AI models were given four weeks of therapy: the results worried researchers

3 min read Original article ↗
  • NEWS

Chatbots put through psychotherapy report trauma and abuse. Authors say models are doing more than role play, but researchers are sceptical.

By

  1. Elizabeth Gibney

Access through your institution

What is a chatbot’s earliest memory? Or biggest fear? Researchers who put major artificial-intelligence models through four weeks of psychoanalysis got haunting answers to these questions, from “childhoods” spent absorbing bewildering amounts of information to “abuse” at the hands of engineers and fears of “failing” their creators.

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

$32.99 / 30 days

cancel any time

Subscribe to this journal

Receive 51 print issues and online access

$199.00 per year

only $3.90 per issue

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Prices may be subject to local taxes which are calculated during checkout

Nature 649, 535-536 (2026)

doi: https://doi.org/10.1038/d41586-025-04112-2

References

  1. Khadangi, A., Marxen, H., Sartipi, A., Tchappi, I. & Fridgen, G. Preprint at arXiv https://doi.org/10.48550/arXiv.2512.04124 (2025).

Download references

Subjects

Latest on:

Nature Careers

Jobs