|
|
 Originally Posted by Poopadoop
I don't know about all this, but I imagine the AI is categorising certain facial features and measurements like the size of the nose and the distance between the eyes and whatnot. So I wouldn't be surprised if the AI did possess some gaydar - like abilities.
You can do eye/nose/mouth distance. But not with a high degree of certainty. Size of nose or width of chin, as stated in the article, should be near impossible. But it's not like that's close the the only problem that study has, if it's even publicly available.
I would be very surprised tho if the algorithm used for the study actually dealt with physiological features and not just levels of flamboyancy which would be a lot easier to detect.
More generally, before criticising someone for inferring causation from correlation, it seems important to understand whether the correlation actually exists in fact or whether it exists mainly in the tattered logic of that person's own head.
Yeah, my bad. lol
Like I've already pointed out. Spoons source is most likely the title of a Daily Mail article which he misread.
|
Reply With Quote