I was once on 25th street in Midtown, when I saw someone drop a tiny object with a little parachute from a window at least 8 or 9 stories up. Once it had finished slowly gliding down to the street, someone picked it up and used it to enter the building. It was the key - I guess the buzzer didn't work! It was a delightful sight.
I can’t believe I watched a story of using AI to drop hats on people and calling it drop shipping turn into a debate about parties, buzzkills and the risk of addictive substances vs “annoying” people against hat drop shipping and similar ideas, a discussion on the legal bounds of unwanted hat drop shipping, the effect of stray hats on babies and a quantitative analysis on the environmental impact of objects dropped from apartment windows in NYC. Followed by another debate on the mental effect of objects dropping from apartments in cities with skyscrapers. This is amazing.
This is the best thing I've seen on HN or indeed on the internet in general for quite a long time. Excellent work and thank you for brightening my day.
I love this kind of project.<p>A lot of states are working on legislation that includes requirements for watermarking AI generated content. But it seldom defines AI with any rigor, making me wonder if soon everyone will need to label everything as made with AI to be on the safe side, kinda like prop 65 warnings.
This concept is great, it’s also a brilliant idea for a webcam on a Bourbon St balcony in New Orleans to throw beads at parties below. I am friends with a guy who owns a multistory bar in the middle of the strip and would be open to this, so if OP or someone else is interested in developing an AI/remote control bead thrower, drop some contact info and I’ll reach out
I am seeking neighboring stores! Sometimes I crave gum on the street, Gum drop anyone?<p>To summarize, I used:<p>1. Low weight but very cool product (like Propeller Hats)<p>2. Raspberry Pi for controlling everything<p>3. Adafruit stepper motor for the dropping mechanism<p>4. Yarn for holding the hat<p>5. Roboflow for the AI
What an unexpectedly cool post, I clicked the link thinking it would be "typical dumb", but it ended up being atypically dumb in the greatest way! Fascinating. The author overcame many challenges and wrote about them in a style as if he solved the hardest parts with only a little fiddling. Maybe he's already seasoned in the ML and robotics domains? So much fun to read.<p>Regarding the Video Object Detection:<p>Why does inference need to be done via Roboflow SaaS?<p><pre><code> ...(api_url="https://detect.roboflow.com", api_key="API_KEY")
</code></pre>
Is it because the Pi is too underpowered to run a fully on-device solution such as Frigate [0] or DOODS [1]? And presumably a Coral TPU wasn't considered because the author mostly used stuff he happened to have laying around.<p>Can anyone comment contrasting experience with Roboflow? Does it perform better than Frigate and DOODS?<p>Asking for a friend. I totally don't have announcement speakers throughout my house that I want to say "Mom approaching the property", "Package delivered", "Dog spotted on a walk", "Dog owner spotted not picking up after their beast", and so on. That last one will be tricky to pull off. Ah well :)<p>[0] <a href="https://github.com/blakeblackshear/frigate/pkgs/container/frigate">https://github.com/blakeblackshear/frigate/pkgs/container/fr...</a><p>[1] <a href="https://github.com/snowzach/doods2">https://github.com/snowzach/doods2</a>
If the goal is to make a window-based store, then why do you need AI at all? Just release the hat once payment goes through.<p>This reminds me of thousands of blockchain projects that used the technology to flip on light switch.
Love this! I play recreational ice hockey in an Adult league and for the past many years I've desired to use AI/Object recognition to recognize who was out on the ice during what times during the game to attribute who impacted goals and which players were taking longer than usual shifts ( every team has those one or two players!).<p>This may be achievable for me with the current state of AI and GPT to help fill the gaps that my knowledge is lacking in. Thanks for showing what you made and how you did it. It's encouragement to me.
> Picture a world where you can walk around New York City and everything you need is falling out of windows onto you. At a moments notice, at the drop of a hat. That's a world I want to live in. That's why I'm teaching you how to do yourself. Remember this as the first place you heard of "Window Shopping."<p>I truly love the concept of pun-driven development (PDD). As a motivating economic principle, a world where every human being has the resources, time, and personal safety to dedicate absurd amounts of their time to inane levels of pun-driven development is perhaps my favorite definition of utopia.
I feel like such a killjoy, but the first thing I thought of is the ongoing lice “epidemic” among people with school aged children in NYC.<p>I have never liked it when the ACs drip on me in midtown let alone a hat dropping on my head!
Fun demo, but it would work just as well for the customer to tap something on their phone (or even send/reply to an SMS) to trigger the hat-drop, and be much, much simpler, and likely more reliable. It looks like it isn't capable of actually placing the hat on the customer's head (it lands on the ground nearby), so the camera and AI stuff is only acting as a trigger, not a guide.<p>And presumably if another random person happens to stop inside the right sidewalk tile for at least 3 seconds during the 5-minute window, before the actual customer gets there, they'll get the hat instead!
This is so cool and just brings me a lot of joy :)<p>Also, I've been working on a project (non-commercial) that looks down on people and have found existing models don't work super well from that angle so thank you for publishing your work on Roboflow.
It would be cool to make something similar for a pet feeder. Imagine having two cats (like we do). A skinny one and a fat one. AI would recognize them and dispense more food for the skinny one throughout the day. Hmm... :-)
Fantastic, I love this kind of silly stuff. The clear next iteration is a 4-prop hat, which can be guided to the target head.<p>Of course, that starts to verge on what's spooky about the idea, but either way, this is really fun and cool.
I'm confused. The article describes a really cool project as if it were already implemented, but there is no video of it actually working? Am I missing something?
Love the creativity and humor which is often the spark for true innovation.This guy is a real life Kramer from Seinfeld. Reminds me of the episode where Kramer drops a ball of oil from his nyc apartment while testing a business idea.
This is fake and an ad, right?<p>Why 800+ votes for a thing that obviously doesn't do what it claims to be doing, and shows pictures and videos of it <i>not</i> doing the thing?
This is cool. It reminded me of a dream project in my backlog: I want to build a fan that tracks my head when I workout and always blows at my face.<p>Do y’all think a similar stack/setup (raspberry pi and python3 and this model thing he linked to) would be a good starting point? I prefer to use a more “algorithm” solution than a full blown model (I mean cameras have had face detection since what, the early 2000s?).<p>Anyway, curious to hear any suggestions.
This is a clever use of AI marketing. I'd still be interested in "I'm using computers to drop hats outside my window onto New Yorkers."
I really want to use llama3 8B Q4_0 llama.cpp for some fun automation tasks so I tried following this guide: <a href="https://voorloopnul.com/blog/quantize-and-run-the-original-llama3-8b-with-llama-cpp/" rel="nofollow">https://voorloopnul.com/blog/quantize-and-run-the-original-l...</a> but all I get out of it is rambling nonsense. Glad ollama exists I guess, running that works fine for me.
> Picture a world where you can walk around New York City and everything you need is falling out of windows onto you.<p>A funny way of criticizing something. Great commentary.
Can you go a bit more in depth for the part regarding training the Ai to recognize the heads? Like what software(s) did you use ecc... I'm an undergrad who's seeking to do similar computer vision internships for his thesis and I find this kinda fascinating
This makes me really miss the Stupid Shit hackathon, this seems like a perfect project for it.<p><a href="https://stupidhackathon.com/" rel="nofollow">https://stupidhackathon.com/</a>
I don't know what is more impressive: that someone thought of such a whacky idea or that they actually implemented it. It's very creative and I can see someone who thinks like this seeing opportunities others wouldn't.
Really, really liked it! Also, would be glad to hear where you got that helicopter heads. I've been looking for one for some time but my head is large sized so I can't find one that fits here where I live.
> My dream is for all the city windows to be constantly dropping things on us all the time. You will need a Raspberry Pi...<p>A Raspberry Pi would hurt quite a bit, depending on the floor!
Reminds me a bit of jafflechutes: <a href="http://jafflechutes.com/whatis.html" rel="nofollow">http://jafflechutes.com/whatis.html</a>
Once superintelligence takes over all jobs, as it is claimed will happen (, and there is an AIBI : AI Basic Income), I hope we are free to do more such projects :)
The vision of a world where you need a sandwich on your way to work and it just drops on your head is both hilarious and something I really need in my life.
Thanks, I am happy to notify you that I archived your post in my hall of fame (and in the internet archive). Kudos!
<a href="https://archive.tunnelsenpai.win/archive/1719179282.959772/index.html" rel="nofollow">https://archive.tunnelsenpai.win/archive/1719179282.959772/i...</a>
Title is very misleading. I initially thought this is a high-tech prank.<p>TLDR: Not just any "New Yorkers", but specifically "customers who want to buy a propeller hat". And hats are dropped not "onto", but "somewhere on the sidewalk next to" these New Yorkers. And sure, this might be "using AI", but AI seems like an overkill to recognize that a person is standing longer than three seconds under the window.<p>So a guy sells hats by dropping them out of the window. Not sure why there are so many comments praising this. Is it because of the pun? Am I missing something?
I have a few qualms with this AI-assisted hat delivery service[1]:<p>1. For a Linux user, you can already build such a system yourself quite
trivially by getting a kaggle account, learning by doing computer vision
projects, and then using opencv to build the vision parts of the system. From
Windows or Mac, you could build using a cloud system such as Amazon Bedrock.<p>2. It doesn't actually replace having a hat for the period from your own front
door to OP's apartment. Most people I know own hats themselves or borrow from
friends to be able to attend specific events, but they still carry a hat in
case there are weather problems. This does not solve the availability issue.<p>3. It does not seem very "viral" or income-generating. I know this is
premature at this point, but without charging users for the service, is it
reasonable to expect to make money off of this?<p>[1] Actually I don't. It's really awesome.
This seems wonderful. I’m in New York next weekend and wanted to buy a hat, but sadly you’re all booked up. Too bad.<p>Although since it only takes a few seconds, I’d expect you to be able to sell thousands of these a day. If you don’t mind me asking, how many slots do you release each day?
It seems I'm in a minority thinking this is not that great... wind can blow the hat (or the thing from the generalized idea) into traffic, or onto a baby, or any other place to upset people. Also, if the recipient can't/doesn't pick the thing up, then it's littering. From the technical perspective finding heads in a video is not that impressive nowadays... So, I don't get all the excitement...
I will be honest, while the project is actually neat, it showcases some of the issues with technological advancements as related to society ( and happens to also touch on one's exposure in a big city ). One could easily imagine a scenario ( or scenarios ), where this could be misused.