In recent years, we have seen many products being created with increasing participation of Artificial Intelligence (AI), Machine Learning, and other wild cards that compose the last decade’s frenzy: Data Science. In this field, the acronym MLUX circulates around the world and refers to Machine Learning User Experience, a path of no return.
Products that can guess when you are leaving home, what you would like to eat, what is the best route to get to work and et cetera; instigate practical, ethical, and methodological questions. It doesn’t take a truckload of information to understand this, just good examples of content are enough to illustrate how Research (with a capital “R” and everything!) in technology, especially UX, has exchanged insights and data with machines that learn while we use them.
Good examples start with an AI Designer (or artificial intelligence designer), another design buddy from startups immersed in Data Science. While they are still a stranger in Brazil, in other places they already have established their space: about 5 out of 10 startups already employ this type of professional in Silicon Valley. In charge of transforming machine learning, data relationship, and manipulation techniques into excellent experiences for users and the business, AI Designers “teach the machine to take into account human experience”, working as part of a tech squad to shape new technologies. Active in areas of long-term investment — such as computer vision, speech, language, video, and AI assistants — these project teams are creating new resources rather than just developing solutions for existing AI.
How many times have you taken your smartphone and it automatically showed you the weather? Or when Siri answers something related to what you were saying in a meeting? And when you just think about eating and magically something related appears on your screen inducing you to order some food? The examples are endless.
Documentaries like “The Network Dilemma” (Netflix, 2020) focus on the relationship between data protection law and augmented reality, a key issue in modern times. During the creative process, after interviewing users, comparing it with usage metrics and business requirements, at some point someone said “what information was interesting for the experience in front of the machines” (Eureka!).
Didn’t get it? One of the most important parts of modeling this type of technology is to provide the AI with necessary data for machine learning. AI Designers work with engineers to create tools for collecting and annotating data to design platforms that optimize the efficiency of these processes and make AI intuitive in identifying and collecting good quality data. However, if more automated methods don’t work, designers help to gather more understandable data sets for the product proposal.
Google’s AI research team, for example, used UX and Machine Learning techniques to understand how different cultures scribble drawings. Through interviews with QuickDraw users and collecting different doodles — why not say “experiences”? — data was obtained on specific traits and movements that each culture attributes to an animal.
Through this relationship between Design and Data Science, platforms like Google For Education were able to receive faster updates in times of the pandemic and the partnership between both platforms accelerated research models and results on a global scale.
The emergence of specific kits for AI Design
Large companies like Apple have been contemplating their development kits with AI Design Guidelines for a few years now.
Frequently asked questions from designers at Apple have brought data scientists and developers closer to the product design process. Throughout the Guideline we noticed that designers were able to meet certain needs when inserted in the creative process of developing self-learning products. After all, how does one bring meaning to the heartbeat on an Apple Watch? How do you relate your heartbeat to the music you love to hear? And how to do this without being invasive? Such questions serve as an example and aim to provide common ground for the development of user experiences with machine learning.
In its special designer corner, Google has also published various materials on AI and Design. For designers in Silicon Valley it’s difficult not to put these practices together, as shown by Reena Jana and Mahima Pushkarna in the article “Six AI terms that UXers should know”.
Building experience between hands and… bits?
We are facing the birth of an entity “too smart to be overlooked”, as Elon Musk said, and whose limitations are only in the limits of access to data that’s introduced to it. In the not-so-distant future — like, now (have you seen “The Network Dilemma”?) — we may find ourselves experimenting with machines, aligning findings with machines, changing our research because the machine had a better conclusion.
According to Musk, 50% of jobs will become extinct due to AI, and he is not the only one afraid. For Kai-Fu Lee, a prominent computer scientist and theorist in the field of artificial intelligence, 40% is an acceptable number that allows good reservations: AI can be the salvation of humanity by freeing us from repetitive chores, because we can remember again what it means to be human. For those who want to know more, this Ted Talk is fast and interesting.
The world of Design is responsible for conceiving and materializing, in this endless wheel of life, the ways in which we will remember humanity.
Questions and actions on how to make interaction with technology and business more humane are already in demand for us with no real scenario that brings us to the late — and dystopian — Animatrix (Warner Bros, 2003).
For those who want more reading material, here are some links:
People + AI Research Team
People + AI Guidebook
What is the role of an AI Designer?
Designing in a World where Machines are Learning
Integrating Data Scientists and User Researchers at Spotify
How UX can (and should!) humanize ML (dscout People Nerds webinar)
Google’s “What if..?” tool
Google’s Facets tool
Interactive Confusion Matrix
Machine Learning for Visualization
A People’s Guide to Artificial Intelligence
*Este artigo também está disponível em português, acesse aqui para conferir. :)