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
Google has a new API that tells you how "toxic" text is, h/t @taoeffect
http://perspectiveapi.com/ pic.twitter.com/gOYCdz2RAQ
-
-
-
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
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Wouldn't christian/muslim be a more appropriate comparison that christian/islam?pic.twitter.com/2Wi30MQD6m
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Amazing how a leading tech company in 2017 came up with a system no better than a 1990s Yahoo chatroom word filter _and still released it_
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
that's quite accurate.. if the gas/fumes are inhaled (w/o a fume hood), it also burns your chest, nostrils and makes you tear up/cough.
-
having tried to smell bromine that wasn't even liquid or gas, bromine that was *trapped in a polymer bottle cap*: can confirm hell out of it
End of conversation
New conversation -
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.