In this position paper, we review the eclectic recent history of academic and artistic works involving computational systems for humor generation, and focus specifically on live performance. We make the case that AI comedy should be evaluated in live conditions, in front of audiences sharing either physical or online spaces, and under real-time constraints. We further suggest that improvised comedy is therefore the perfect substrate for deploying and assessing computational humor systems. Using examples of successful AI-infused shows, we demonstrate that live performance raises three sets of challenges for computational humor generation: 1) questions around robotic embodiment, anthropomorphism and competition between humans and machines, 2) questions around comedic timing and the nature of audience interaction, and 3) questions about the human interpretation of seemingly absurd AI-generated humor. We argue that these questions impact the choice of methodologies for evaluating computational humor, as any such method needs to work around the constraints of live audiences and performance spaces. These interrogations also highlight different types of collaborative relationship of human comedians towards AI tools.

Social robotics researchers are increasingly interested in multi-party trained conversational agents. With a growing demand for real-world evaluations, our study presents Large Language Models (LLMs) deployed in a month-long live show at the Edinburgh Festival Fringe. This case study investigates human improvisers co-creating with conversational agents in a professional theatre setting. We explore the technical capabilities and constraints of on-the-spot multi-party dialogue, providing comprehensive insights from both audience and performer experiences with AI on stage. Our human-in-the-loop methodology underlines the challenges of these LLMs in generating context-relevant responses, stressing the user interface's crucial role. Audience feedback indicates an evolving interest for AI-driven live entertainment, direct human-AI interaction, and a diverse range of expectations about AI's conversational competence and utility as a creativity support tool. Human performers express immense enthusiasm, varied satisfaction, and the evolving public opinion highlights mixed emotions about AI's role in arts.

This study presents the first report of Artificial Improvisation, or improvisational theatre performed live, on-stage, alongside an artificial intelligence-based improvisational performer. The Artificial Improvisor is a form of artificial conversational agent, or chatbot, focused on open domain dialogue and collaborative narrative generation. Using state-of-the-art machine learning techniques spanning from natural language processing and speech recognition to reinforcement and deep learning, these chatbots have become more lifelike and harder to discern from humans. Recent work in conversational agents has been focused on goal-directed dialogue focused on closed domains such as appointment setting, bank information requests, question-answering, and movie discussion. Natural human conversations are seldom limited in scope and jump from topic to topic, they are laced with metaphor and subtext and face-to-face communication is supplemented with non-verbal cues.

Theatrical improvisation (impro or improv) is a demanding form of live, collaborative performance. Improv is a humorous and playful artform built on an open-ended narrative structure which simultaneously celebrates effort and failure. It is thus an ideal test bed for the development and deployment of interactive artificial intelligence (AI)-based conversational agents, or artificial improvisors. This case study introduces an improv show experiment featuring human actors and artificial improvisors. We have previously developed a deep-learning-based artificial improvisor, trained on movie subtitles, that can generate plausible, context-based, lines of dialogue suitable for theatre.

Robots can deliver room service, conduct funeral ceremonies and lead workouts for the elderly. But can they tell a joke? Edmonton audiences can find out, starting next weekend, when local improv artists go head-to-head with artificial intelligence to see who is funnier. Called Improbotics, the show kicks off at 7:30 p.m. at Rapid Fire Theatre (located within the Citadel Theatre at 9828 101A Ave.) and runs Saturday nights from Jan. 12 until Feb. 2. The event is the brainchild of local improv artist and University of Alberta computer science PhD student Kory Mathewson, who has been performing improv for 15 years but began to connect theatre and artificial intelligence about three years ago as part of an improv group known as HumanMachine. HumanMachine consists of Mathewson, a colleague named Piotr Mirowski (an artificial intelligence researcher in London, England, who will not be at the upcoming Edmonton shows) and a piece of equipment known as A.L.Ex, which stands for Artificial Language Experiment -- a computer system that can do speech recognition, improvised dialogue and voice synthesis.

When Kory Mathewson began his PhD in computing science at the University of Alberta, he didn't think it would lead to doing improv on stage with a robot--but that's exactly what happened. Mathewson has two shows in this year's Edmonton Fringe Fest: TEDxRFT, an improv show that riffs on the popular TED Talks videos, and Human Machine, an AI improv show. "The Human Machine AI improv show is part of my PhD work. I'm studying how humans and machine-learning systems interact, and so this show is a little bit of a play on the work that I've been doing," he said. "I've been building dialogue systems, and this show explores how humans and these dialogue systems--like Siri, Alexa or Google Home--play into our lives, and the funny things they say."

It feels like artificial intelligence crept into our lives almost without us knowing, helping us pick movies on Netflix, our favourite tunes on Spotify and buy things on Amazon. As it gets older and smarter, AI's reach will be staggering, with experts at the 2018 Davos World Economic Forum predicting there's a 50-per-cent chance artificial intelligence will outperform humans in all tasks in 45 years. Consider the ways it's already at work in our lives. There is face recognition to unlock our phones; fraud detection on credit cards; smart homes that call Uber, dim lights and lower the heat; fridges that give us recipes when we pull something out for dinner, and stoves that begin to preheat (because they talk to the fridge). All possible because AI – or "deep learning" technology – sorts and identifies huge swaths of data and connects the dots (or thinks) for us. In Davos, the big thinkers believe that in the next five to 25 years, AI will help teach kids in the classroom (there are already AI teaching assistants at some universities), write a Top 40 pop song and pen a New York Times bestseller.