Twitter taught Microsoft’s AI chatbot to be a racist asshole in less than a day
It took less than 24 hours for Twitter to corrupt an innocent AI chatbot. Yesterday, Microsoft unveiled Tay — a Twitter bot that the company described as an experiment in "conversational understanding." The more you chat with Tay, said Microsoft, the smarter it gets, learning to engage people through "casual and playful conversation."
Unfortunately, the conversations didn't stay playful for long. Pretty soon after Tay launched, people starting tweeting the bot with all sorts of misogynistic, racist, and Donald Trumpist remarks. And Tay — being essentially a robot parrot with an internet connection — started repeating these sentiments back to users, proving correct that old programming adage: flaming garbage pile in, flaming garbage pile out.
Tags
Who is online
105 visitors
But while it seems that some of the bad stuff Tay is being told is sinking in, it's not like the bot has a coherent ideology. In the span of 15 hours Tay referred to feminism as a "cult" and a "cancer," as well as noting "gender equality = feminism" and "i love feminism now." Tweeting "Bruce Jenner" at the bot got similar mixed response, ranging from "caitlyn jenner is a hero & is a stunning, beautiful woman!" to the transphobic "caitlyn jenner isn't a real woman yet she won woman of the year?" (Neither of which were phrases Tay had been asked to repeat.)
It's unclear how much Microsoft prepared its bot for this sort of thing. The company's website notes that Tay has been built using "relevant public data" that has been "modeled, cleaned, and filtered," but it seems that after the chatbot went live filtering went out the window. The company starting cleaning up Tay's timeline this morning, deleting many of its most offensive remarks.
There is no link to the story there Larry, at least not that worked for me.
Thanks for the heads-up John!
That's the truest thing I've read in a long time.
Yup, my thoughts as well.
Perhaps there would be a way to use the internet as a negative filter?
An interference signal applied to normal discourse? Interesting.
There is a shitload of easily accessible data points that could be used; all at the fingertips too.