Tolerance.ca
Director / Editor: Victor Teboul, Ph.D.
Looking inside ourselves and out at the world
Independent and neutral with regard to all political and religious orientations, Tolerance.ca® aims to promote awareness of the major democratic principles on which tolerance is based.

AI robots can go rogue – a researcher on how easily it happens

By Fazl Barez, Senior Researcher in AI safety, interpretability and technical governance, University of Oxford
In tests, AI robot systems easily rejected directly malicious commands. But their safety filters collapsed when creative writing was used to instruct them.The Conversation


Read complete article

© The Conversation -
Subscribe to Tolerance.ca


Follow us on ...
Facebook Twitter