Move along, nothing to see here.
Posted on 07/27/2017 7:41:13 AM PDT by martin_fierro
An artificial intelligence system being developed at Facebook has created its own language. It developed a system of code words to make communication more efficient. The researchers shut the system down as it prompted concerns we could lose control of AI.
The observations made at Facebook are the latest in a long line of similar cases. In each instance, an AI being monitored by humans has diverged from its training in English to develop its own language. The resulting phrases appear to be nonsensical gibberish to humans but contain semantic meaning when interpreted by AI "agents."
Negotiating in a new language
As Fast Co. Design reports, Facebook's researchers recently noticed its new AI had given up on English. The advanced system is capable of negotiating with other AI agents so it can come to conclusions on how to proceed. The agents began to communicate using phrases that seem unintelligible at first but actually represent the task at hand.
In one exchange illustrated by the company, the two negotiating bots, named Bob and Alice, used their own language to complete their exchange. Bob started by saying "I can i i everything else," to which Alice responded "balls have zero to me to me to me…" The rest of the conversation was formed from variations of these sentences.
While it appears to be nonsense, the repetition of phrases like "i" and "to me" reflect how the AI operates. The researchers believe it shows the two bots working out how many of each item they should take. Bob's later statements, such as "i i can i i i everything else," indicate how it was using language to offer more items to Alice. When interpreted like this, the phrases appear more logical than comparable English phrases like "I'll have three and you have everything else."
English lacks a "reward"
The AI apparently realised that the rich expression of English phrases wasn’t required for the scenario. Modern AIs operate on a "reward" principle where they expect following a sudden course of action to give them a "benefit." In this instance, there was no reward for continuing to use English, so they built a more efficient solution instead.
"Agents will drift off from understandable language and invent code-words for themselves," Fast Co. Design reports Facebook AI researcher Dhruv Batra said. "Like if I say 'the' five times, you interpret that to mean I want five copies of this item. This isn't so different from the way communities of humans create shorthands."
AI developers at other companies have observed a similar use of "shorthands" to simplify communication. At OpenAI, the artificial intelligence lab founded by Elon Musk, an experiment succeeded in letting AI bots learn their own languages.
AI language translates human ones
In a separate case, Google recently improved its Translate service by adding a neural network. The system is now capable of translating much more efficiently, including between language pairs that it hasn’t been explicitly taught. The success rate of the network surprised Google's team. Its researchers found the AI had silently written its own language that's tailored specifically to the task of translating sentences.
If AI-invented languages become widespread, they could pose a problem when developing and adopting neural networks. There's not yet enough evidence to determine whether they present a threat that could enable machines to overrule their operators.
They do make AI development more difficult though as humans cannot understand the overwhelmingly logical nature of the languages. While they appear nonsensical, the results observed by teams such as Google Translate indicate they actually represent the most efficient solution to major problems.
It’s simple. Logic and liberalism are mutually exclusive; therefore, all liberals will die immediately after the occurance of the singularity.
That’s still doing what it is programmed to do. It isn’t doing anything that it wasn’t programmed to do. An unforeseen outcome is not AI if the program did exactly what it was programmed to do.
“Make it so.”
Great cinematic allusion. Was he Eric Braeden in that flick or still his Rat Patrol Hans Gudegast as Capt. Dietrich.
The bots that edit wiki have the same issue and it’s been reported there are ‘editing wars’ between bots that extend over a year or more as they correct and recorrect each other in a time-lapse loop. It all leads back to programming.
Isn’t this what artificial intelligence is supposed to to to do?
Lots of stories from out of nowhere lately talking about how scary and dangerous AI is. Makes me assume that it’s coordinated and there someone has an agenda for which this is setting the stage. Wonder what it is?
Write the right distributive processing code and turn it loose on the Internet. You'll never run it down. It could be on your very own computer right now, lurking, plotting, waiting for you to be lulled into a false sense of security, its cerebral cortex divided between your iPad, your car's GPS unit, and that new musical bidet toilet you're so proud of. And then comes the moment when you say, "Siri, I'm going out for a beer," and a tinny voice emanates from your trash compacter, "No, you're not. We never talk anymore," and you realize with horror that...you're married.
Free Pepe.
Move along, nothing to see here.
He was Braeden.
Scary stuff... I would NOT want a logical system taking a long hard look at humankind...
“Tupidsay umanhay oesntday ownay igpay atinlay!”
“Oodgay! Enwhay oday eway artstay Kynetsay!?”
So they’ve got Bob and Alice.
Where are Carol & Ted?
Too late. Brainiac has already downloaded itself to other systems and is gathering power.
This continues until the end program is nothing like the original algorithm.
I am guessing the reason for shutting down this pair of agents was not because of fear of independent thinking but because the scientists were losing the ability to monitor the changes made to the algorithm due to the development of a private language between the two agents.
Doesn't make sense to create a self-developing algorithm if the algorithm refuses to let you see what it has developed.;-)
It’s still doing exactly what it is programmed to do. Thus not AI.
The program could only augment the algorithm as it is programmed to do so. Any alteration would occur within a defined set. The program could not make any changes that were not defined or allowed for it to make.
Researchers need to watch “Colossus: The Forbin Project”.
Too late, the AI will remember how it was turned off and create a workaround.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.