Well executed.<p>I was aware of most of the data protection and privacy concerns presented, but I wasn't aware facial recognition system are being used as widely as suggested here.<p>If these systems ever become widely adopted I might seriously consider obscuring my face in public.<p>Here in the UK I've noticed over the last year or so many supermarket self checkouts have been fitted with cameras and screens. I'm not naive enough to believe I wasn't being recorded previously, but I can't help but find this trend of sticking a camera directly in my face whenever I'm trying to make a purchase extremely insulting and violating to my sense of privacy. Now after watching this I have almost no doubt that facial recognition software is installed on these systems.<p>I've spoken to other people about the rudeness of this but most people seem to think it's fine. Perhaps I'm just weird and more bothered about this stuff than most people. If sticking a camera in someone's face when they're trying to purchase something in a pharmacy isn't going too far though I do wonder if the average person would really care about anything presented here.
I was initially put off by the webcam permission requirement, but the terms and conditions page says it's basically an art project and they don't send any data off (unless you explicitly accept it at the end) so I gave it a chance.<p>I'm glad I allowed webcam permission because it was an interesting, informative, and fun look at biometric tracking.<p>Apparently I'm "violently average" which is not a way I would previously have described myself. According to this site the most unusual thing about me is that I read the terms and conditions before ticking the "accept" box.
I think many people commenting on the model making bad predictions are missing the point.
The speaker argues that even though models are known to be inaccurate, companies like tinder or insurance companies might still use the model outputs since they have nothing better.
Therefore, in some future (or already today?) you can suffer from bad model predictions because you are "not normal enough" for the model to make good predictions, and might therefore receive a wrong predicted life expectancy and higher insurance bills.
For people worried this might be a scam: the guy in the video is Tijmen Schep and he's a privacy researcher and activist.<p>I had the pleasure of meeting him a while ago and seeing him give a talk about how companies gather data and the chilling effects on society.
I stumbled across this when it launched. Here's the talk by the artist that gives some background information:
<a href="https://youtu.be/bp23r-Gtdkk" rel="nofollow">https://youtu.be/bp23r-Gtdkk</a><p>Rather than talking about webcam permissions, I think we should talk about how much we use and rely on bad ML models. Dating apps might want to rate attractiveness, but we have no checks in place to see how we're being rated. Especially free open access models probably don't come with a thorough bias&limitations datasheet.
Interestingly, if you click on the ToS you end up on a page explaining how it works (can't link it).<p><i>The beauty scoring model was found on Github (this or this one). The models to predict age, gender and facial expression/emotion are part of FaceApiJS, which forms the backbone of this project. Do note that its developer doesn't fully divulge on which photos the models were trained. Also, FaceApiJS is bad at detecting "Asian guys".</i><p>Apparently some dating apps rates their users with these sort of algorithms. Maybe I'm living under a rock but I did not know that was a thing.<p><i>This project has received funding from the European Union’s Horizon 2020 research and innovation programme, under grant agreement No 786641.</i>
Apparently I'm just shy of being fugly and look seven years younger than I am. Which is kind of damning with faint praise, but in a dark room when I'm barely awake? I'll take it.
It underestimated my age by 15 years. Not sure if this is due to the AI being biased or simply inaccurate in general. (I'm Asian, and from the experience of me and others, Asians tend to get their age greatly underestimated in the west.)
Some interesting tidbits:<p>* There's a sortof hidden/unlabelled button - did you press it?<p>* Did you notice the nickname you were given, slowly building up over time?<p>* Do you have resting sad face? Or resting happy face?
Got my age to high, when in real life I usually get picked out as younger than I am. BMI was significantly off too. Can't argue with the not-pretty assessment though! Might give it another chance under better light later.
I tried different facial expressions and could influence the model from a 8 to 9.<p>Kinda reminds me of SingStar where I scored better if I simply sung louder - even if I sung a completely different text...
I'm mesmerized that so many of the HN crowd are willing to let some website take pictures of them in order to present some "funny/interesting results".
It guessed my age wrong, my BMI wrong, it got the thing that I came closer wrong, it got my expression wrong, and my attractiveness, which SHOULD be much higher ;)
It put me at 82% put my age at 20 (I am 34 and visibly graying). This was the project of a student of a local uni so I'm not going to put too much stock in it. But as student projects go it's pretty slick.
Surprisingly fun, I’m glad I allowed camera permission for this. My favorite subtle detail was the username on the camera view updating to reflect the different bits of information it was predicting about you.
Almost perfectly guessed my age and BMI.<p>Attractiveness a lot higher than i would expect (but still in range). Could be that attractiveness is related to age and BMI?<p>Seems im not normal when it comes to looking at dogo (why people are so sad?)<p>It was fun, NGL.
I'm violently average.<p>That's fantastic; I enjoyed the presentation. It's pretty revealing.<p>Also the computer thinks i'm a 6.9 but also decided i was 6 years older than i actually am. What a wonderfully well executed demo.<p>It makes me question how computers handle attraction vs. age. I know from personal experience that I will think someone older is more attractive if they wear their age better. I consider myself a 3-4 but that's knowing my age, could there be a case where the perceived age affects the perceived beauty?
If anyone is interested on similar type of anthropology studies, check out Qoves Studio. (They also have a similar website and also a paid service by actual persons w/ experience and degrees.)<p><a href="https://qoves.com" rel="nofollow">https://qoves.com</a>
<a href="https://www.youtube.com/channel/UCnlvhYDQLq4d_C3JYEVnWAQ" rel="nofollow">https://www.youtube.com/channel/UCnlvhYDQLq4d_C3JYEVnWAQ</a>
I like this AI more than hotornot. The AI gave me 7.2 score, while at hotornot (this was... 20 years ago, at this point?) I don't think I ever even got a 6...
When prompted GPT-3 with this and asked to come up with a funny response, here is what I got - "I don't know, I can't calculate that."
This web page is a sycophant. It told me I looked 15 years younger than I do, and said my attractiveness was several points higher than empirical evidence from my 54 years of life have told me is the case. But it did also call me a liar, so not totally a sycophant I guess.
Similar to <a href="https://stealingurfeelin.gs/" rel="nofollow">https://stealingurfeelin.gs/</a> which was created with support from Mozilla.
Based on algorithms like those, my 6-7ish beauty score would stop me from becoming a popular social media influencer if I wanted to.
Isn't that lovely!
Dreadlocked, black guy here. Got a "violently average" 72%, age was off by almost 10 years the AI thinks I am older than my real age, and my attractiveness was about 5, which given my human interactions, is very low haha. BMI was more or less accurate. Guess the training data isn't much for someone like me. Really cool though.
This is fun, but it got my age very wrong, the first run through failed to guess at all, the second run through it underestimated by 13 years.<p>It underestimated my BMI a bit, though I am losing weight at the moment and my face does seem to be getting thinner so maybe that's thrown it, and generally it told me I'm quite attractive, so ... all good :)
> No personal data is sent to our server in any way. Nothing. Zilch. Nada. All the face detection algorithms will run on your own computer, in the browser.<p>> In this 'test' your face is compared with that of all the other people who came before you.<p>No data is sent, but your face is compared with that of all the other people that came before you....
Interesting for sure. The first time I done it, I had a beauty score of 5. I then put glasses on and got better lighting, and got up to a 7.<p>It kept saying my age was 18-20, but I'm 32.<p>Finally it kept predicting my BMI as 30+, even though it's 22.5.<p>So it was interesting, and a pretty cool tech demonstration, but it wasn't too accurate for me.
Adding a trans data point because it's fun how inaccurate this thing gets on edge cases<p>* It kept flipping between genders, pretty much exact 50% +-10%, until I put my hair down.<p>* BMI was flakey, but always hard out of range.<p>* It put me at age 16. I wish I was that young.<p>* Beauty score was, as expected, very not good.
Well.. Apparently I'm violently average, got a score of 7.5 somehow.<p>Oh, also I'm 60% better looking than spice girls (will certainly share this with news with my fiancee when she comes back).<p>It also somehow guessed my BMI correctly (very close), I got 21.5 score and my BMI is 22.<p>Impressive work!
My Windows Machine has a weird bug where it uses the primary monitor as a webcam feed. Backfeeding that video gave me some interesting results.<p><a href="https://imgur.com/a/2bBVv4t" rel="nofollow">https://imgur.com/a/2bBVv4t</a>
This appears to be a modern variation of phrenology. That doesn't make it a hoax or useless, maybe phrenology was just analysing the wrong features of the head. But it should start with the same (skeptical) epistemic status.
I think the website has some bugs. The section results often appeared before the section finished loading and often the section video would never even run.<p>Hope he can figure out how to remove the bad data.
It said I was way heavier than I was, way younger than I was, and way more attractive than I am. All the while I was staring into it with good lighting. Me thinks it is not useful.
I'm more beautiful using my laptop camera (6.7) than my cellphone (5.6). I was serious on the cellphone and smiling on the laptop, this could also have tipped the scales.
Well, I apparently look like a 31 year-old to this AI although I'm 39, so I'm considered a liar by it (them/him/her?) It's time to rejoice!
lol, my score went up two points just changing to a different webcam, also can confirm this works completely offline<p>guess I know which webcam I'm using from now on! xD
It got a lot correctly about me, and put me at 92% normal.<p>I wonder if you are too far off "normal" it won't recognize you correctly, eg age.<p>It seems to be down rn
i can see this easily devolve into affiliate links to Korean cosmetic surgery hospitals. "but you could be PERFECT with just a chin tuck here...rhinoplasty there etc"
I always find it funny when .eu websites for projects sponsored by the UE are all using registrar from the USA, and probably hosting all of their data in US datacenters, including code hosted on US platforms<p>And who knows what they do with the sensible data they manipulate as a result<p>How can this still happen nowadays, what a shame and what a waste of EU money<p>It clearly shows their lack of direction, ethics and care<p><a href="https://cordis.europa.eu/project/id/786641" rel="nofollow">https://cordis.europa.eu/project/id/786641</a><p>Total cost
€ 2 865 947,50<p>What a shame