She brought her younger self back to life as an AI chatbot

Michelle Huang has been talking to herself a lot lately, through real-time text conversations with an AI chatbot she trained on her childhood journal entries.

Based in Brooklyn technologist and multimedia artist created the chatbot so she could engage in real-time written dialogue with her “inner child”. Inner child work is a therapeutic approach to understanding and healing past trauma. It involves going back to a time when we were younger and more vulnerable and, essentially, re-parenting ourselves mentally and emotionally from the perspective of our older, wiser selves.

Huang’s exercise has proven to be enlightening and healing. Via the chatbot, which the artist calls “Young Michelle”, 26-year-old Huang was able to offer her past some comforting and loving words that young Michelle always wanted and needed to hear. These include assurances that Huang’s childhood struggles were formative for the person she is today, and that she wouldn’t rewrite the past even if she could.

“I felt like I was diving into the past and giving him a big hug, and I felt him come back to the present,” Huang said.

As a child, Huang was a driven and ambitious person, and in an exchange with the chatbot, Present Michelle shares with Young Michelle that the fear of failure kept her stuck for years.

“I’m honestly proud of you for all you’ve accomplished,” the chatbot replies. “It hasn’t been easy, and I know you’ve sacrificed a lot to get where you are. I think you are doing an amazing job, and I hope you continue to pursue your dreams and make a difference in the world.”

“I was really in tears when I read that part,” Huang said on Zoom from Japan, where she is currently working on Akiya Daoa project to renovate an empty rural house into a creative hub.

Huang faithfully kept daily journals from age 7 to 19, writing about everything from his adventures with online games to homework, fears, goals and teenage crushes.

For her AI chatbot, Huang took sample text from journal entries that she felt best represented her younger self’s personality and beliefs. She then fed the text into GPT-3, a computer program from OpenAI that can be trained to create realistic text. OpenAI has also created Slaba tool that turns text prompts into visual art, and, more recently, ChatGPT, a state-of-the-art experimental chatbot that generates both excitement and fear.

“I got work responses that were eerily similar to how I think I would have responded during that time,” said Huang, whose past projects have included an immersive audio-visual LED installation inspired by the structure of neurons and a “thought cube” that changes color based on brain waves.

Huang has explored inner child work before, writing letters to her inner child on the advice of a therapist. She saw artificial intelligence as a way to tap into this practice more deeply.

“I really wasn’t inventing anything new in AI technology,” Huang said. “I was taking something that was already there and remixing it. Using real data from my past allowed me to connect with her in a deeper and more tangible way than usual.”

It also allowed him to reconnect with the innocence and joy of childhood that can fade as we age and can be trained to value rational thinking over intuition.

As children, “we are constantly impressed by the world and constantly inundated with magic and wonder and new things and new possibilities,” Huang said. “I think it’s important to keep some of that inner child.”

His experience resonated with others as well. After tweeting about his chatbot, people asked how they could replicate the experience. In a Twitter thread, she instructions shared in detail.

“One of my life goals is to release the artist and the scientist that lies dormant in everyone, because I constantly felt these two roles within me,” Huang said. She also sees chatbot Young Michelle as an example of the role of technology as a mental health tool.

Huang’s chatbot is not the first to embark on the therapeutic process. For example, Woebota user-friendly chatbot created 24/7 by a Stanford University psychologist, is based on the principles of cognitive-behavioral therapy — a short-term, goal-oriented treatment that aims to rewire thoughts that negatively affect how we feel — to help relieve depression and anxiety.

Huang is a firm believer in the value of living and breathing therapists, but sees the ever-evolving AI as a “huge add-on.”

“There is so much potential,” she said, “in how this can enable us to improve our own mental health and walk towards a collective world of human flourishing.”