Exclusive: Scientists at MIT hope talking to 60-year-old self will shift thinking on health, money and work
If your meticulously planned life has been derailed by couch time, fast food binges, excessive drinking, and neglecting your company pension, it might be time to chat with your future self.
Researchers at the Massachusetts Institute of Technology (MIT) have developed an AI-powered chatbot that simulates a user’s older self, offering observations and wisdom. The goal is to encourage people to consider the person they want to become.
The chatbot uses a digitally aged profile picture to depict youthful users as elderly, generating plausible synthetic memories and drawing on current aspirations to create stories about its successful life.
The goal is to promote long-term thinking and behavior change,” said Pat Pataranutaporn, a researcher on the Future You project at MIT’s Media Lab. “This could motivate people to make wiser choices in the present, optimizing their long-term well-being and life outcomes.”
In one conversation, a student aspiring to be a biology teacher asked the chatbot, a simulated 60-year-old version of herself, about the most rewarding moment in her career. The chatbot, portraying a retired biology teacher in Boston, recounted a special moment when it helped a struggling student improve their grades. “It was so gratifying to see the student’s face light up with pride and accomplishment,” the chatbot said.
To interact with the chatbot, users first answer a series of questions about themselves, their friends and family, past experiences, and their ideal future life. They then upload a portrait, which the program digitally ages to resemble the user at 60.
Next, the program uses the user’s answers to generate rich synthetic memories for the simulated older self, ensuring that the chatbot’s responses draw on a coherent backstory.
The final component is the chatbot itself, powered by OpenAI’s GPT-3.5, which introduces itself as a potential older version of the user and shares life experiences.
Users are informed that the “future self” is not a prediction but a potential future based on the information they provided. They are encouraged to explore different futures by altering their answers to the questionnaire.
A preprint scientific paper on the project, which has not been peer-reviewed, reported that trials with 344 volunteers showed conversations with the chatbot left participants feeling less anxious and more connected to their future selves. This stronger connection is expected to promote better life decisions, such as focusing on specific goals, exercising regularly, eating healthily, and saving for the future, said Pataranutaporn.
Ivo Vlaev, a professor of behavioural science at the University of Warwick, noted that people often struggle to imagine their future self, but doing so could enhance persistence in education, healthier lifestyles, and more prudent financial planning.
He described the MIT project as a “fascinating application” of behavioural science principles. “It embodies the idea of a nudge—subtle interventions designed to guide behaviour in beneficial ways—by making the future self more salient and relevant to the present,” he said. “If implemented effectively, it has the potential to significantly impact how people make decisions today with their future well-being in mind.”
“From a practical standpoint, the effectiveness will likely depend on how well it can simulate meaningful and relevant conversations,” he added. “If users perceive the chatbot as authentic and insightful, it could significantly influence their behavior. However, if the interactions feel superficial or gimmicky, the impact might be limited.
