Marco Tempest holds the role of Creative Technologist at the NASA Jet Propulsion Laboratory, is an alumnus of the MIT MediaLab’s Director’s Fellowship, and serves as the Founder and Director of the MagicLab situated in New York City. Blending his expertise in technology and stage magic, Tempest embodies Arthur C. Clarke’s renowned assertion that “Any sufficiently advanced technology is indistinguishable from magic.” His unique talent lies in leveraging illusion to prototype cutting-edge technologies, crafting immersive user experiences that offer a glimpse into the future of technology, allowing users to interact with tomorrow’s innovations today. This approach yields valuable insights into user interactions with emerging technologies.
Recently, Tempest unveiled his latest creation, a narrative centered around Ada Lovelace, the pioneering computer programmer, reimagined through real-time AI storytelling. Describing the project, Tempest explained, “The piece is rendered on a laptop with a webcam using Nvidia’s Ada Lovelace architecture, showcasing the very essence of her vision — machines capable of creating art.”
Ada Lovelace, a pivotal figure in computer development, was a fitting choice for this innovative storytelling approach. In 1833, at just 17 years old, Lovelace crossed paths with Charles Babbage, a visionary scientist seeking funding for a sophisticated calculating machine known as “The Difference Engine.” Programmed using punch cards akin to the looms of the era, Lovelace undertook the task of developing a program for these cards. Her foresight envisioned machines with the potential to generate art—a vision realized nearly two centuries later.
To bring this narrative to life, Tempest harnessed the power of open-source software such as ComfyUI, Stable Diffusion, OBS, OSC, NDI, and locally operated models on his laptop, with tailored enhancements to facilitate live storytelling with AI. Employing an iPhone equipped with a customized app for video segmentation, Tempest’s performance was seamlessly captured, with the app adeptly removing backgrounds, tracking hand movements, and streaming video and positional data to the live performance setup.
Behind the scenes, Tempest utilized ComfyUI, a rapid open-source LLM with a web interface, to generate images and video sequences. Developing a bespoke workflow capable of managing pre-programmed prompts for AI image generation, he integrated computer vision elements orchestrated by Aximmetry show control software. This comprehensive setup handled video compositing, timeline management, gesture recognition, music playback, voice cloning cues, and dynamic parameter adjustments, allowing autonomous content selection and rendering during performances.
Renowned for his captivating use of digital technologies to engage audiences, Marco Tempest has established a reputation for delivering immersive and astonishing experiences. A regular speaker at TED conferences, Tempest’s mission across his career has remained consistent: to inspire, simplify complex topics, effectively convey messages, captivate, innovate, and nurture ideas with the belief that with adequate care and support, nothing is unachievable.
