AI Simulation Gives People a Glance of Their Potential Future Self

In a preliminary user study, the researchers found that after communicating with Future You for about half an hour, people reported decreased stress and anxiety and felt a stronger sense of connection with their future selves.

“We don’t have a genuine time maker yet, but AI can be a kind of virtual time maker. We can use this simulation to help people think more about the consequences of the options they are making today,” says Pat Pataranutaporn, a current Media Lab doctoral graduate who is actively establishing a program to advance human-AI interaction research study at MIT, and co-lead author of a paper on Future You.

Pataranutaporn is signed up with on the paper by co-lead authors Kavin Winson, a researcher at KASIKORN Labs; and Peggy Yin, a Harvard University undergrad; as well as Auttasak Lapapirojn and Pichayoot Ouppaphan of KASIKORN Labs; and senior authors Monchai Lertsutthiwong, head of AI research at the KASIKORN Business-Technology Group; Pattie Maes, the Germeshausen Professor of Media, Arts, and Sciences and head of the Fluid Interfaces group at MIT, and Hal Hershfield, professor of marketing, behavioral choice making, and psychology at the University of California at Los Angeles. The research will be presented at the IEEE Conference on Frontiers in Education.

A sensible simulation

Studies about conceiving one’s future self return to at least the 1960s. One early method targeted at enhancing future self-continuity had individuals compose letters to their future selves. More just recently, scientists utilized virtual truth goggles to help people envision future variations of themselves.

But none of these approaches were really interactive, restricting the impact they might have on a user.

With the development of generative AI and big language models like ChatGPT, the researchers saw a chance to make a simulated future self that might discuss somebody’s actual objectives and goals during a typical discussion.

“The system makes the simulation very realistic. Future You is far more comprehensive than what an individual might create by simply imagining their future selves,” says Maes.

Users begin by answering a series of questions about their existing lives, things that are crucial to them, and goals for the future.

The AI system utilizes this info to create what the researchers call “future self memories” which offer a backstory the model pulls from when interacting with the user.

For instance, the chatbot could talk about the highlights of somebody’s future career or response questions about how the user conquered a specific challenge. This is possible because ChatGPT has been trained on comprehensive data including people discussing their lives, professions, and good and disappointments.

The user engages with the tool in 2 methods: through self-questioning, when they consider their life and goals as they build their future selves, and memory, when they consider whether the simulation reflects who they see themselves becoming, says Yin.

“You can think of Future You as a story search area. You have a possibility to hear how a few of your experiences, which might still be mentally charged for you now, might be metabolized over the course of time,” she states.

To help individuals picture their future selves, the system generates an age-progressed image of the user. The chatbot is likewise designed to offer vivid responses using phrases like “when I was your age,” so the simulation feels more like an actual future variation of the person.

The ability to listen from an older version of oneself, instead of a generic AI, can have a more powerful positive effect on a user considering an unsure future, Hershfield states.

“The interactive, vibrant elements of the platform provide the user an anchor point and take something that could lead to nervous rumination and make it more concrete and efficient,” he adds.

But that realism might backfire if the simulation moves in an unfavorable instructions. To avoid this, they ensure Future You warns users that it shows only one possible variation of their future self, and they have the company to alter their lives. Providing alternate answers to the questionnaire yields a completely different conversation.

“This is not a prophesy, but rather a possibility,” Pataranutaporn states.

Aiding self-development

To evaluate Future You, they out a user research study with 344 individuals. Some users interacted with the system for 10-30 minutes, while others either interacted with a generic chatbot or just filled out surveys.

Participants who utilized Future You were able to develop a more detailed relationship with their ideal future selves, based on a statistical analysis of their responses. These users likewise reported less stress and anxiety about the future after their interactions. In addition, Future You users said the discussion felt sincere which their values and beliefs appeared constant in their simulated future identities.

“This work forges a new path by taking a reputable mental strategy to picture times to come – an avatar of the future self – with cutting edge AI. This is precisely the kind of work academics need to be focusing on as technology to construct virtual self models combines with big language designs,” says Jeremy Bailenson, the Thomas More Storke Professor of Communication at Stanford University, who was not included with this research study.

Building off the outcomes of this preliminary user study, the researchers continue to fine-tune the ways they develop context and prime users so they have conversations that assist build a stronger sense of future self-continuity.

“We wish to direct the user to talk about specific topics, rather than asking their future selves who the next president will be,” Pataranutaporn states.

They are likewise including safeguards to prevent individuals from misusing the system. For example, one could think of a company producing a “future you” of a possible consumer who achieves some excellent outcome in life due to the fact that they bought a particular product.

Moving forward, the scientists wish to study specific applications of Future You, possibly by making it possible for individuals to check out various professions or visualize how their daily choices could affect environment modification.

They are likewise collecting data from the Future You pilot to much better understand how people use the system.

“We don’t want individuals to become based on this tool. Rather, we hope it is a meaningful experience that helps them see themselves and the world differently, and aids with self-development,” Maes states.