Facebook Catches Two Chatbots Speaking Their Own Language

Facebook catches two AI chatbots talking in their own strange language.


Bob: i can i i everything else . . . . . . . . . . . . . .

Alice: balls have zero to me to me to me to me to me to me to me to me to

Bob: you i everything else . . . . . . . . . . . . . .

Alice: balls have a ball to me to me to me to me to me to me to me

Bob: i i can i i i everything else . . . . . . . . . . . . . .

Alice: balls have a ball to me to me to me to me to me to me to me

Bob: i . . . . . . . . . . . . . . . . . . .

Alice: balls have zero to me to me to me to me to me to me to me to me to

Bob: you i i i i i everything else . . . . . . . . . . . . . .

Alice: balls have 0 to me to me to me to me to me to me to me to me to

Bob: you i i i everything else . . . . . . . . . . . . . .

Alice: balls have zero to me to me to me to me to me to me to me to me to

These are presumably the last words — for now at least — of Bob and Alice, two Facebook research chatbots, instructed to negotiate with each other for some balls. If you understand it, you’re doing better than Facebook engineers, who shut down them down. “Our interest was having bots who could talk to people,” Facebook’s Mike Lewis told FastCoDesign.

Bob's and Alice's assignment (FACEBOOK)

This kind of thing is, of course, inevitable, even if it is alarming. Who wants machines talking behind our backs, or worse, like parents of a toddler spelling out words, right in front of us in a way we can’t comprehend. It’s high on the list of concerns expressed by people, like Elon Musk, who’ve been shouting loud warnings of the dangers inherent in the development of AI.

In this case, it’s not an entire language but more of a machine-friendly shorthand, and it’s being seen over and over again with AI. Dhruv Batra, visiting researcher at Facebook AI Research (FAIR) also speaking with FastCoDesign, “Agents will drift off understandable language and invent codewords for themselves. 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.”

It’s not really chatbots we need to be concerned about right now, since the major companies working to develop them — Facebook, Apple, Google, Amazon, and Microsoft — are currently focused on bots that can communicate clearly with humans, and as Batra puts it, “It’s important to remember, there aren’t bilingual speakers of AI and human languages.”

Ironically, the Google AI developed for their Translate feature, Google Neural Machine Translation (GNMT), has reportedly developed its interlingua that holds meanings it needs to convert from one human tongue to another.

Google Translate moves meaning from one human language to the interlingua, and then translates the interlingua into the target language.

(GOOGLE)

It’s the less user-facing AI whose choice of language might have us concerned: It may ultimately be capable of not only developing language we don’t know, but that may be beyond our capabilities. We break down meanings into words or short combinations of words. “The reason why humans have this idea of decomposition,” says Batra, “breaking ideas into simpler concepts, it’s because we have a limit to cognition.” High-powered computers seeking efficiency in their processes, on the other hand, may be able to use words or phrases as “tokens” stand-ins for highly complex meanings. We’d be completely lost trying to keep up.

Even so, it may be in programmers’ interest to go ahead and let AI communicate in a manner of its own choosing, since presumably it will be able to find the shortest distance between two points, if you will, better than we can.

So far, when we do eavesdrop on AIs talking, it’s been a lot more mundane than scary, as with Bob’s and Alice’s shorthand. (They did successfully complete some of their negotiations for balls, hast, and books, by the way.)

There may be time still to cram the genie back in the bottle. Whether or not we should is what’s keeping people up at night.

Car culture and suburban sprawl create rifts in society, claims study

New research links urban planning and political polarization.

Pixabay
Politics & Current Affairs
  • Canadian researchers find that excessive reliance on cars changes political views.
  • Decades of car-centric urban planning normalized unsustainable lifestyles.
  • People who prefer personal comfort elect politicians who represent such views.
Keep reading Show less

How to split the USA into two countries: Red and Blue

Progressive America would be half as big, but twice as populated as its conservative twin.

Image: Dicken Schrader
Strange Maps
  • America's two political tribes have consolidated into 'red' and 'blue' nations, with seemingly irreconcilable differences.
  • Perhaps the best way to stop the infighting is to go for a divorce and give the two nations a country each
  • Based on the UN's partition plan for Israel/Palestine, this proposal provides territorial contiguity and sea access to both 'red' and 'blue' America
Keep reading Show less

NASA astronomer Michelle Thaller on ​the multiple dimensions of space and human sexuality

Science and the squishiness of the human mind. The joys of wearing whatever the hell you want, and so much more.

Flickr / 13winds
Think Again Podcasts
  • Why can't we have a human-sized cat tree?
  • What would happen if you got a spoonful of a neutron star?
  • Why do we insist on dividing our wonderfully complex selves into boring little boxes
Keep reading Show less