When Bots Teach Themselves to Cheat
Once upon a time, a bot deep in a game of tic-tac-toe figured out that making improbable moves caused its bot opponent to crash. Smart. Also sassy. Moments when experimental bots go rogue—some would call it cheating—are not typically celebrated in scientific papers or press releases. Most AI researchers strive to avoid them, but a select few document and study these bugs in the hopes of revealing the roots of algorithmic impishness.
In 1 playlist(s)
WIRED Business
Get in-depth coverage of current and future trends in technology, and how they are shaping business,…Social links
Follow podcast
Recent clips
Microsoft’s AI Red Team Has Already Made the Case for Itself
05:34
Apps Are Rushing to Add AI. Is Any of It Useful?
05:21
Please Stop Asking Chatbots for Love Advice
08:43