Infosecurity.US

Information Security & Occasional Forays Into Adjacent Realms

  • Web Log

Joscha Bach, Ph.D., 'The Lebowski Theorem of Machine Superintelligence' →

April 18, 2018 by Marc Handelman in Machine Learning, Information Security, Reward and Punishment, Philosophy, Superintelligence

via Jason Kottke, comes a Lebowski Cogitation with sterling credentials, in which, the Dude wades in with his take on machine learning (in reality {if you like that sort of thing} via a twitter message by Joscha Back, Ph.D,); utilizing the non-virtual Jeffrey Lebowski (whom, of course, abides, if only on celluloid, and bits on the wire,) as the vector:

'No superintelligent AI is going to bother with a task that is harder than hacking its reward function.' - The Lebowski Theorem - Joscha Back, Ph.D.

April 18, 2018 /Marc Handelman
Machine Learning, Information Security, Reward and Punishment, Philosophy, Superintelligence
  • Newer
  • Older