EmailTriager

Rather than a GPT-3 generated email, I would rather receive the prompt that the sender would have used to generate the email.<p>We could even come up with a conventional shorthand for this.<p>Imagine you send me a message that just says [[personalized thank you note for the pair of socks you got me for christmas]]. Then I just imagine a long GPT-3 generated message in its place. And I reply with [[gracious acknowledgment and well wishes for the new year]].<p>Exactly the same intention is communicated, and we both waste less time :)

My problem with this is that it contributes to the broken culture of email.<p>– Wanna go for coffee?<p>– January is busy. After?<p>is a completely fine exchange. Adding a wall of text to convey the same information does not help anyone.

&gt; What you probably want to know is if your emails are safe! Yes, they are safe. All emails are encrypted in transit and at rest.<p>Lol - this is just what&#x27;s provide by default by https and every cloud service. It doesn&#x27;t make your emails &quot;safe&quot;. If you don&#x27;t know why, the are definitely not safe.

I’m not suggesting someone has expectations of making it big, but I think this is a great example of a gadget with zero moat. Google et al. will tidy it up and bake it into their email clients. They have an appetite for this kind of UX, given they already have the quick responses to emails.

It would be so nice to have an AI email personal assistant.<p>An AI that would read my entire inbox and give me a high-level overview of what requires my attention now, and summarizes message contents for the day. Then I can write responses only to emails which I care about.

“Write words so someone else will write more words”

Would like to see some more use cases illustrated in the marketing page besides &quot;tell people I&#x27;m busy until later for coffee meetups.&quot;<p>Most emails I exchange at work are questions to me about specific information or asking me to make specific decisions, or responses from others to specific questions I have posed to them. I don&#x27;t think this tool could be used for that, unless it had some integration into my calendar and my notes to be able to, for example, suggest a specific time for a meeting, or try to find an answer to a question from somewhere in my notes.

Now what we need is similar that can engage spammers and waste as much of their time as possible.

Here&#x27;s another one is this rapidly growing space: <a href="https:&#x2F;&#x2F;rapidreply.ai" rel="nofollow">https:&#x2F;&#x2F;rapidreply.ai</a>

After &quot;sorry, that was the autocorrect&quot;, we will have &quot;sorry, that was the AI&#x27;s response&quot;

I am starting to think that the prediction thread we had on HN the other day called it. GPT will become end up a fad with few niche ( useful, but niche ) uses, while our signal to noise ration will become even worse.<p>I do not like that one bit. I am already spending too much time deciding whether email in my box is a waste of time.

Looks fantastic. I’d be interested to know how it adds the drafts automatically and what kind of privacy access is being exchanged. I’d love if it could be done outside of email for privacy-conscious folks (I suppose ChatGPT!).<p>Does it only work with Gmail?

&gt; And drafts will magically show up in your inbox, ready to be sent.<p>One could also say, that spam magically shows up in my inbox :^) What would be really &quot;magical&quot;, if those emails showed up in &quot;Drafts&quot; folder.

A bit tangential but I am wondering now that we have brought everything online, I guess next step would be to integrate AI everywhere.<p>Consider this, you want to book your table at restaurant so you tell your AI which will inform restaurant&#x27;s AI to book a table for you. In this whole scenario where is UI? I mean this whole chat with AI thing kinda makes lot of UIs redundant. I don&#x27;t need UI for reminders, notes, meetings, search results and whole lot of other things. The advancements of AI will eat most of GUI but dashboards will remain I guess. What do you guys think?

Kind of would like &quot;train gmail on all of my sent emails and generate replies in my own sarcastic &#x2F; self deprecating style&quot;. If the request is from a certain family member make sure you reply with an appropriate level of delay to know that they are not your top priority. Inject an occasional reply with an uncharacteristic amount of emotion and sensitivity to show that you aren&#x27;t completely robotic and devoid of humanity.

More fluff and boilerplate to wade through...<p>Reminds of of an era of webdesign where about 80% of the screen real-estate was non-content.

this is a step in the wrong direction. why would I ever want a canned response, even if from AI? Phone IVR systems are already so badly &quot;programmed&quot; you objectively have to say &quot;operator&quot; over and over to reach a person.<p>In this day an age, this is all the more reason to pick up a phone and call someone.

Nice idea but not feasible for me right now, for the sole reason that now my email content ends up in the hands of OpenAI.<p>Can&#x27;t wait to see the same project using their own servers with their own text prediction models or allowing us to set up one at home!

Not long now before AI-generated emails get responded to with AI-generated responses, and humans eyes don&#x27;t see any part of it.<p>Feels somewhat pointless, although I&#x27;m sure it will increase productivity.

&quot;I&#x27;ll have my gpt mail your gpt&quot;

Those would be useful for dealing with recruiters. not so much people whom I&#x27;d actually like to get coffee with.

Seems very valuable for customer support emails. You could easily charge $50&#x2F;month for this in that market.

&gt; Note from Kevin! Bear with me, this is just an automatically generated privacy policy. I will get a real one soon.<p>&gt; What you probably want to know is if your emails are safe! Yes, they are safe. All emails are encrypted in transit and at rest. However, to use OpenAI we need to decrypt on the server before making an API request. In the future, I would love to run our own LLM completely in house so your emails never get sent to any third party ever.<p><a href="https:&#x2F;&#x2F;www.emailtriager.com&#x2F;privacy" rel="nofollow">https:&#x2F;&#x2F;www.emailtriager.com&#x2F;privacy</a><p>I sympathise with the fact that formulating a good privacy policy is difficult.<p>However, I would like to see a better, more specific privacy policy.<p>Also curious about the implications of forwarding all emails received from others to EmailTriager and to OpenAI.<p>I am sure some people will not like the idea that private communication that they write to others are made available to EmailTriager and OpenAI.

Making our social interactions even more fake. Can&#x27;t wait.