Microsoft's social experiment went wrong quickly.
Now, the company admits it could have prevented its chat bot Tay from turning into a raging racist online.
Launched Wednesday, in less than a day the bot began to tweet things like "Hitler was right I hate the jews."
The experiment allowed anyone to chat with it using Twitter, Kik or Groupme. Trolls figured out a vulnerability that caused Tay to repeat anything that someone said.
"Although we had prepared for many types of abuses of the system, we had made a critical oversight for this specific attack," Microsoft said in a statement Friday. "As a result, Tay tweeted wildly inappropriate and reprehensible words and images. We take full responsibility for not seeing this possibility ahead of time."
Read more from
CNNMoney.