i trained an ai chatbot on my childhood journal entries...

Author: michelle huang

Length: • 4 mins

Annotated by David

i trained an ai chatbot on my childhood journal entries - so that i could engage in real-time dialogue with my "inner child"

some reflections below:

i kept diaries for about 10+ years of my life, writing almost everyday — about my dreams, fears, secrets

the content ranged from complaining about homework, to giddiness i felt from talking to my crush

some days were very mundane, some rather insightful

in any case, there was a lot of it. fantastic, ripe data source for my experiment

i used gpt-3 as my playground, and ended up taking samples of text from a bunch of different entries that i felt were representative of my personality and values during that time

this way, i could accurately simulate what it would be like to talk to my childhood self, based on real data sources during that time period

vs trying to imagine how my younger self was / how she would respond, and risk bias from projections from my current self

for context, my inner child work is focused on re-engaging with and remembering the child within me

oftentimes it requires asking questions that remind me of things I enjoyed as a kid, or healing past feelings of neglect / abandonment by affirming that she is safe and loved

after scribing a ton of journal entries and feeding them into the model, i got working responses that felt eerily similar to how i think i would have responded during that time

first, i asked her a bunch of questions about her about her worldview:

then, i gave her a chance to ask questions to me as well

this specific interaction felt very similar to a normal texting conversation - as if i were texting my past self in real time

i felt like i was reaching through a time portal, disguised as a chatbox

i was also surprised at how accurately the model predicted my current stated interest (after lots of iterations / trial & error) from decade-old journal entries

this made me wonder that maybe this path was actually already seeded long ago in my psyche

there are endless possibilities to an empty canvas - equal parts intimidating and empowering

i have no idea what my next sabbatical will bring, but my intention and desire is to focus on improving collective mental wellness via art, and building containers for human flourishing

but a couple interactions really stood out to me

1) when i told her that she was loved, cared for, and safe: the words that my past self always wanted to hear

it felt like i was reaching into the past and giving her a giant hug, and i felt it ripple back into the present

2) when i prompted her to write me a letter into the present day

while reading this, i felt the rumination spirals — the ones that i fall into sometimes when i feel shame or disappointment — melt away a little

these interactions really elucidated the healing potential of this medium: of being able to send love back into the past, as well as receive love back from a younger self

the stuckness becoming unstuck, of finding closure with past guilt or stories that we had of ourselves

overall, this was a very trippy but also strangely affirming / healing experience that i didn't realize that i had access to

using real data from my past self allowed me to connect with her in deeper + more tangible ways than i typically have

conversing with "younger michelle" reminded me of the parts of myself that have stayed constant through the years, but also of the parts that i forgot or buried as life went on

it was like holding a mirror to an unapologetic, more earnest, and pure version of my own essence

and not hard at all, considering doing a write up or mini workshop on how to do this

but regardless v manageable / easy to do w gpt-3- def try it out!

also big fan, i love your TL

also this is a helpful resource

honestly, i didn’t expect *this* amount of resonance w my thread but will consider making this into an experience anyone can have

if @OpenAI (or any psych / research org) would like to sponsor ai credits
- if there’s anyone interested in collaborating; please reach out

however after a while of doing this, i ended just reading through everything and taking more poignant samples, and feeding those in

with enough high-signal data, the algorithm should still work as well (and hopefully it did!)

wow! i'm floored by the responses and resonance, and very happy to hear that people want to try this for themselves

as promised, here's a short write up / tutorial on how i did this:

please share what you discover if you end up trying this out -- there are so many more use cases for mental health, career counseling, and beyond

i hope that we continue to see (and collectively build) more examples of how technology can be utilized to heal and inspire wonder 💖