You might have seen the recent news about Open AI or more specifically DALL-E— an AI system that can generate an entire picture from a simple text command. Usually generated images look slightly unnatural – as predicted since this AI can’t physically see. Yet sometimes the images yield surprising results, below are some of my favorites.
Inputting “Salmon in a river” generates salmon fillets in a river swimming like live fish, which is super strange! You could ask anyone on the planet to describe salmon in a river – and no one would think of raw fillets in the water. We can start to see how data pollution can affect generated images. Here, there have been so many pictures of raw/cooked salmon over the actual fish, so DALL-E can’t discern the difference between the two and chooses the more popular one.
Here’s another interesting one: inputting “Chess match on a pizza”, not only do you get the physical pieces and somehow a chess board instead of cheese, but I’m especially impressed by the first image. DALL-E chose to include 2 people playing on this pizza chess board – which again shows how much input data affects this AI’s understanding of the game chess as a 1 on 1 board game rather than just pieces on a checkered board.
One last cool example of DALL-E is when inputting “Future of City of Kigali” DALL-E generates the image below:
For context, Kigali is the capital city of Rwanda, a country in central Africa. As things currently stand, they’re ranked roughly in the bottom 20% of all Nation’s Gross Domestic Products, a statistic used to show the
economic growth and output of a nation. Yet DALL-E is pretty confident that this developing nation will one day become a futuristic city with an emphasis on greenery.
All of these images show how far AI has come, especially in visualizing our world. Thinking about it, DALL-E has boiled down our complex 3d world into 1’s and 0’s that computers use, which seems a bit out there.
As an avid reader of the New York Times, I was recently captivated by this article, “A.I. Wrote These Thanksgiving Recipes. Would You Make Them?” by Priya Krishna. Krishna used another AI, Open AI’s GPT-3, a program that takes input and can give a plethora of not only recipe ideas but full measurements and instructions. Some of the inputs for GPT-3 were basic background questions like describing your heritage, to which Krishna typed:
“I am originally from Texas, and I grew up in an Indian American household. I love spicy flavors, Italian and Thai food, and desserts that are not too sweet. Some ingredients I frequently cook with are chaat masala, miso, soy sauce, herbs and tomato paste.”
Not only did this AI create full start-to-finish recipes, but also created fusions based on thanksgiving dishes and Krishna’s culture. One recipe was Pumpkin Spice Chaat, a variation of a traditional Indian dish. Not only did GPT-3 have a spark of inspiration to fuse two cultures together, but wrote introductory notes (usually tips and tricks written by the experienced chef to aid the home cook, or backgrounds on why they cooked the dish) in the voice and perspective of Krishna. Here is the full top-to-bottom recipe:
Pumpkin Spice Chaat
Written by the A.I. system GPT-3.
I grew up in an Indian American household, and I love spicy flavors. I often do not enjoy traditional Thanksgiving food because it is too bland. I like recipes that have different kinds of flavors and textures, that balance savory with sweet and spicy and tangy. This recipe for pumpkin spice chaat is perfect for my tastes! It is made with pumpkin purée, chaat masala, ginger, cloves, nutmeg, black pepper, honey, lime juice, cilantro, mango, red onion and chickpeas. It is a delicious and easy snack or side dish that is perfect for Thanksgiving.
Sidenote from Max: This introduction sounds so authentic, the voice and reasoning behind this fusion dish is so clear!!! (End sidenote)
Ingredients:
1 can pumpkin purée
1 tablespoon chaat masala
1 teaspoon ground ginger
¼ teaspoon ground cloves
½ teaspoon ground cinnamon
½ teaspoon ground black pepper
1 tablespoon olive oil
1 tablespoon lime juice
2 tablespoons chopped cilantro
¼ cup chopped roasted peanuts
½ cup yogurt
Instructions:
- In a bowl, mix together the pumpkin purée, chaat masala, ginger, cloves, cinnamon and black pepper.
- Heat the oil in a pan over medium heat. Add the pumpkin mixture and cook for 5 minutes.
- Add the lime juice and cilantro and cook for another minute.
- Serve with the peanuts, yogurt and lime wedges.
(End Recipe)
Before I describe how the dish went when Krishna actually made it, let’s revisit DALL-E for a second. Krishna decided to go a step further, inputting “Pumpkin Spice Chaat” into the image generation platform. Below, one of the images is what DALL-E generated, and one of the images is what Krishna made as per GPT-3’s instructions in her kitchen. Which is the fake one?
It turns out, the left one was generated by DALL-E. Shocking! The vivid colors, pumpkin pieces on the Chaat, dots of yogurt, not to mention the LITERAL PIECE OF PUMPKIN in the background, make the image look authentic. This trick of putting the raw ingredients in the background is something that every food blogger does – as I’m sure you’ve seen at one point or another.
Overall, Krishna rated the flavors of the Chaat as a “grassy-flavored mush”. While sure, the flavor aspects of these recipes are lacking, I’m thoroughly impressed by the depth of both recipe creation and image generation of these dishes. Maybe one day our recipes passed down from generation to generation will be indistinguishable from those generated in minutes by AI.