it's a differentiable model and a whitebox, so use that power!

Re: Flowrite: Turn short lists of facts into well-written emails

#49

Post by jacobr1 »

tyingq wrote: post #22
aequitas wrote: post #19

Earlier quoted context omitted.

> It's conjuring, for example "after weeks of hard work" from thin air. I think this is not that dissimilar from a human writer. Recruiter email's come to mind as an example of this as well.

I'd hope a human writer would have guessed the effort to create a startup company and product was more than "weeks of hard work" though.

I don't know, I get both recruiter emails as a hiring manager and as a potential hire. The majority them try to be familiar, each seems to fail with a different detail. Some guess my location incorrectly, or talk about a product launch from a competitor (attributing it to us) or get our industry wrong, or present skill-sets we don't need in a way that it describes them as being a core part of our architecture, or congratulates us on vague recent successes that could potentially apply to anyone. I had one last week that congratulated me on having a recent child (not the case) from I presume some badly matched social media profile with someone sharing a similar name. I get 2-10 of these a day and I really don't see many that take the time to actual do any research. It is clear most of form-fills, based on some kind of automated data collection or just tossing a wide net.

Re: Flowrite: Turn short lists of facts into well-written emails

#50

Post by insomniacity »

pbronez wrote: post #42
crazypython wrote: post #17

Earlier quoted context omitted.

Scroll up or go to https://www.flowrite.com/?ref=lbixer#examples to see more examples of what it can do.

The additional examples seem to integrate external knowledge. How does that work? It expands "follow up" to "in person or via Skype / phone call" -- where did those platform preferences come from? when asked "How about a Zoom call on the following Tuesday at 2PM?" it replies "I'll be in a Zoom meeting on Tuesday at 2PM, so let me know if that works for you." Does this mean Flowrite looked at a calendar and detected a…

> where did those platform preferences come from?

GPT-3. Which I think is reasonable - not a lot of work to read it through and replace it with "on Zoom, or next time you're in the bay area".

Good point on the calendar though.

Post reply on HN