|Artificial intelligence machine gets testy with its programmer|
|By Thom Holwerda on 2015-06-26 21:47:00|
Researchers have shown that machines are inching closer to self-learning, and perhaps even copping a little attitude.
Over at Google, a computer program using a database of movie scripts was asked again and again by researchers to define morality. It struggles to do so, and in a conversation recorded by its human engineers, becomes exasperated and ends the conversation by lashing out at its human inquisitor.
Eerie. The full paper is more interesting.
- PiDP-8/I: a modern replica of the 1968 PDP-8/I - 2017-07-11
- Improvements to the Xerox Alto Mandelbrot drop runtime - 2017-06-28
- Charles P. Thacker, designer of the Xerox Alto, passes away - 2017-06-14
- The MOnSter 6502 - 2017-05-23
- More related articles