AI simulation gives people a glimpse of their potential future selves | MIT News

Have you ever wanted to travel through time to see what your future self might be like? Now, thanks to the power of generative AI, you can.

Researchers from MIT and elsewhere have created a system that allows users to have an online, text-based conversation with an AI-generated simulation of their potential future selves.

Called Future You, the system aims to help young people improve their sense of future self continuity, a psychological concept that describes how connected a person feels to their future self.

Research has shown that a stronger sense of future self-continuity can positively influence how people make long-term decisions, from one’s likelihood of contributing to financial savings to their focus on achieving academic success.

Future You uses a large language model that uses information provided by the user to generate a relatable, 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 give advice or insights about the path they can take.

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

“We don’t have a real-time machine yet, but AI can be a kind of virtual time machine. We can use this simulation to help people think more about the consequences of the choices they make today,” says Pat Pataranutaporn, a recent Media Lab doctoral graduate who is actively developing a program to advance human-AI interaction research at promote MIT, and co. -lead author of a paper on Future You.

Pataranutaporn is joined on the paper by co-lead authors Kavin Winson, a researcher at KASIKORN Labs; and Peggy Yin, a Harvard University undergraduate; as well as Auttasak Lapapirojn and Pichayoot Ouppaphan from 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 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 conceptualizing one’s future self go back to at least the 1960s. One early method aimed at improving future self continuity had people write letters to their future selves. More recently, researchers have used virtual reality glasses to help people visualize future versions of themselves.

But none of these methods were very interactive, limiting the impact they could have on a user.

With the advent of generative AI and large language models like ChatGPT, the researchers saw an opportunity to make 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 what a person can come up with by just imagining their future self,” says Maes.

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

The AI ​​system uses this information to create what the researchers call “future self-memories” that provide a background from which the model draws when interacting with the user.

For example, the chatbot can 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 is trained on extensive data involving people talking about their lives, careers, and good and bad experiences.

The user engages the tool in two ways: through introspection, when they consider their life and goals while constructing their future selves, and retrospection, when they think about whether the simulation reflects who they see themselves as, Yin says.

“You can imagine Future You as a story search space. You have a chance to hear how some of your experiences, which may still be emotionally charged for you now, can be metabolized over time,” she says.

To help people visualize their future selves, the system generates an age-advanced photo of the user. The chatbot is also designed to provide live responses using phrases like “when I was your age,” so the simulation feels more like a real future version of the individual.

The ability to take advice from an older version of yourself, rather than a generic AI, could have a stronger positive impact on a user considering an uncertain future, Hershfield says.

“The interactive, vivid components of the platform give the user an anchor point and take something that can lead to anxious rumination and make it more concrete and productive,” he adds.

But that realism can backfire if the simulation moves in a negative direction. To prevent this, they ensure that Future You warns users that it only shows one potential version of their future selves, and they have the agency to change their lives. Providing alternative answers to the questionnaire produces a totally different conversation.

“This is not a prophecy, but rather a possibility,” says Pataranutaporn.

Support self-development

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

Participants who used Future You were able to build a closer relationship with their ideal future selves, based on a statistical analysis of their responses. These users also reported less anxiety about the future after their interactions. In addition, Future You users said that the conversation felt genuine and that their values ​​and beliefs seemed consistent in their simulated future identities.

“This work forges a new path by taking a well-established psychological technique to visualize times to come – an avatar of the future self – with the latest AI. This is exactly the type of work that academics should focus on as technology to build virtual self-models merges with large language models,” says Jeremy Bailenson, the Thomas More Storke Professor of Communication at Stanford University, who was not involved in this research.

Based on the results of this initial user study, the researchers continue to refine the ways in which they establish context and engage users in conversations that help build a stronger sense of future self-continuity.

“We want to guide the user to talk about certain topics, rather than asking their future self who will be the next president,” says Pataranutaporn.

They also add safeguards to prevent people from abusing the system. For example, one might imagine a company creating a “future you” of a potential customer who achieves a good outcome in life because they bought a particular product.

Moving forward, the researchers want to study specific applications of Future You, perhaps by enabling 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 is a meaningful experience that helps them see themselves and the world differently, and helps with self-development,” says Maes.

The researchers acknowledge the support of Thanawit Prasongpongchai, a designer at KBTG and visiting scientist at the Media Lab.