So I’ve used neural networks to generate recipes in the past. They’re computer programs that can learn to imitate the data we give them, copying the way that humans drive cars, label images, or translate languages.
That is, they try to learn. They’re called “neural” because they have virtual neurons that work a little like the real neurons in our brains. Their virtual brains, however, are really tiny. Where a human has about 86 billion neurons, the neural networks we use today have hundreds to low thousands - think nematode worm or, optimistically, jellyfish. So they often struggle, and recipes, my friends, are one of those times. (you haven’t lived until you’ve seen a neural net’s attempt at “small sandwiches”)
I turned to cocktails, inspired by Beth Skwarecki’s cocktails bot (and helped immensely by the dataset she sent me).
The neural net’s first attempt was… an attempt.
I let it train for a little longer, and things got a little more recognizable, as it learned to kinda spell more ingredients.
It had, however, not learned when to quit. 64-ounce (2 liter) cocktails are not unheard of at this stage.
It continued to learn on its own, all without input from me, and eventually ended up with cocktails that were almost plausible.
Some of my other training attempts, however, did not go so well. At first the cocktail titles in my training set were in all caps, which confused the heck out of the neural net because capital letters were so rare that it didn’t see enough examples of what to do with them. It struggled with the titles.
You may also notice that the ill-fated all-caps attempt had a lot of repetition - that’s because I was using textgenrnn, which has a somewhat limited memory. It could learn to spell ingredients, but had no idea whether it had already added sugar and cream. When I switched to char-rnn for the lowercase recipes above, I could give it a memory of 50 characters, enough to cut down on repetition. The textgenrnn version, however, became strangely obsessed with creme de cacao. The less said about its cocktails, the better.
For more neural net cocktails (including custom-generated cocktails for any name you care to provide), check out Beth’s cocktails bot!
For a few more of the cocktails I generated (including some very unfortunately-named ones), you can sign up here, and optionally get bonus material every time I post.
Okay I used to HATE roses as a symbol of romance and shit or whatever until I learned why they’re signs of love bc it’s the most metal creation myth of all time
Well ok have y’all ever heard of the goddess of love Aphrodite?
So in greek mythology, all of the roses were white. all of em with no exception. white. remember this detail, it’s important to the story
so basically one day, our local love bitch Aphrodite was bragging to the other gods about how she could make anyone fall in love with anyone, because she was the goddess of love, and everyone got kind of irked with her bragging bc it was annoying, and Zeus (in his Zeus way) decided to pull a BIG PRANK on Aphrodite by making her fall in love w this mortal named Adonis. Adonis was a hunter, and this made Aphrodite CRAZY because hunting is super dangerous, and she was thirsty for Adonis right & she didn’t want him to die. EXCEPT therein lies the prank, bc Zeus MADE Adonis get gored by a wild boar (rip) and he died.
and here’s where the thing with the red roses come in. Bc all the roses are white, right? And right as Adonis was about to die, Aphrodite SWOOPED DOWN FROM THE HEAVENS in a golden chariot pulled by swans on a slide made of clouds (a cloud slide). as she rushed to his side, Aphrodite pricked her foot on a rose thorn and her blood landed on the petals of the rose, and all of the roses around her became red with her blood as she mourned for her dead lover who was killed in the hunt by a violent wild boar, all bc Zeus wanted Aphrodite to stop boasting.
tl;dr: red roses are a sign of romance bc they were originally white, but the red ones are red because they’re dipped in the blood of the goddess Aphrodite as she mourned the death of her lover
Here, have this bouquet of “Zeus Is a Dick” flowers.
90% of greek mythology is zeus being a huge pile of cunt
So there’s these computer programs called artificial neural networks that are good at imitating things. By seeing examples of what humans did, they can learn to translate languages, predict product sales, and even categorize text and images as innocuous or explicit (it has a lot of trouble with this last task, as it turns out).
One neural network I use, called textgenrnn, tries its best to imitate any kind of text you give it. I’ve given them paint colors, bandnames, and even guinea pig names and in each case their results are somewhat… mixed. (Paint colors called Stanky Bean, Stargoon, and Turdly, for example) The problem is that it doesn’t know what any of these words mean - it’s just picking letter combinations that seem likely to it.
This is what happened when I gave it all the cookies from a list of American recipes. This is what human cookies sound like to a neural network.
Now if you’ll excuse me, I’m going to go whip up a batch of Fluffin Coffee Drops.
For more cookies, including the neural net’s strange obsession with “balls,” as well as bonus material every time I post, you can sign up here.
