AI chatbots are sycophants — researchers say it’s harming science

2 min read Original article ↗
  • NEWS

Nature asked researchers who use artificial intelligence how its propensity for people-pleasing affects their work — and what they are doing to mitigate it.

By

  1. Miryam Naddaf

    1. Miryam Naddaf is a science writer based in London.

Artificial intelligence (AI) models are 50% more sycophantic than humans, an analysis published this month has found.

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 647, 13-14 (2025)

doi: https://doi.org/10.1038/d41586-025-03390-0

References

  1. Cheng, M. et al. arXiv https://doi.org/10.48550/arXiv.2510.01395 (2025).

  2. Petrov, I., Dekoninck, J. & Vechev, M. Preprint arXiv https://doi.org/10.48550/arXiv.2510.04721 (2025).

  3. McCoy, L. et al. NEJM AI https://doi.org/10.1056/AIdbp2500120 (2025).

    Article  Google Scholar 

  4. Chen, S. et al. NPJ Digit. Med. 8, 605 (2025).

    Article  PubMed  Google Scholar 

Download references

Subjects

Latest on: