AI designed this gin, but would you drink it?
Two years ago, I owned a bar with over 300 different gins — one of the largest collections of juniper-flavored spirits at any establishment in the United States. None of those gins was designed by a computer, a fact that my bartenders would likely have explained was for the best: A gin’s non-juniper botanicals are what make it distinctive, and the most popular recipes have traditionally come from experienced distillers.
But now that we’re in the AI-as-possible-gourmand era, what if a trained AI system took over the process of formulating, naming, labeling, and even marketing a new type of gin? Could Artificial Intelligence — aided somewhat by humans — create a viable product?
Somewhat surprisingly, the answer is “yes.” This weekend, Bristol, UK-based Circumstance Distillery and creative technologists Tiny Giant debuted Monker’s Garkel as “the world’s first gin created by Artificial Intelligence,” and though I was skeptical about AI’s actual role in the project, machine learning had a greater influence in the outcome than might be imagined.
Trained with a database of potential ingredients, a recurrent neural network named “Ginette” generated a range of roughly 20 recipe options with anywhere from six to nine botanicals — fair numbers given typical gin distilling recipes. Circumstance’s human distillers narrowed the list down to four options, then two, expecting that they’d prefer a mix of juniper, damson plum, fig, burdock, carrot, and cinnamon. But while “good,” that recipe turned out to be “less interesting” in flavor profile than the winning mix of juniper, coriander, angelica root, prune, gooseberry, raspberry, clementine, orange, and marigold.
Given my own experience with gins, including the knowledge that even seemingly small variations in one key ingredient might radically change the flavor of one batch of gin compared with another, I wondered just how little input people had in the final mix. So I wasn’t shocked to hear that humans selected the ultimate proportions of each ingredient, just as they’d narrowed down more viable recipes from a larger batch of AI suggestions, and kept tweaking those proportions until they properly produced layers of flavor.
I don’t like to use the word “never” when discussing AI’s ability to replace humans at various tasks. But if anything strikes me as likel