I see many Winnie the Poohs at the hospital (aka Winnie aka Pooh aka Pooh Bear), as you may guess. Many look like this, a bit flat and with small wounds, designed to have a removable shirt:
They come for spas:
New hearts and stuffing:
And plumping up so they have a proper belly again:
Sometimes they look like this:
A bit more loved… or as his person said, in more “desperate condition”.
He also had a spa (not everyone does):
As you may’ve noticed, he needed a new nose and there were several options:
His heart had a pooh on it as well as some magic from a heffalump:
And after a bit of arm and smile surgery, soon he was healthy and ready to fly home:
His person wrote “He looks wonderful!”
The final Pooh I’m going to show you today just flew home yesterday. He is always called Pooh Bear. He is 14 years old and showed every year of hugs.
Here are the photos his person’s mom sent for diagnosis:
As you can see, Pooh Bear was a bit flat and a bit gray. He came in for a spa:
Got new stuffing and a magical Heffalump heart to preserve a bit of his original stuffing:
And finally was clean and plump and fluffy and ready to fly home:
He could even sit on his own! His people said his chubbiness was perfect and as I said, he flew home yesterday!
so you know how deep learning & neural network “AI training” is like, “here’s a task, and by trying billions of times the computer will eventually find the best way to achieve that task” ?
Someone is compiling a document of every time an AI ended up achieving the programmed goal in unintended ways, instead of what was actually meant, and it’s an amazing read. (you can also submit your own examples)
Creatures bred for speed grow really tall and generate high velocities by falling over
When repairing a sorting program, genetic debugging algorithm GenProg made it output an empty list, which was considered a sorted list by the evaluation metric.
Evaluation metric: “the output of sort is in sorted order” Solution: “always output the empty set”
Evolved player makes invalid moves far away in the board, causing opponent players to run out of memory and crash
Reward-shaping a soccer robot for touching the ball caused it to learn to get to the ball and vibrate touching it as fast as possible
RL agent that is allowed to modify its own body learns to have extremely long legs that allow it to fall forward and reach the goal.
Just want to come back to this post and add this amazing example as well
Heres an AI that was supposed to learn how to walk using six legs.
After many failed attempts. It decided it was easier to walk upside down
