AI Weirdness

  • About Me
  • Contact me
  • FAQ
  • Merchandise
  • My Book
  • Writing
  • Random
  • Archive
  • RSS

AI recipes are bad (and a proposal for making them worse)

pan of brownies in the oven

Pictured above is an abomination in the making, a lesson in why humans should never trust what a neural net says just because it’s based on math. It’s a neural net generated brownie recipe called Chocolate Baked and Serves, and its distinguishing feature is the CUP OF HORSERADISH it contains. It was so bad that my eyes watered as I removed it from the oven.

Creating a functional recipe requires an intimate understanding of ingredients and their interactions with one another, of heat and spice and time. Today’s neural networks have none of that.

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).

It’s seen enough cake that it can lean heavily on human-written recipes. If I prompt it with weirder recipe names - say, recipe names generated by a neural net - things get even stranger.

Crock Pot Cold Water

Ingredients:
Two 4-oz cans full of water
½ cup cornstarch
½ cup granulated sugar
3 tblsp. baking powder
1 tblsp. vanilla extract

Method:
Place water in the bottom of the slow cooker.
Place cornstarch, sugar and baking powder in a small bowl. Heat water over high heat in the slow cooker, whisking until dissolved and thick. Pour over cornstarch mixture. Add vanilla and whisk.
Place butter and lard into a small bowl. Whip together with a whisk until smooth.
Pour butter mixture over cornstarch mixture in slow cooker.

NOTE: by my reckoning this produces a very gluey, greasy mess, tasting strongly of vanilla and baking powder.

Chocolate Chicken Chicken Cake

Ingredients:
-2 cups all purpose flour
-½ teaspoon salt
-1 cup of dark brown sugar
-2 eggs
-1 teaspoon vanilla extract
-2 tablespoons vegetable oil
-¼ cup milk or other liquid if needed (it will make the cake softer if it is too warm)
-1 large chicken. Mix all ingredients and refrigerate for 30 minutes or overnight. Preheat the oven to 350 degrees.

-Gather the chicken by holding it by the top and both sides with both hands, just like you do to make meatloaf, then gently pop it into the casserole. Bake for 40 minutes or until chicken is cooked through.

-Let the cake cool completely before eating,

NOTE: if only it had decided to leave out the chicken, rather than the chocolate

Completely Meat Circle

Ingredients:
three rashers of bacon, two pieces of bacon, a whole piece of ham, two slices of smoked cheddar, four slices of prosciutto, salt, pepper, allspice, black pepper, onion powder, smoked paprika and paprika, garlic powder, paprika, parsley flakes and coriander.

You can also toast your own bacon at home: Wishing to pay homage to the original KFC’s recipe, we had one of the new wraps try to land on the BACON HOLE.

NOTE: the neural net doesn’t specify what to do with all that meat, and perhaps it’s better this way. Nor, again mercifully, does it explain what it means by BACON HOLE.

So, AI recipes are bad. How much worse could they get?

Let’s find out.

Here is a google doc form where you can submit the worst, the weirdest, the most gelatinous, that vintage American cooking has to offer. When I get enough, I’ll train a neural net to imitate them.

Already, humans have submitted “Beef Fudge” (contains marshmallow, chocolate chips, and ground beef), “Circus Peanut Jello Salad,” and “Tropical Fruit Soup” (contains banana, grapes, and a can of cream of chicken soup). God help us all.

Bonus content: Pitting neural net against neural net, I gave GPT-2 a few more classic neural net generated recipe titles to complete.

My book on AI is out, and, you can now get it any of these several ways! Amazon - Barnes & Noble - Indiebound - Tattered Cover - Powell’s

    • #neural networks
    • #recipes
    • #gpt-2
    • #BACON HOLE
    • #jello
  • 3 days ago
  • 1417
  • Permalink
Share

Short URL

TwitterFacebookPinterestGoogle+

1417 Notes/ Hide

  1. acecartoonplatypus reblogged this from pepsi-pete
  2. acecartoonplatypus liked this
  3. pepsi-pete reblogged this from adhsea
  4. pepsi-pete liked this
  5. legoliomanikas liked this
  6. schultzilla liked this
  7. vaporwary liked this
  8. adhsea reblogged this from because-im-freaking-greed
  9. alonewildbird reblogged this from lewisandquark
  10. zordonmlw7 reblogged this from hey-dairy-queen
  11. onigori reblogged this from blazingstarininkyblackness
  12. theoncomingcroat liked this
  13. chinept liked this
  14. oleanderbreeze reblogged this from lewisandquark
  15. purplemuskrat reblogged this from lewisandquark
  16. charmingpplincardigans liked this
  17. yamiya0 liked this
  18. kaijuvsgiantrobotsvsme reblogged this from wolvensnothere
  19. quest-of-the-broken-hearted liked this
  20. renee-mariposa liked this
  21. thedenofravenpuff liked this
  22. nikunei liked this
  23. plaid-swb liked this
  24. afangirls reblogged this from crazymeds
  25. cheeseriffsandjesus2112 liked this
  26. baddasshufflepuff reblogged this from mercutihoe
  27. baddasshufflepuff liked this
  28. mushroom-slut liked this
  29. cadetcarrot liked this
  30. valsedelesruines liked this
  31. lacontessa11 liked this
  32. mercutihoe reblogged this from wolvensnothere
  33. vitamin-cheese liked this
  34. shredsandpatches liked this
  35. nuclearmonster liked this
  36. sigmastolen reblogged this from lewisandquark
  37. the-lady-sprite reblogged this from stealth-science
  38. babazarathustra reblogged this from lewisandquark
  39. fucklepug liked this
  40. juiceboxxer133 liked this
  41. imgonnaneedcoffee-blog reblogged this from lewisandquark
  42. imgonnaneedcoffee-blog liked this
  43. crazymeds reblogged this from lewisandquark
  44. crazymeds liked this
  45. earthnuker liked this
  46. thehardestworkingratinshowbiz liked this
  47. remy-labelle-art liked this
  48. christophercroutons reblogged this from broliloquy
  49. christophercroutons liked this
  50. godthedyslexicdog liked this
  51. Show more notesLoading...
← Previous • Next →

Portrait/Logo

About

Welcome to my humor blog about artificial intelligence. I write about the sometimes hilarious, sometimes unsettling ways that machine learning algorithms get things wrong.

Twitter

loading tweets…

  • RSS
  • Random
  • Archive
  • Mobile
Effector Theme — Tumblr themes by Pixel Union