Scientists Try to Teach AI to Create Children’s Book Art — AI Creates an Apocalyptic Nightmare from Hell Instead

| |

Top Tier Gear USA


Well, this is certainly comforting (in much the same way getting a hug from a rabid, starving polar bear would be considered “comforting”).

A team of scientists attempted to train a deep learning algorithm to recognize illustrations from thousands of pages of children’s books including those by authors Dr. Seuss, Marc Brown, and Maurice Sendak. They used not one or even two but three models to do it: ALexNEt, VGG-19 and GoogLeNet.

Should be no problem easy peasy pie, right?

Wrong. What came out the other end was either a bunch of stuff being set on fire in what looks like the pits of hell, or something strikingly similar to puddles of cartoon blood spatter.

Here’s a smiling turtle… lit on fire by AI:


Here’s a city scene… which AI turned into an apocalyptic nightmare from hell:


Here’s what used to be a little girl…:


And here’s what happens to Cat in the Hat drawings:


The AI was supposed to learn how to recognize individual objects, such as an eye, a car, a tree, etc.


This is what happened instead.

If this is the way AI programmed by our best and brightest computer scientists sees our world, then I can’t wait for it to take it over and run the whole show, can you?


Delivered by The Daily Sheeple

We encourage you to share and republish our reports, analyses, breaking news and videos (Click for details).

Contributed by Piper McGowin of The Daily Sheeple.

Piper writes for The Daily Sheeple. There’s a lot of B.S. out there. Someone has to write about it.

Wake The Flock Up! Please Share With Sheeple Far & Wide:
  • William the Resolute

    What makes you think the creators thought it a failure….?

    • It is always entertaining to see what people who have never programmed a computer and couldn’t do it to save their lives think about what happens when human-programmed artificial intelligence software goes awry. If they already had Dr. Suess, why did they need the computer to recreate it?

      • This was to be expected; the technology simply isn’t there yet. We are making big strides towards autonomy though.

        • For every stride that we make forward in technology, we take two steps back in education of the population. Alex Jones uses the correct word in calling this technocracy. The problem is that the number of people who will be able and willing to support technocracy is dropping with the general literacy rate. Eventually the technocrats will be unable to keep their system operating. The banksters are already in a frenzy trying to figure out how to keep their debt-based system open for business as they approach an unserviceable level and are running out of willing and able lenders. Autonomy isn’t possible in worldwide scams of such a magnitude.

          • Exactly. I saw an article on TDS that even stated that lenders were quickly becoming more risk-averse with their investments, which is usually the sign of a bearish market, and stagflation.

  • SleepKnowMore

    Computers only do what they are programmed to do… even really smart ones. Perhaps one day we will program one to filter out fake news stories.

    • GAZOO2

      The goal is for them to think on their own.

    • We just program them out by not watching CNN, MSNBC, ABC, FOX NEWS, CBS, etc and not going to their websites. Rather simple solution, actually. If everyone did it there would be no more fake news. Fake news exists because fake people exist.

  • G’ma G

    Frankly, Sendak and Suess on top of Brown? Of course you are going to get composite pictures that look scary.

  • The road to hell is paved with good intentions.

  • The Tuna Fairy

    Some of that looks like the Deep Dream results, those can be tweaked for different effects. You can tweak anything to make it look evil. Looks like that’s all the same filters running.
    If you haven’t played with Deep Dream, it’s interesting…