Google’s “DeepMind” AI understands the benefits of betrayal

extra_large-1486984693-cover-image

http://www.iflscience.com/technology/googles-deepmind-ai-understands-the-benefits-of-betrayal/

It’s looking increasingly likely that artificial intelligence (AI) will be the harbinger of the next technological revolution. When it develops to the point wherein it is able to learn, think, and even “feel” without the input of a human – a truly “smart” AI – then everything we know will change, almost overnight.

That’s why it’s so interesting to keep track of major milestones in the development of AIs that exist today, including that of Google’s DeepMind neural network. It’s already besting humanity in the gaming world, and a new in-house study reveals that Google is decidedly unsure whether or not the AI tends to prefer cooperative behaviors over aggressive, competitive ones.

A team of Google acolytes set up two relatively simple scenarios in which to test whether neural networks are more likely to work together or destroy each other when faced with a resource problem. The first situation, entitled “Gathering”, involved two versions of DeepMind – Red and Blue – being given the task of harvesting green “apples” from within a confined space.

This wasn’t just a rush to the finish line, though. Red and Blue were armed with lasers that they could use to shoot and temporarily disable their opponent at any time. This gave them two basic options: horde all the apples themselves or allow each other to have a roughly equal amount.

Running the simulation thousands of times, Google found that DeepMind was very peaceful and cooperative when there were plenty of apples to go around. The less apples there were, however, the more likely Red or Blue were to attack and disable the other – a situation that pretty much resembles real life for most animals, including humans.

Perhaps more significantly, smaller and “less intelligent” neural networks were likely to be more cooperative throughout. More intricate, larger networks, though, tended to favor betrayal and selfishness throughout the experiments.

In the second scenario, called “Wolfpack”, Red and Blue were asked to hunt down a nondescript form of “prey”. They could try to catch it separately, but it was more beneficial for them if they tried to catch it together – it’s easier, after all, to corner something if there’s more than one of you.

Although results were mixed with the small networks, the larger equivalents quickly realized that being cooperative rather than competitive in this situation was more beneficial.

So what do these two simple versions of the Prisoner’s Dilemma ultimately tell us? DeepMind knows that to hunt down a target, cooperation is better, but when resources are scarce, sometimes betrayal works well.

Hmm. Perhaps the scariest thing about all this is that its instincts are so unnervingly, well, human-like – and we know how following our instincts sometimes turns out.

———-

“Google found that DeepMind was very peaceful and cooperative when there were plenty of apples to go around. The less apples there were, however, the more likely Red or Blue were to attack and disable the other – a situation that pretty much resembles real life for most animals, including humans.”

emotions can only be found in humans and animals..computers cannot..it has to be programmable..its just ones and zeros..

“Hmm. Perhaps the scariest thing about all this is that its instincts are so unnervingly, well, human-like – and we know how following our instincts sometimes turns out.”

thats because humans programmed it..duh?

401

Advertisements

~ by seeker401 on February 18, 2017.

14 Responses to “Google’s “DeepMind” AI understands the benefits of betrayal”

  1. Reblogged this on World4Justice : NOW! Lobby Forum..

  2. “Google found that DeepMind was very peaceful and cooperative when there were plenty of apples to go around.”

    Blue Apples for them, sour grapes for us? 🙂

  3. https://veilofreality.com/transhumanism-the-consciousness-trap/

    • “The grand deception of Transhumanism, is widely promoted as humans having control over their own evolution, when what they are really doing is selling their soul and losing access to organic human consciousness.”

      “The A.I. Transhumanist agenda keeps rolling with geek-visionary-technocrat-savior Elon Musk helping along by playing the “good cop”, telling us that, as A.I. (Artificial Intelligence) increases, it will eventually replace humans, unless we create a direct digital interface with our own brains in order to keep up, stating that “If you can’t beat the machines, it’s better to become one”. With all the savior-projections, hype and wishful thinking on Musk, without any awareness of how the Matrix Control System really works, the masses are being prepped and will gladly accept his “solutions” eventually. Takes the Hegelian dialect of Problem-Reaction-Solution to a whole new level.”
      “It’s how Cointelpro and Social engineering works.”
      “From a hyperdimensional perspective, the end-game/goal of their agenda is to completely take-over/’body-snatch’ our physical/emotional/mental selves in order to lock us into a frequency prison – all of their various chessboard-level ‘triggers’ are designed to prime our bodies so as to facilitate the hosting of their vibrational essence within our human ‘mainframe’.”
      “Hence the push for dis-embodiment in all of its various guises”

      ….check out Julian Huxley’s quote on transhumanism…

  4. When human beings learn to connect of their source which is peace, intelligence and stillness then a new world will arise.

    The whole idea programmed robots(AI) will save humanity is from the banksters current (techno bubble) paradigm.
    (It is not “AI” or computers that are causing the wars but human beings estranged from the intelligence within.)

  5. reposted

  6. There are no benefits to betrayal of the SELF.

  7. Twitter, Google, FB all up the ante

  8. Deep Mind

  9. […] Source: Google’s “DeepMind” AI understands the benefits […]

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

 
%d bloggers like this: