Artificial intelligence spotted inventing its own creepy language and it’s baffling researchers

AN ARTIFICIAL intelligence program has developed its own language and no one can understand it.

OpenAI is an artificial intelligence systems developer - their programs are fantastic examples of super-computing but there are quirks.

3

3

3

DALLE-E2 is 's latest AI system - it can generate realistic or artistic images from user-entered text descriptions.

DALLE-E2 represents a milestone in machine learning - OpenAI's site says the program "learned the relationship between images and the text used to describe them."

A DALLE-E2 demonstration includes for visiting users to play with and generate images - toggling different keywords will result in different images, styles, and subjects.

But the system has one strange behavior - it's its own language of random arrangements of letters, and researchers don't know why.

Read More in AI

SPOOKY SELFIE

AI 'face search engine' sparks fears as its finds pictures of you on the web

TAKING OVER

Could artificial intelligence REALLY wipe out humanity?

Giannis Daras, a computer science Ph.D. student at the University of Texas, published a detailing DALLE-E2's unexplained new language.

Daras told DALLE-E2 to create an image of "farmers talking about vegetables" and the program did so, but the farmers' speech read "" - some unknown AI word.

Daras "vicootes" back into the DALLE-E2 system and got back pictures of vegetables.

"We then feed the words: 'Apoploe vesrreaitars' and we get birds." Daras wrote on Twitter.

Most read in Tech

YOUR SPACE OR MINE?

Aliens can spot us by clocking 12 signs – even from 12,000 lightyears

ROUND THE BEND

Google Maps U-turns on frustrating change - update app now to fix it

FREE TV

Virgin Media customers unlock TWO new TV channels on their boxes at no extra cost

SPACED OUT

Jeff Bezos' satellite internet is coming - it could BOOST speeds and cut prices

"It seems that the farmers are talking about birds, messing with their vegetables!"

Daras and a co-author have written a on DALLE-E2's "hidden vocabulary".

They acknowledge that telling DALLE-E2 to generate images of words - the command "an image of the word airplane" is Daras' example - normally results in DALLE-E2 spitting out "gibberish text".

When plugged back into DALLE-E2, that gibberish text will result in images of airplanes - which says something about the way DALLE-E2 talks to and thinks of itself.

Read More On The Sun

GUN TERROR

'Mass shooting' at funeral leaves 'at least five hurt' as cops ask to avoid area

PUMPKIN SPICE

Mama June's daughter Pumpkin, 22, shows off bump in photoshoot with sisters

Some AI researchers argued that DALLE-E2's gibberish text is "".

Hopefully, we don't come to find the DALLE-E2's second language was a security flaw that needed patching after it's too late.