Artificial Intelligence Recipes Are Bad

Janelle Shane studies artificial intelligence and posts the funniest results, as we've seen before. After several attempts at training algorithms to generate recipes, and even baking brownies full of horseradish (shown above), she has completely given up all hope.

I’ve seen neural net recipes that call for crushed sherry or 21 pounds of cabbage. One of my personal favorites is a recipe called “Small Sandwiches” that called for dozens of fussily chopped, minced, and diced ingredients - before chucking them in the food processor for 3 hours. Part of the problem has been neural nets with memory so terrible that halfway through the recipe they forget they’re making cake.

More recent neural nets like GPT-2, given better long-term memory and extensive training on a huge portion of the internet, can make recipes that are more likely to pass for the real thing. Use talktotransformer.com to prompt GPT-2 with “Black Forest Cake. Ingredients:” and the quantities and ingredients will be reasonable, even if the whole thing doesn’t quite work (generating a few examples in a row, I saw some Black Forest recipes that called for kneading the batter, and one that suggested pouring the batter into a toaster).

In her latest post, Shane passes along AI recipes for Crock Pot Cold Water, Chocolate Chicken Chicken Cake (which contains chicken but no chocolate), and Completely Meat Circle. How could you possibly make these recipes worse? Shane proposes to next have a neural network study vintage American recipes, as in those abominations that rely heavily on Jell-O and condensed soup. You can submit your suggestions for that experiment. -via Metafilter


Newest 4
Newest 4 Comments

I like brownies. I like horseradish. I might try both together if the proportions seemed reasonable. I draw the line at chicken cake though.
Abusive comment hidden. (Show it anyway.)
While this is really funny, I can see why AI has so much trouble learning from existing recipes. The way we record recipes usually assumes that A. the reader knows how to eat, and 2. the reader knows a few things about cooking. A young person learning to cook with a recipe often needs guidance, or else they end up as a funny internet story. However, even a human who has never cooked has actually eaten before, and knows that chicken doesn't belong in cake, and horseradish doesn't belong in brownies. AI does not have that assumed experience.
Abusive comment hidden. (Show it anyway.)
Login to comment.
Email This Post to a Friend
"Artificial Intelligence Recipes Are Bad"

Separate multiple emails with a comma. Limit 5.

 

Success! Your email has been sent!

close window
X

This website uses cookies.

This website uses cookies to improve user experience. By using this website you consent to all cookies in accordance with our Privacy Policy.

I agree
 
Learn More