by kypro on 7/5/22, 3:13 PM
Well executed.
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.
If these systems ever become widely adopted I might seriously consider obscuring my face in public.
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.
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.
by jstanley on 7/5/22, 5:56 AM
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.
I'm glad I allowed webcam permission because it was an interesting, informative, and fun look at biometric tracking.
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.
by Bromeo on 7/5/22, 1:04 PM
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.
by NightWhistler on 7/5/22, 1:59 PM
For people worried this might be a scam: the guy in the video is Tijmen Schep and he's a privacy researcher and activist.
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.
by kuu on 7/5/22, 8:42 AM
Sharing my face with my camera with a random website? Sure, what could go wrong... /s
by luplex on 7/5/22, 11:51 AM
I stumbled across this when it launched. Here's the talk by the artist that gives some background information:
https://youtu.be/bp23r-GtdkkRather 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.
by Joeboy on 7/5/22, 9:26 AM
I was not really prepared for being told how unattractive I am this morning.
by stackbutterflow on 7/5/22, 9:52 AM
Interestingly, if you click on the ToS you end up on a page explaining how it works (can't link it).
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".
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.
This project has received funding from the European Union’s Horizon 2020 research and innovation programme, under grant agreement No 786641.
by chris_st on 7/5/22, 2:09 PM
I think it's hilarious that it decided, based on the AI algorithm, that I lied about my age!
by lampshades on 7/5/22, 1:55 PM
I scored a 9 in beauty you ugly fucks.
And my expression was happy, unlike all you normal ugly folk.
by jzellis on 7/5/22, 9:37 AM
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.
by needle0 on 7/5/22, 10:03 AM
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.)
by throwawayben on 7/5/22, 9:49 AM
It gave me an attractiveness of 9.5, and 5-10 years younger than I am, which has actually given me a big boost of confidence. How strange.
by hiisukun on 7/5/22, 12:29 PM
Some interesting tidbits:
* There's a sortof hidden/unlabelled button - did you press it?
* Did you notice the nickname you were given, slowly building up over time?
* Do you have resting sad face? Or resting happy face?
by systoll on 7/5/22, 12:35 PM
Beauty score of 10.5 out of ten?
I’ll thank our AI overlords for the compliment, but I don’t think I’m off the charts attractive.
by isaacfrond on 7/5/22, 8:58 AM
Beauty score of 5.9 out of 10. Hmm. It may be average, but that I'm still a bit peeved.
by memorable on 7/5/22, 1:10 PM
> You are more attractive than 0% of the Spice Girls.
That hurts.
by dspillett on 7/5/22, 9:45 AM
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.
by iopq on 7/5/22, 1:49 PM
I am apparently 6 BMI higher and 5 years younger now
But the way it tells me that is I lied about my age (I didn't)
by Wronnay on 7/5/22, 4:58 PM
I tried different facial expressions and could influence the model from a 8 to 9.
Kinda reminds me of SingStar where I scored better if I simply sung louder - even if I sung a completely different text...
by kennethh on 7/5/22, 8:22 AM
Pretty cool to see it guess your age and BMI. Lots of interesting information.
I also got the score violent average.
by hericium on 7/5/22, 9:55 AM
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".
by self_awareness on 7/5/22, 9:41 AM
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 ;)
by timwaagh on 7/5/22, 5:23 PM
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.
by null0pointer on 7/5/22, 10:47 AM
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.
by patrulek on 7/5/22, 9:17 AM
Almost perfectly guessed my age and BMI.
Attractiveness a lot higher than i would expect (but still in range). Could be that attractiveness is related to age and BMI?
Seems im not normal when it comes to looking at dogo (why people are so sad?)
It was fun, NGL.
by SLWW on 7/6/22, 1:12 AM
I'm violently average.
That's fantastic; I enjoyed the presentation. It's pretty revealing.
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.
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?
by kyawzazaw on 7/5/22, 9:20 PM
by rayxi271828 on 7/5/22, 11:16 AM
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...
by shubham_saboo on 7/5/22, 10:33 AM
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."
by mtbkvc on 7/5/22, 1:59 PM
just realized i'm too ugly to even have an AI gf in the future. eye-opening software for me, never considered this as an option.
by rossdavidh on 7/5/22, 5:56 PM
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.
by thegagne on 7/5/22, 4:27 PM
by cardosof on 7/5/22, 2:55 PM
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!
by karaterobot on 7/5/22, 3:03 PM
I was able to double my attractiveness by sticking out my tongue and squinting one of my eyes. Hold on for a minute while I update my tinder profile.
by wonderwonder on 7/5/22, 3:08 PM
Algorithm says I am a 4.5 on attractiveness but also says I am 12 years younger than I am. I don't know if I should feel insulted or happy. :)
by seanp2k2 on 7/5/22, 5:34 PM
Nice demo. It was off by a decade (thought I was younger, marked me down as a liar about my age lol) and obviously the beauty score was too low.
by cosmojg on 7/5/22, 1:01 PM
Time to get laser eye surgery.
by DreadLocks on 7/6/22, 7:31 AM
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.
by whoomp12342 on 7/5/22, 7:24 PM
How normal am I?
> So! Lets talk about your face
Nope nope nope nope I am gone.
by Nursie on 7/5/22, 9:19 AM
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.
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 :)
by Pakdef on 7/5/22, 11:54 AM
> 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.
> In this 'test' your face is compared with that of all the other people who came before you.
No data is sent, but your face is compared with that of all the other people that came before you....
by drakonka on 7/5/22, 7:00 PM
This is very well done! Really fun data to draw people in coupled with genuinely interesting, educational voice-over.
by tristanperry on 7/5/22, 9:48 AM
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.
It kept saying my age was 18-20, but I'm 32.
Finally it kept predicting my BMI as 30+, even though it's 22.5.
So it was interesting, and a pretty cool tech demonstration, but it wasn't too accurate for me.
by CraftingLinks on 7/5/22, 10:27 AM
Average Joe misses the point of the site.
by par on 7/5/22, 2:33 PM
It thinks I'm a lot skinnier than I actually am, and it thinks I'm uglier than I actually am. xD
by sascha_sl on 7/6/22, 7:35 AM
Adding a trans data point because it's fun how inaccurate this thing gets on edge cases
* It kept flipping between genders, pretty much exact 50% +-10%, until I put my hair down.
* BMI was flakey, but always hard out of range.
* It put me at age 16. I wish I was that young.
* Beauty score was, as expected, very not good.
by swat535 on 7/5/22, 5:48 PM
Well.. Apparently I'm violently average, got a score of 7.5 somehow.
Oh, also I'm 60% better looking than spice girls (will certainly share this with news with my fiancee when she comes back).
It also somehow guessed my BMI correctly (very close), I got 21.5 score and my BMI is 22.
Impressive work!
by WrtCdEvrydy on 7/5/22, 12:17 PM
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.
https://imgur.com/a/2bBVv4t
by astura on 7/5/22, 11:45 AM
Are these real/standard algorithms? This site though I was 30 years younger than I am.
by hirundo on 7/5/22, 2:41 PM
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.
by t0bia_s on 7/5/22, 11:23 AM
Why not just upload a portrait picture? Why camera access to random site?
by merpnderp on 7/5/22, 3:32 PM
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.
Hope he can figure out how to remove the bad data.
by Madmallard on 7/5/22, 8:51 AM
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.
by atum47 on 7/5/22, 4:02 PM
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.
by Moctogo on 7/5/22, 4:00 PM
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!
by toolz on 7/5/22, 1:35 PM
lol, my score went up two points just changing to a different webcam, also can confirm this works completely offline
guess I know which webcam I'm using from now on! xD
by pedro_hab on 7/5/22, 5:09 PM
It got a lot correctly about me, and put me at 92% normal.
I wonder if you are too far off "normal" it won't recognize you correctly, eg age.
It seems to be down rn
by shaolinspirit on 7/5/22, 9:03 AM
wow, got 8. guess I'm not that ugly as I thought.
by kansface on 7/5/22, 3:58 PM
My face was not recognized. I have glasses, a beard, and some crazy hair at the moment. Non-faced is far less normal than I expected.
by Saint_Genet on 7/5/22, 7:36 PM
I can’t help wondering how the AI would judge the clearly very attractive, but not white lady on the front page of the link.
by MrBlueIncognito on 7/5/22, 10:51 AM
Apparently there's a score of 10.1 too :D
by fnands on 7/5/22, 9:32 AM
My result:
45% Normal: "Pretty strange, in a sexy way."
Thanks, I guess? Got pretty close on age underestimated my BMI a little.
by wruza on 7/5/22, 10:24 AM
Has anyone tried sending non-face to it?
by Saint_Genet on 7/5/22, 9:06 AM
Almost got misgendered. I have long hair and shaved an hour ago, but still. Also, guessed I have a BMI of 20
by Marinus on 7/5/22, 12:26 PM
Doesn't detect the location of my face properly. Not sure if that's a good or a bad thing :-)
by kurupt213 on 7/6/22, 6:58 PM
I must be a Monet because my score keeps going up as I move my camera further from my face
by vhodges on 7/5/22, 3:13 PM
Hehe... I wrote a FB app (circa 2008) called How Normal Am I? - it got pretty popular for the time.
by mywittyname on 7/5/22, 2:34 PM
This flagged me as lying about my age because it guessed that I'm 10 years younger than I am.
by citizenpaul on 7/5/22, 3:28 PM
This won't load for me. I assume its because I have a bunch of privacy protection stuff going?
What is it?
by albinoloverats on 7/5/22, 4:14 PM
Apparently I'm a sad 5 year old girl living in the US :-/
Who knew? Because I certainly didn't.
by lom on 7/5/22, 1:52 PM
Beauty, age, gender and BMI are all just `…` for me ?
Also sad to hear that my life expectancy is only 58
by nottorp on 7/5/22, 3:09 PM
Isn't this a dupe? Or I'm mixing channels and got it some other way before.
by Alducer on 7/5/22, 12:50 PM
very inaccurate generally, and the markers for eyebrows were just in random places...
by tyiz on 7/5/22, 6:14 PM
Camera access? Nice try, bye.
by ccbccccbbcccbb on 7/5/22, 10:25 AM
Should read
"How gullible am I for uploading my face to some random data harvester?"
by davidkuennen on 7/5/22, 10:19 AM
Very educational. Well done.
by langsoul-com on 7/5/22, 11:43 AM
My beauty score is average, racist AI xD
Also, very VERY interesting and informative project.
by ksec on 7/5/22, 8:21 PM
Great website. Now I know I am not only average but a liar and ugly.
by cpfohl on 7/5/22, 11:30 AM
This was cool. Well done.
by upupandup on 7/5/22, 3:23 PM
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"
by focusedone on 7/5/22, 2:23 PM
36% Normal. "Pretty strange, in a sexy way"
OK, I'll take it.
by mechanical_bear on 7/5/22, 6:21 PM
Violently Average
by mhh__ on 7/5/22, 2:25 PM
56% of people were sad when looking at the dog
by k__ on 7/5/22, 10:59 AM
lol, I got a beauty score of 5.
Which isn't surprising, since I look like crap with that shitty cam.
by aero-glide2 on 7/5/22, 11:35 AM
Beauty less than normal, sigh
by Poppys on 7/5/22, 3:10 PM
Seems to have been overrun.
by cocochanel on 7/5/22, 2:56 PM
more attractive than 100% of the spice girls. i'll take that :)
by easrng on 7/5/22, 9:47 AM
Wow, got my age exactly!
by Shadonototra on 7/5/22, 12:55 PM
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
And who knows what they do with the sensible data they manipulate as a result
How can this still happen nowadays, what a shame and what a waste of EU money
It clearly shows their lack of direction, ethics and care
https://cordis.europa.eu/project/id/786641
Total cost
€ 2 865 947,50
What a shame