Stanford researcher Ellen Kuhl's lab has published two papers introducing BurgerAI, an AI system that designs novel burger recipes tailored to individual age, taste, nutritional needs, and sustainability priorities, per a Stanford University press release and reporting in News-Medical and Nanowerk. First author Vahidullah Tac (Schmidt Science postdoctoral fellow) and the team trained BurgerAI on 2,216 burger recipes from Food.com. Kuhl explains, "Most AI systems are trained to predict what already exists. We wanted AI to invent what should exist next." In a blinded taste test with more than 100 diners at a San Francisco restaurant, AI-designed burgers matched or outperformed a popular fast-food burger on taste, while a mushroom-based variant achieved an environmental impact more than an order of magnitude lower (npj Science of Food; Stanford). The authors link BurgerAI's mathematics to diffusion-based generative approaches and argue for applications beyond food to materials science and pharmaceuticals (Nanowerk; npj Science of Food).
Show HN: Tested – AI Tools Scored by a Panel of LLMs (Claude, GPT, Gemini, Grok)