[Dr_tldr]

When I put a picture of myself that had the contrast turned up my picture was rated "godlike", when I put in the original picture it was rated "hot", and when I turned down the contrast some it was rated "ok." I'm an unhealthy, almost pasty shade of white with a slightly bulbous nose and a classic fivehead.

Now, this a problem for bigger reasons:

An older picture of Denzel Washington gets an ok: http://imgur.com/Li0gZqH

A recent picture of Howard Stern gets a hot: http://imgur.com/L8hxoVK

Obviously this is just a toy and your algorithm is pretty inexact, but... you need to fix it, or at least note in giant letters that it only works for white people right now and that you're working on your algorithm to make it more universal. Because it only (kinda, sorta?) works for white people right now. If you claim something is universal in your headline then note its specificity in the fine print, you're lying. If you build an algorithm that calls most people who aren't white ugly, you need to think about the buzz-to-backlash factor of demoing it.

It's really not a good look, and you've got a week at most before you get called a "Nazi Dating App" on twitter and your potential VCs get spooked and pull out. I don't think it's intentional on your part, but literally no one cares about what your intentions are when there's an opportunity to create moral indignation clickbait. Just a friendly word of warning!

[verroq]

If people are not mature enough to understand that a machine learning algorithm cannot be racist, shouldn't you go educate them instead of telling people not to offend these idiots?

Secondly what makes you think that every race is equally attractive universally? Studies have people find people of their own race more attractive. If whites are more attractive (either by their training set or user base ratings) doesn't that merely reflect the composition of their user base?

[nonamybinnes]

If an algorithm is based on people that are racially biased ("Studies have people find people of their own race more attractive"), the algorithm is racially biased - which can or cannot be interpreted as, believe it or not, racist.

[Dr_tldr]

You have very poor reading comprehension skills, or else you appended your comment to the wrong post. Almost no part of what you're saying corresponds to anything that I said.

PS: Giving some solid advice to public-facing startups looking for funding. Definitely take the autistic high-ground on every issue. Investors don't care about bad PR, they only care about abstract principles of truth as you understand them.

[novaleaf]

he was reading between the lines. A little too much of course, but people get pretty race-sensitive when you throw around look comparisons of black/white/whatever people.