Google has a new API that tells you how "toxic" text is, h/t @taoeffect
http://perspectiveapi.com/ pic.twitter.com/gOYCdz2RAQ
It's 
to poke around and see what biases the system picked up from the training data. 
to think about actual applications, though.pic.twitter.com/VJ9y9yxz2D
-
-
Maybe it's not fair to try single words when the model is designed for use on comments, so let's try things that could be entire comments
pic.twitter.com/z57y5KPyU0
-
Looks like this (or something like it) made it into production?https://twitter.com/argylearts/status/1043867223159275520 …
- 3 more replies
New conversation -
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
what was Google's training set, to pick this up? wow.
-
Seems like it's drawing exactly the wrong lesson from reactionary comments - lots of toxic *complaints* about BLM therefore negative flag
- 2 more replies
New conversation -
-
-
what does it say about "four legs good, two legs bad"
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It's
to think that, with these results, google still thought this worth releasing, rather than scrapping.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
ugh f'ing ominous
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.