Thanks for the feedback. The objective is to spread kindness, regardless of the tool. Also, the final AI-generated message is provided to the user to read and then send, so "dictated but not read" is not applicable.
I think writing an inspirational message, and knowing a stranger will read your exact words, is just a fulfilling as being on the receiving end. For that reason I recommend you lose the AI component, except perhaps as a translation mechanism.
This was originally that way, but when I ran some tests, the main reason of not sending it continuously was the typing part. So, I tested this method and people became more active.
I’d rather have pre-defined templates than some AI magic button. That way you can set a mood and intent for messages without relying on an llm ( which can open up messages to be rather unkind).
Great feedback, will consider it for the next update. BTW, if you haven't noticed, you can write a message in any language yourself and send to AI to translate it optionally if it is not in English then send it or send it directly. This is the most authentic way, the AI-crafted message is for the users who prefer simpler way to spread kindness.
Doesn't a message written by an AI carry significantly less weight, though? I'd much rather read someone written by an actual human (this applies to most things, really), and would hold it in much higher regard.
thanks for the suggestion, I did:
"You’re right that the means can change the message. People often value perceived effort and authenticity, so provenance matters. The evidence is mixed: AI drafts can be rated more empathetic than typical human responses, but when recipients discover a message was machine‑authored, the benefit can vanish unless it’s disclosed and human‑edited.
So the app is designed for that reality: (1) hand‑written for people who prefer them; (2) AI‑assisted drafts that must be reviewed by the sender; and (3) clear, simple disclosure"
I think it's more tailwind CSS than the claude, the reason you see many of those colors in the recent apps is the creator uses lovable, bold, or other full agentic coders which by default use tailwind CSS
This is really nice. I’ve been experimenting with something similar but in a different angle — an app called Comfort Call that just gives you a short, realistic phone call when you need it. I built it because sometimes people don’t want another push reminder, they just need a small human-like interruption to feel less alone or to step away from a tough moment.
Well at least the undeniable impersonality should remove some of the potential hazards of telling people to get their generic cheerleading directly from a chatbot, I'd expect a much lower fraction of users to end up trying to date this thing.
Wait, what? An email address harvester that expects people to volunteer? And that tries to get the sender's geographical position along the way?
The stated purpose could be served without requiring an email address. It could also be served without assuming people will prefer an AI-generated message over their own personally crafted prose ... do such people really exist?
The second goal presumes a person's illiteracy. The first presumes a person's stupidity. Based on those facts and my sampling of recent Internet dialogues, this plan should be a roaring success.
A warning to participants -- from a legal standpoint, you can't accuse someone of stealing your email address if you volunteer it in the first place.
> ... kindness may be the only medicine for the world’s pain.
On the contrary, education is the only medicine for the world's pain. And to avoid unintended consequences, kindness must be accompanied by wisdom.
Great feedback, a couple of clarifications:
It is not an email harvester. The reason for collecting emails is to be able to send kind messages. If someone wants to unsubscribe, they can easily do so by clicking the unsubscribe button in the email they receive.
Geographical position is optional. You’re right that it can be misused in the wrong hands. The intent for requesting geographical information is:
A. Showing the country counts, which indicates how many people across the world have sent these messages.
B. Displaying it in the email so the receiver can see the place from which the sender has sent it.
But again, this is optional, as I mentioned earlier.
The AI-generated message is a secondary option. The “how it works” section explains that you can craft a message in any language yourself. The AI then checks the content to ensure it is not harmful, and it can optionally translate it if you write it in a non-English language.
And I completely agree with you that education is paramount. Thanks for bringing these matters up so I can clarify.
You say it's not an email harvester. But who are you? Are you an unkind person who tells lies about your true purposes? We don't know. Think about how this looks to someone who doesn't know you.
What the world needs is kindness. Real kindness. But it also needs people who understand basic epistemology.
That’s a fair assumption. We also need people who can trust with caution, otherwise, there wouldn’t be any transactions or exchanges in the world, since every form of transaction or exchange involves an element of trust.
I don't know if it is an email harvester or an AI experiment. But when I saw the email field, my first thought was, "Why does this service need my email to send my anonymous kind thoughts to someone?", and you lost me there - I am not going to trust a service that I know nothing about with any personal data, especially one where such personal data isn't really required for the purpose stated.
Nothing says kind message like having AI write it for you. Might as well put “dictated but not read” at the bottom of each message.
Thanks for the feedback. The objective is to spread kindness, regardless of the tool. Also, the final AI-generated message is provided to the user to read and then send, so "dictated but not read" is not applicable.
I think writing an inspirational message, and knowing a stranger will read your exact words, is just a fulfilling as being on the receiving end. For that reason I recommend you lose the AI component, except perhaps as a translation mechanism.
This was originally that way, but when I ran some tests, the main reason of not sending it continuously was the typing part. So, I tested this method and people became more active.
I’d rather have pre-defined templates than some AI magic button. That way you can set a mood and intent for messages without relying on an llm ( which can open up messages to be rather unkind).
Great feedback, will consider it for the next update. BTW, if you haven't noticed, you can write a message in any language yourself and send to AI to translate it optionally if it is not in English then send it or send it directly. This is the most authentic way, the AI-crafted message is for the users who prefer simpler way to spread kindness.
If it's the thought that counts, AI generated messages are not thought. This system is the opposite of kindness. It's dehumanizing.
Doesn't a message written by an AI carry significantly less weight, though? I'd much rather read someone written by an actual human (this applies to most things, really), and would hold it in much higher regard.
The main use case is to spread kindness and joy, crafting by hand or AI-generated are just tools to achieve that goal
There is something wrong with this position. Ask AI to explain it to you because I am too busy to do it myself.
thanks for the suggestion, I did: "You’re right that the means can change the message. People often value perceived effort and authenticity, so provenance matters. The evidence is mixed: AI drafts can be rated more empathetic than typical human responses, but when recipients discover a message was machine‑authored, the benefit can vanish unless it’s disclosed and human‑edited. So the app is designed for that reality: (1) hand‑written for people who prefer them; (2) AI‑assisted drafts that must be reviewed by the sender; and (3) clear, simple disclosure"
How did you feel when you read my response? That's how people who see through the BS will feel when they receive an AI generated note from your app.
Did Claude generate the front end? I feel like I’ve used Claude enough at this point that I can recognize its UI style :)
Yes, Windsurf + sonnet 4
gradient purple + pink color lol
they love it so much are they
I think it's more tailwind CSS than the claude, the reason you see many of those colors in the recent apps is the creator uses lovable, bold, or other full agentic coders which by default use tailwind CSS
Oh, you’re right - it’s Tailwind.
I have asked Claude to make a website with an “elegant and beautiful UI” and it used Tailwind, which gave it that look.
This is really nice. I’ve been experimenting with something similar but in a different angle — an app called Comfort Call that just gives you a short, realistic phone call when you need it. I built it because sometimes people don’t want another push reminder, they just need a small human-like interruption to feel less alone or to step away from a tough moment.
beautiful idea
Well at least the undeniable impersonality should remove some of the potential hazards of telling people to get their generic cheerleading directly from a chatbot, I'd expect a much lower fraction of users to end up trying to date this thing.
Good point, and I hope more people use it in the authentic way, which is crafting it themselves and not letting AI to generate the message.
Like clicking a button on Facebook to wish someone a happy birthday.
Except you don't know anything about who the recipient is or what their circumstance is.
Screw the Ai. I thought it was great until I saw that.
Wait, what? An email address harvester that expects people to volunteer? And that tries to get the sender's geographical position along the way?
The stated purpose could be served without requiring an email address. It could also be served without assuming people will prefer an AI-generated message over their own personally crafted prose ... do such people really exist?
The second goal presumes a person's illiteracy. The first presumes a person's stupidity. Based on those facts and my sampling of recent Internet dialogues, this plan should be a roaring success.
A warning to participants -- from a legal standpoint, you can't accuse someone of stealing your email address if you volunteer it in the first place.
> ... kindness may be the only medicine for the world’s pain.
On the contrary, education is the only medicine for the world's pain. And to avoid unintended consequences, kindness must be accompanied by wisdom.
Great feedback, a couple of clarifications: It is not an email harvester. The reason for collecting emails is to be able to send kind messages. If someone wants to unsubscribe, they can easily do so by clicking the unsubscribe button in the email they receive. Geographical position is optional. You’re right that it can be misused in the wrong hands. The intent for requesting geographical information is: A. Showing the country counts, which indicates how many people across the world have sent these messages. B. Displaying it in the email so the receiver can see the place from which the sender has sent it. But again, this is optional, as I mentioned earlier. The AI-generated message is a secondary option. The “how it works” section explains that you can craft a message in any language yourself. The AI then checks the content to ensure it is not harmful, and it can optionally translate it if you write it in a non-English language. And I completely agree with you that education is paramount. Thanks for bringing these matters up so I can clarify.
You say it's not an email harvester. But who are you? Are you an unkind person who tells lies about your true purposes? We don't know. Think about how this looks to someone who doesn't know you.
What the world needs is kindness. Real kindness. But it also needs people who understand basic epistemology.
That’s a fair assumption. We also need people who can trust with caution, otherwise, there wouldn’t be any transactions or exchanges in the world, since every form of transaction or exchange involves an element of trust.
I can trust with caution. THIS looks like a scam, with “kindness” as bait.
And if it isn’t a scam, it would remain a creepy application of AI that cheapens the idea of kindess.
I don't know if it is an email harvester or an AI experiment. But when I saw the email field, my first thought was, "Why does this service need my email to send my anonymous kind thoughts to someone?", and you lost me there - I am not going to trust a service that I know nothing about with any personal data, especially one where such personal data isn't really required for the purpose stated.
I respect your decision, and wish you the best.
do you send marketing emails to the account holder?
I don’t have a marketing agency or anything like that.
bad actors on the internet ll have a field day with this one
what security problems you could see? I'd love to know them.