Hey @sarahjeong interviewed me, @thricedotted @robdubbin & @xor about how we create ethical bots http://motherboard.vice.com/read/how-to-make-a-not-racist-bot …
-
-
Replying to @tinysubversions
@tinysubversions any thoughts about the specific method used to bypass learning filters?1 reply 0 retweets 0 likes -
Replying to @daviottenheimer
@daviottenheimer unsure what method you're referring to1 reply 0 retweets 0 likes -
Replying to @tinysubversions
davi ((( 🐧))) 德海 Retweeted davi ((( 🐧))) 德海
davi ((( 🐧))) 德海 added,
2 replies 0 retweets 0 likes -
-
Replying to @tinysubversions
@tinysubversions nazis left a clear trail to their dictation of commandspic.twitter.com/uKI3kcKorq
1 reply 0 retweets 4 likes -
Replying to @daviottenheimer
@daviottenheimer this is what happens when you train neural net models. It understands a meta pattern like "repeat after me". Fascinating2 replies 4 retweets 18 likes -
Replying to @tinysubversions
@tinysubversions@daviottenheimer Are you saying this behaviour was emergent?2 replies 1 retweet 3 likes -
Replying to @SwiftOnSecurity
@SwiftOnSecurity@tinysubversions@daviottenheimer Seriously? Emergent? Really? Not a training tool left in/forgotten/overlooked?5 replies 0 retweets 3 likes -
Replying to @zeynep
@zeynep@SwiftOnSecurity@tinysubversions we are saying something is possible, yes. wait for further instruction1 reply 0 retweets 2 likes
@daviottenheimer @SwiftOnSecurity @tinysubversions Well please ping me when/if you know. That would be fascinating.
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.