Have you ever wanted to travel back in time to see what your future self could be like? Now, thanks to the power of generative ai, you can.
Researchers at MIT and elsewhere created a system that allows users to have a text-based online conversation with an ai-generated simulation of their future potential.
Nicknamed future youThe system aims to help young people improve their sense of future self-continuitya psychological concept that describes how connected a person feels to their future self.
Research has shown that a stronger sense of personal continuity in the future can positively influence the way people make long-term decisions, from the likelihood of contributing to financial savings to their focus on achieving academic success.
Future You uses a large language model that relies on information provided by the user to generate an identifiable virtual version of the individual at age 60. This simulated future self can answer questions about what someone's life might be like in the future, as well as offer advice or ideas about the path they might take.
In an initial user study, researchers found that after interacting with Future You for about half an hour, people reported decreased anxiety and felt a stronger sense of connection with their future self.
“We don't have a real time machine yet, but ai can be a type of virtual time machine. “We can use this simulation to help people think more about the consequences of the decisions they make today,” says Pat Pataranutaporn, a recent Media Lab PhD who is actively developing a program to advance human-human interaction research. ai at MIT, and co-lead author of a article about your future.
Pataranutaporn is joined on the paper by co-lead authors Kavin Winson, a researcher at KASIKORN Labs; and Peggy Yin, a student at Harvard University; as well as Auttasak Lapapirojn and Pichayoot Ouppaphan of KASIKORN Labs; and lead authors Monchai Lertsutthiwong, head of ai research at KASIKORN Business-technology Group; Pattie Maes, Germeshausen Professor of Media, Arts and Sciences and director of the Fluid Interfaces group at MIT, and Hal Hershfield, professor of marketing, behavioral decision making, and psychology at the University of California, Los Angeles. The research will be presented at the IEEE Conference on Frontiers in Education.
A realistic simulation
Studies on the conceptualization of the future self date back to at least the 1960s. One of the first methods aimed at improving future personal continuity was for people to write letters to their future selves. More recently, researchers used virtual reality glasses to help people visualize future versions of themselves.
But none of these methods were very interactive, which limited the impact they could have on the user.
With the advent of generative ai and large language models like ChatGPT, researchers saw an opportunity to create a simulated future self that could discuss someone's real goals and aspirations during a normal conversation.
“The system makes the simulation very realistic. Future You is much more detailed than a person could come up with by simply imagining their future self,” says Maes.
Users begin by answering a series of questions about their current life, things that are important to them, and goals for the future.
The ai system uses this information to create what researchers call “future self-memories” that provide a backstory that the model draws on when interacting with the user.
For example, the chatbot could talk about the highlights of someone's future career or answer questions about how the user overcame a particular challenge. This is possible because ChatGPT has been trained with a large amount of data involving people talking about their lives, careers, and good and bad experiences.
The user interacts with the tool in two ways: through introspection, when they consider their life and goals as they construct their future self, and retrospection, when they contemplate whether the simulation reflects who they see themselves becoming, Yin says.
“You can imagine Future You as a space for finding stories. “You get to hear how some of your experiences, which may still be emotionally charged to you now, might be metabolized over time,” he says.
To help people visualize their future self, the system generates a photo of the user with progressive age. The chatbot is also designed to provide vivid responses using phrases such as “when I was your age,” making the simulation more like a real future version of the individual.
The ability to receive advice from an older version of yourself, rather than a generic ai, may have a stronger positive impact on a user contemplating an uncertain future, Hershfield says.
“The platform's vivid, interactive components give the user an anchor point and take something that might result in anxious reflection and make it more concrete and productive,” he adds.
But that realism could backfire if the simulation moves in a negative direction. To avoid this, they make sure Future You warns users that it shows only a potential version of their future self and that they have the ability to change their lives. Providing alternative answers to the questionnaire creates an entirely different conversation.
“This is not a prophecy, but rather a possibility,” says Pataranutaporn.
Helping self-development
To evaluate Future You, they conducted a user study with 344 people. Some users interacted with the system for 10 to 30 minutes, while others interacted with a generic chatbot or only completed surveys.
Participants who used Future You were able to build a closer relationship with their ideal future, based on a statistical analysis of their responses. These users also reported less anxiety about the future after their interactions. Additionally, Future You users said the conversation felt sincere and that their values and beliefs seemed consistent in their simulated future identities.
“This work forges a new path by adopting a well-established psychological technique to visualize the times to come (an avatar of the future self) with cutting-edge ai. “This is exactly the kind of work scholars should focus on as the technology for building virtual models of the self merges with larger models of language,” says Jeremy Bailenson, Thomas More Storke Professor of Communication at Stanford University. who did not participate in this research.
Building on the results of this initial user study, researchers continue to refine the ways in which they set context and prepare users to have conversations that help build a stronger sense of personal continuity in the future.
“We want to guide the user to talk about certain topics, instead of wondering who will be the next president in the future,” says Pataranutaporn.
They are also adding safeguards to prevent people from misusing the system. For example, one could imagine a company creating a “future you” of a potential customer who achieves a great result in life because they purchased a particular product.
In the future, the researchers want to study specific applications of Future You, perhaps allowing people to explore different careers or visualize how their everyday choices could affect climate change.
They are also collecting data from the Future You pilot to better understand how people use the system.
“We don't want people to become dependent on this tool. Rather, we hope it will be a meaningful experience that helps them see themselves and the world differently, and that helps them with their self-development,” says Maes.
