Disruption of the research software landscape through AI software generation

Specialized research software has historically been costly and time-consuming to create, but large language models (LLMs) have become capable enough at code generation to fundamentally change this. We describe how LLM-assisted programming disrupts the landscape by allowing researchers to build tools without support from software engineers, illustrate this with an example built rapidly by a single LLM-assisted developer, and discuss opportunities and risks.

This is a preview of subscription content, access

Access options

• Purchase on SpringerLink
• Instant access to the full article PDF.

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

Subjects

• Technology
• Programming language

Code availability

MOSS is openly available under an MIT license at https://github.com/StructuralNeurobiologyLab/MOSS.

References

1. Hocquet, A. et al. Nat. Comput. Sci.4, 465–468 (2024).

   Article 
   PubMed 
   Google Scholar 

2. Schindelin, J. et al. Nat. Methods9, 676–682 (2012).

   Article 
   CAS 
   PubMed 
   PubMed Central 
   Google Scholar 

3. Berg, S. et al. Nat. Methods16, 1226–1232 (2019).

   Article 
   CAS 
   PubMed 
   Google Scholar 

4. Sofroniew, N. et al. napari. Zenodohttps://doi.org/10.5281/ZENODO.3555620 (2019).

5. Makovetsky, R., Piché, N. & Marsh, M. Microsc. Microanal.24, 532–533 (2018). (Suppl. 1).

6. Last, M. G. F., Abendstein, L., Voortman, L. M. & Sharp, T. H. eLife13, RP98552 (2024).

7. Ouyang, W. et al. Preprint at bioRxivhttps://doi.org/10.1101/2022.06.07.495102 (2022).

8. Archit, A. et al. Nat. Methods22, 579–591 (2025).

9. OpenAI et al. Preprint at arXivhttps://doi.org/10.48550/arXiv.2303.08774 (2023).

10. Jimenez, C. E. et al. in International Conference on Learning Representations 54107–54157 (2024).

11. Peng, S. et al. Preprint at arXivhttps://doi.org/10.48550/arXiv.2302.06590 (2023).

12. Karpathy, A. Xhttps://x.com/karpathy/status/1886192184808149383 (2025).

13. Ronneberger, O., Fischer, P. & Brox, T. in Medical Image Computing and Computer-Assisted Intervention 234–241 (Springer, 2015).

14. Jumper, J. et al. Nature596, 583–589 (2021).

15. Kirillov, A. et al. in Proc. IEEE/CVF International Conference on Computer Vision 3992–4003 (IEEE, 2023).

Acknowledgements

MOSS was developed using LLM-assisted programming tools including Anthropic’s Claude. We thank M. So-Last for helpful discussions on U-Nets.

Authors and Affiliations

Contributions

MOSS was developed by N.D.M. The manuscript was written jointly by N.D.M and J.M.R.K.

Ethics declarations

Competing interests

J.M.R.K. owns shares of ariadne.ai ag.

Peer review

Peer review information

Nature Methods thanks Robert Haase, Wei Ouyang and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Rights and permissions

About this article

Cite this article

Medina, N.D., Kornfeld, J.M.R. Disruption of the research software landscape through AI software generation.
Nat Methods (2026). https://doi.org/10.1038/s41592-026-03210-x

• Version of record:17 August 2026

• DOI
  :https://doi.org/10.1038/s41592-026-03210-x