Artificial intelligence spotted inventing its own creepy language – New York Post

An artificial intelligence program has developed its own language and no one can understand it.

OpenAI is anartificial intelligencesystems developer their programs are fantastic examples of super-computing but there are quirks.

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

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

A DALLE-E2 demonstration includesinteractive keywordsfor 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 itswritingits own language of random arrangements of letters, and researchers dont know why.

Giannis Daras, a computer science Ph.D. student at the University of Texas, published aTwitter threaddetailing DALLE-E2s 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 vicootes some unknown AI word.

Darasfedvicootes 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.

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

Stay up on the very latest with Evening Update.

Daras and a co-author have written apaperon DALLE-E2s 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.

Some AI researchers argued that DALLE-E2s gibberish text is random noise.

Hopefully, we dont come to find the DALLE-E2s second language was a security flaw that needed patching after its too late.

This article originally appeared onThe Sunand was reproduced here with permission.

See original here:
Artificial intelligence spotted inventing its own creepy language - New York Post