Check out more details in our paper (arxiv.org/abs/2511.01805), webpage (lm-belief-change.github.io), and code (github.com/JiayiGeng/lm...)

Co-authors include @howard-chen.bsky.social, Ryan Liu, @manoelhortaribeiro.bsky.social, @robbwiller.bsky.social, @gneubig.bsky.social, and Thomas Griffiths

Paper: osf.io/preprints/ps...
OSF/prereg: osf.io/g59fm/
All chatbots linked above!

Major kudos to brilliant post-doc Jonas Schoene, who led this project!

Thanks to co-authors: Johannes Eichstaedt,, Aadesh Salecha, Sonja Lyubomirsky

And to: @stanfordhai.bsky.social, @stanfordpacs.bsky.social, @pascl-stanford.bsky.social, @uclaanderson.bsky.social

We find high public interest in using validated well-being chatbots.

In a nationally rep survey (N=3,056), about 1/2 of U.S. adults said they’d use empirically validated well-being chatbots. About 1/4 have already used #generativeAI chatbots for well-being.

Importantly, results generalized to key subpopulations, including those with high baseline levels of anxiety or depressed mood.

Linguistic analyses showed users had diff conversations with each chatbot:

Savoring → Sensory perceptions & positive emotions
Gratitude → Social interactions & positive emotions
Meaning → Reflection on others & cognitive processes
Hero’s journey → Achievement & cognitive processes

Does use tradeoff with human therapy?
Maybe, though initial evidence against: conversations increased willingness to try well-being chatbots again and to seek human therapy, even among those previously reluctant.

RESULTS: All four chatbots…

⚡️Improved happiness, life satisfaction, and meaning,
⚡️Reduced anxiety and depressed mood, relative to control.

Effect sizes exceed or match those from traditional positive psych interventions in @dunnhappylab.bsky.social recent meta-analysis.

#4: The Hero’s Journey Chatbot

Guides the user to reframe their life story in terms of the archetypal Hero’s Journey, highlighting challenges, strengths, and next steps (h/t Ben Rogers, @kurtjgray.bsky.social, Herrison Chicas)

👉 herobot.cpwbinterventions.xyz/readme

#3: The Meaning Chatbot

Prompts the user to reflect on what gives their life purpose, such as people, activities, and beliefs that are meaningful to them.

👉 cpwbinterventions.xyz/readme

#2: The Gratitude Chatbot

Guides user through a short exercise to express gratitude to a specific person. Encourages the user to notice others’ contributions and articulate what they appreciate.

👉 gratitudebot.cpwbinterventions.xyz/readme

#1: The Savoring Chatbot

Guides user to slow down and reflect on a positive moment from their life in detail, e.g., associated sensations, thoughts, and meaning.

👉 savoringbot.cpwbinterventions.xyz/readme

In a preregistered, randomized experiment (N=2,922), we tested whether four different AI chatbots could improve happiness and feelings of meaning in life.

Millions use #GenerativeAI chatbots for emotional support, yet little research re: whether AI dialogues can improve psychological well-being

We test whether brief, structured dialogues grounded in psych research can reliably help

WP👉 osf.io/preprints/ps...

We were fortunate to work with Governor Spencer Cox
and the @natlgovsassoc.bsky.social on a field experiment testing the #DisagreeBetter ads. We find politicians advocating for civil discourse increase viewers' openness to those they disagree with politically. Learn more👇

bsky.app/profile/robb...