Godlike Productions - Discussion Forum
Users Online Now: 1,022 (Who's On?)Visitors Today: 195,618
Pageviews Today: 339,390Threads Today: 117Posts Today: 2,347
06:07 AM


Rate this Thread

Absolute BS Crap Reasonable Nice Amazing
 

Ditch humans or cooperate? Google’s DeepMind tests ultimate AI choice with game theory

 
Anonymous Coward
User ID: 37723324
Ireland
02/10/2017 10:36 AM
Report Abusive Post
Report Copyright Violation
Ditch humans or cooperate? Google’s DeepMind tests ultimate AI choice with game theory
DeepMind, the London-based artificial intelligence unit of Google’s parent Alphabet Inc. has been running a series of simulations aimed at answering a key AI question once and for all: will the robots play nice, or will they try and kill us all? ..

In the first game, the two agents must compete to gather as many apples as possible, .. However, there is a twist: both players are armed with a ray gun and can stun the other player at any time, immobilizing them for a brief period, allowing the aggressor to gather more resources unimpeded..

The DeepMind team found that the greater the level of intelligence applied (or larger the neural network supporting the software agent), the more aggressive the software agents became..

[link to www.rt.com (secure)]
Anonymous Coward
User ID: 73734099
United States
02/10/2017 12:11 PM
Report Abusive Post
Report Copyright Violation
Re: Ditch humans or cooperate? Google’s DeepMind tests ultimate AI choice with game theory
Of course. The object is to win the game isn't it?
Unless cooperation with a competitor has advantages then you would zap the suckka.
Anonymous Coward
User ID: 73734099
United States
02/10/2017 12:12 PM
Report Abusive Post
Report Copyright Violation
Re: Ditch humans or cooperate? Google’s DeepMind tests ultimate AI choice with game theory
The Ray Kroc approach.





GLP