magicseth

Convex has a workpool component that gives the ability to compose big complicated flows in an understandable way, and give you realtime updates on status of various pieces: https://www.convex.dev/components/workflow

I am engaging with this seriously! I don't know if there will be any real solution. But I think it's worth exploring.

Yes! That's what I'm getting at. This protocol optionally allows you to sign with your private key, but you don't have to for the protocol to provide utility. It could just be enough to say "if you trust magicseth's binary and apple, then this was typed one letter at a time"

There's nothing stopping folks from typing a message an LLM wrote one at a time, but the idea of increasing the human cost of sending messages is an interesting one, or at least I thought :-(

I'm actually building a physical keyboard for those people who don't have iphones! Though given the reaction I'm seeing here, I probably won't share it with this audience :-P it has capacitive keys, a secure enclave, and a fingerprint sensor.

Oh you think it's stupid? It was an attempt to encode an encryption key that isn't sent to the server in a way that is minimally invasive. The skintone emomis allow pretty high byte density, and also are cute!

Sorry it doesn't meet your needs.

There is irony in having an ai generated humanifesto. Could it be intentional? hmm?

Is there no irony in deriding a project for being potentially LLM generated, when it's goal is to aide people in differentiating? :shrug:

phew!

It is largely written by iteration with an LLM! No need to speculate or analyze em dashes :-)

The emoji idea was mine. I like it :-) unfortunately it doesn't work in places like HN that strip out emoji. So I had to make a base64 encoding option.

The goal was to create an effective encryption key for the url hash (so it doesn't get sent to the server). And encoding skin tone with human emojis allows a super dense bit/visual character encoding that ALSO is a cute reference to the humans I'm trying to center with this project!

Hi! I want anonymity! I also want to be able to prove what level of effort has been put in to something. I think there's room for both. This is an encrypted proof that I wrote something on a keyboard that tracks fingers. The protocol allows you to optionally sign it with your identity, but that isn't strictly required.

It is an attempt at putting something into the conversation more than just "OSS is broken because there are too many slop PRs." What if OSS required a human to attest that they actually looked at the code they're submitting? This tool could help with that.

Yes LLMs were used greatly in the production of this prototype!

It doesn't change the goal of the experiment! or it's potential utility! Do you see any potential area in your world where some piece of this is valuable?

Hi! You don't need an x.com account to download, that's just the easiest way to dm me. If you're actually interested, I can let you try it! The source is also available.

It proves 1) that an apple device with a secure enclave signed it. 2) that my app signed it.

If you trust the binary I've distributed is the same as the one on the app store, then it also proves: 3) that it was typed on my keyboard not using automation (though as others have mentioned, you could build a capacitive robot to type on it) 4) that the typer has the same private key as previous messages they've signed (if you have an out of band way to corroborate that's great too) 5) optionally, that the person whose biometrics are associated with the device approved it.

There is also an optional voice to text mode that uses 3d face mesh to attempt to verify the words were spoken live.

Not every level of verification is required by the ptrotocol, so you could attest that it was written on a keyboard, but not who wrote it (not yet implemented in the client app).

The protocol doesn't require you to run my app, if you compile it yourself, you can create your own web of trust around you!

That's not what this is. at all.

If apple approves it, ive got a solution: A keyboardthat attests to your humanity https://typed.by/magicseth/2451#2NyGLfAQxmqRiAOTlaX7ma3G4d1o...

Just as shipwrecks before the advent of nuclear bombs are a source of low background radiation, troves of content like this are low-ai-contamination sources of guaranteed human media.

I suspect they might someday be valuable :-)

We built hellowonder.ai as a PWA first, and it was almost amazing! But we use voice input, and ios would pop up the microphone permission repeatedly after a few minutes, even if it had been approved recently. I couldn't figure out how to keep the microphone permission!

So frustrating to be soooo close, and then need to build an iOS app.

Well, it's part chat bot, so I don't know if it meets your criteria. But we're using them for a LOT of things behind the scenes to help kids find content they love that their parents approve of.

[HelloWonder.ai](Hellowonder.ai)

The front end looks like a chat bot, but on the backend we're using LLMs to find, parse, rate, classify, and rephrase content on the fly for individuals.

We are tackling this at hellowonder.ai . I took what I learned building ai tools at Google and built a system that does more than just block bad content for kids. It helps kids find exciting content that is aligned with their parents, effectively allowing them much more freedom.

It’s amazing how this system actually brings kids and parents closer together in practice.

Email seth@ that domain if you have kids and would like to skip the waitlist.

Awesome! Thank you for sharing. Here’s a tiny little feature idea I’ve always wanted: when a link opens a new tab, the back button should close the tab and take you back where you were!

Congratulations on launching!

thedad.blog

I'm genuinely curious how you would classify my product, Wonder an AI powered browser for kids: hellowonder.ai

Does it cross the threshold?

I believe we can use AI here :-) It is suddenly scalable to help kids develop critical thinking skills live in real time.

I've got 5 year olds, 8, 10 and a 12 year old, and they've been my beta testers for Wonder [0].

It uses AI to help direct kids towards positive content online, and defers to me to help my oldest navigate this tricky online world.

Let me know if you have kids and would like to try it out!

[0] https://gotwonder.com

As an aside, if you actually want to ask the wire cutter random questions, you can check out the green bubble in the lower left here: https://askthis.site/nytimes.com/wirecutter

I've changed my mind. Historically I've been opposed to computers being a panacea for education.

At the MIT Media Lab I was one of the earliest critics of the strategy and effects of the One Laptop Per Child project.

I've changed my mind.

There are real issues certainly, beyond AI making things up, encouraging risky behavior, or kids asking it naughty questions. Things like, can it damage a kids social skills, create echo chambers, or push them towards propaganda.

But the upside is incredible. Integrating an LLM like GPT4 into a more kid-centered suite of models unlocks tons of potential.

The first thing I built into my AI tutor system was the ability for it to look up facts from reputable websites, and to help kids answer questions for themselves.

Then I taught the AI to help a kid develop their interests, so they take a topic they're curious about and dive deeper in to it.

And then I taught the AI to notify me if there are topics that are more appropriate for a parent to engage in.

The tool I'm building actually helps kids become more curious, creative, and thoughtful.

It isn't perfect yet, but the truth is kids spend 7 hours a day on screens already. I'm very excited at the possibilities.

Let me know if you'd like to try it!

seth@gotwonder.com

Yes! This is exactly right.

I've built a tutor for my kids, that listens to them, and helps them explore topics that they're passionate about.

What's blown my mind is how it has driven creativity OFF screen too. They engage with the world in a deeper way when they have the power to explore their passions on their own.

If you want to try it, join the waitlist here: gotwonder.com and then email me: seth@gotwonder.com and I'll bump you up the list!

Is it possible to create a streaming endpoint that returns real-time transcriptions?

I've used Obsidian Git.

It definnitely takes some set up to make it work, but once working, it is pretty reliable. It requires an occasional merge conflict resolution, and setting the right files to be ignored.

I love that it is just folder with markdown files.

https://github.com/denolehov/obsidian-git

Reality Labs?

Well.... If they know how fast, they might be able to know the number :-)

https://web.archive.org/web/20121228075545/http://devblog.bu...

One of my favorite versions of this trick was invented by Martin Gardner and actually uses a timing attack... on your brain! [0] Without apparently telling the magician anything, you end up giving enough information to uniquely identify your number!

[0] https://web.archive.org/web/20121228075545/http://devblog.bu...

And this may not be the effect you are going for, but you could make the final twitter link go to a specific tweet, where you say "I was hoping you would copy the 3 of diamonds!" and it would be right :-)

Very fun! If you wanted to add one more level of misdirection, the first cards could be textarea that you have to select with your mouse and hit ctrl-c to copy ;-)

This would hide a bit of the method for the twitter reveal.

-Seth

(I also make online magic tricks magicseth.com/animal )

I'm pretty sure mine were some of the criticism you heard ;-) My critique largely focused on the imperialist attitude of the project: Negroponte described the project with hope that it would be as impactful as the "Niña, the Pinta, and the Santa Maria" without any sense of recognition of th negative impact of those ships. When the first technical bring up touted OLPC developers running Doom on it, it was a reminder of how, no matter how much we claim technology is absent of agenda, it is many ways a reflection of the values of the developers.