Here's my second most recent idea on how to do it, haven't written up the latest yet:
http://zeroprecedent.com/A%E2%9D%AF%E2%9D%AEON%20deck%20v.3....
Here's my second most recent idea on how to do it, haven't written up the latest yet:
http://zeroprecedent.com/A%E2%9D%AF%E2%9D%AEON%20deck%20v.3....
Feels like this is what social media is trying to achieve anyway but they're mostly stuck with the existing social graph as a starting point...
I hope this is the year we all get a thousand true friends! Instant connection every time
Yes, but how? How will it avoid optimizing on the wrong thing?
"It will gather a lot of data and then use algorithms to predict your affinities from it."
Yes, but how? What algorithm would do that? Ordinary recommender systems, neural networks, something else? And tight knit communities of close friends rarely have a lot of churn, but at-scale systems often do - how will it reconcile these tendencies?
I guess I was looking for something a little more like a research paper.
But it's obviously possible, right?
Current social networks are like those bikes with a huge front tire.
Someone make the tires equal already