--- title: "The Newest “Will Smith Eating Spaghetti” Video Includes AI-Generated Squelching and Chomping Sounds That Just Might Make You Sick" description: "In a new \"Will Smith eating spaghetti\" AI clip, a far more recognizable Smith can be seen indulging in a tasty-looking plate of noodles." date: "2025-05-22" modified: "2025-05-22" authors: - name: "Victor Tangermann" job_title: "Senior Editor" link: "https://futurism.com/authors/victor" url: "https://futurism.com/new-smith-eating-spaghetti-video-sounds" categories: - "Artificial Intelligence" tags: - "ai video" - "artificial intelligence" - "DeepMind" - "Google" - "video generator" --- # The Newest “Will Smith Eating Spaghetti” Video Includes AI-Generated Squelching and Chomping Sounds That Just Might Make You Sick ![In a new "Will Smith eating spaghetti" AI clip, a far more recognizable Smith can be seen indulging in a tasty-looking plate of noodles.]() *\Image: Javi Lopez via X\* Just over two years ago, we came across a [deranged, AI-generated video]() of famed actor Will Smith indulging in a bowl of spaghetti. The clip, which went viral at the time, was the stuff of nightmares, with the AI model morphing Smith's facial features in obscene ways, clearly unable to determine where his body ended and a forkful of sauce-laden pasta began. But the technology has improved dramatically since then. In a revised clip [shared by AI content creator Javi Lopez](), a far more recognizable Smith can be seen indulging in a tasty-looking plate of noodles. Unfortunately, the clip — which was rendered using Google DeepMind's just-debuted Veo 3 video generation model — includes AI-generated sound as well, exposing us to a horrid soundtrack of squelching and masticating, the equivalent of nails on a chalkboard for those suffering from misophonia. "I don't feel so good," [quipped]() tech YouTuber Marques "MKBHD" Brownlee. Nonetheless, it's an impressive tech demo, highlighting how models like Veo 3 are getting eerily close to being able to generate photorealistic video — including believable sound and dialogue. https://twitter.com/javilopen/status/1925495026903380358 Google unveiled its "state-of-the-art" Veo 3 model earlier this week at its Google I/O 2025 developer conference. "For the first time, we’re emerging from the silent era of video generation,” said DeepMind CEO Demis Hassabis during the event. Beyond generating photorealistic footage, the feature allows users to "suggest dialogue with a description of how you want it to sound," according to Hassabis. A [video sequence]() opening Google's I/O, which was generated with the tool, shows zoo animals taking over a Wild West town. Getting access to the model doesn't come cheap, with the feature [currently locked]() behind Google's $249.99-per-month AI Ultra plan. Sample videos circulating on social media are strikingly difficult to differentiate from real life. And the jury's still out on whether that's a good or a bad thing. Critics have long rung the alarm bells over tools like Veo 3 [putting human video editors]() out of a job or facilitating a [flood of disinformation]() and propaganda on the internet. **More on AI:** [*Star Wars' Showcase of AI Special Effects Was a Complete Disaster*]() ## Author I've been at Futurism since 2017, where my role has evolved to encompass design, writing, and increasingly editing. I've always been fascinated by space exploration and advanced transportation, which I've leaned into by interviewing luminaries in those fields while closely following the dimensions of policy and regulation that allow next-generation projects to succeed -- or, sometimes, to fail. I'm also keenly interested in the effects of generative AI on society, policies, and democratic institutions, as well as clean energy, physics and biology, and the vagaries of tech leadership. My work for Futurism has been cited by publications including Ars Technica, Gizmodo, PC Magazine, Jalopnik, Fox News, and the New York Post. I spent my childhood living in locations including Manila, the Philippines, and Geneva, Switzerland, attended McGill University, and now live in Toronto, Canada. Before Futurism I worked at AskMen and a small photography studio. In my free time, I'm an avid gardener, foodie, and craft beer lover, as well as a maker of artisanal hot pepper sauces. I have a magnificent dog named Freida. ### Author social links [Bluesky]()