This adorable little robot is designed to make sure its photosynthesising passenger is well taken care of. It moves towards brighter light if it needs, or hides in the shade to keep cool. When in the light, it rotates to make sure the plant gets plenty of illumination. It even likes to play with humans.
Oh, and apparently, it gets antsy when it’s thirsty.
The robot is actually an art project called “Sharing Human Technology with Plants” by a roboticist named Sun Tianqi. It’s made from a modified version of a Vincross HEXA robot, and in his own words, its purpose is “to explore the relationship between living beings and robots.”
I don’t care if it’s silly. I want one.
ok I know that for like a hundred years sci fi authors have been telling us that when we make sentient robots we’ll enslave them and treat them like garbage but I put it to you: robots that have been programmed to hover at the literal hight of cuteness, riding the line just before humans have to literally throw themselves off buildings because the robots are so fucking adorable: paralytical cuteness
This adorable little robot is designed to make sure its photosynthesising passenger is well taken care of. It moves towards brighter light if it needs, or hides in the shade to keep cool. When in the light, it rotates to make sure the plant gets plenty of illumination. It even likes to play with humans.
Oh, and apparently, it gets antsy when it’s thirsty.
The robot is actually an art project called “Sharing Human Technology with Plants” by a roboticist named Sun Tianqi. It’s made from a modified version of a Vincross HEXA robot, and in his own words, its purpose is “to explore the relationship between living beings and robots.”
I don’t care if it’s silly. I want one.
ok I know that for like a hundred years sci fi authors have been telling us that when we make sentient robots we’ll enslave them and treat them like garbage but I put it to you: robots that have been programmed to hover at the literal hight of cuteness, riding the line just before humans have to literally throw themselves off buildings because the robots are so fucking adorable: paralytical cuteness
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
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
Human: “It must be a dreary existence, unable to love, to eat, to sleep, to laugh… I feel sorry for you.” Robot: “I can laugh. I have a sense of humor, you know.” Human: “Really? I’ve never heard you laugh before.” Robot: “I’ve never heard you say anything funny.”
Hello 911 I’d like to report a violation of the First Law of Robotics, this robot just straight up murdered a human
ifesbob 