These Space Posters Are Amazing. And Then You Find Out They Were Made By NASA And They Get Even More

The phonetic alphabet. Try spelling your name!

on the topic of humans being the intergalactic “hold my beer” species: imagine an alien stepping onto a human starship and seeing a space roomba™ with a knife duct taped onto it, just wandering around the ship

it doesn’t have any special intelligence. it’s just a normal space roomba. there are other space roombas on the ship and they don’t have knives. it’s just this one. knife space roomba has full clearance to every room in the ship. occasionally crew members will be talking and then suddenly swear and clutch their ankle. knife space roomba putters off, leaving them to their mild stab wounds.

“what is the point?” asks the alien as another crew member casually steps over the knife-wielding robot. “is it to test your speed and agility?”

“no it doesn’t really go that fast,” replies the captain.

“does it teach you to stay ever-vigilant?”

“I mean I guess so but that’s more of a side effect.”

“does it weed out the weak? does it protect you from invaders? do repeated stabbings let your species heal more quickly in the future?”

“it doesn’t stab very hard, it gets us more than it gets our enemies, and no, but that sounds cool — someone write that down.”

“but then what is its purpose?”

“I don’t know,” the captain says, leaning down to give the space roomba an affectionate pat. “it just seemed cool”

happy 10 year anniversary S.T.A.L.K.E.R.

New paint colors invented by neural network

So if you’ve ever picked out paint, you know that every infinitesimally different shade of blue, beige, and gray has its own descriptive, attractive name. Tuscan sunrise, blushing pear, Tradewind, etc… There are in fact people who invent these names for a living. But given that the human eye can see millions of distinct colors, sooner or later we’re going to run out of good names. Can AI help?

For this experiment, I gave the neural network a list of about 7,700 Sherwin-Williams paint colors along with their RGB values. (RGB = red, green, and blue color values) Could the neural network learn to invent new paint colors and give them attractive names?

One way I have of checking on the neural network’s progress during training is to ask it to produce some output using the lowest-creativity setting. Then the neural network plays it safe, and we can get an idea of what it has learned for sure.

By the first checkpoint, the neural network has learned to produce valid RGB values - these are colors, all right, and you could technically paint your walls with them. It’s a little farther behind the curve on the names, although it does seem to be attempting a combination of the colors brown, blue, and gray.

By the second checkpoint, the neural network can properly spell green and gray. It doesn’t seem to actually know what color they are, however.

Let’s check in with what the more-creative setting is producing.

…oh, okay.

Later in the training process, the neural network is about as well-trained as it’s going to be (perhaps with different parameters, it could have done a bit better - a lot of neural network training involves choosing the right training parameters). By this point, it’s able to figure out some of the basic colors, like white, red, and grey:

Although not reliably.

In fact, looking at the neural network’s output as a whole, it is evident that:

The neural network really likes brown, beige, and grey.

The neural network has really really bad ideas for paint names.

by Kris Wilson

Brooklyn Nine-Nine characters as Pokémon Go teams. What team are you on?

Hi, I’m a Jehovah’s Witness wondering if you’d be interested in a gym membership over at Jehovah’s Fitness

Jfc that kitty parade music justmakes it hilarious

Be inspired