AI learns to write sorting software on its own

Armando Solar-Lezama is in the Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA.

You can also search for this author in PubMed Google Scholar

For decades, the computing industry relied on Moore's law: as transistors became ever smaller, the number that could be crammed onto a computer chip seemed to double every two years, enabling a similar leap in computing power. But Moore's law has a natural limit, so software optimization has become just as crucial as miniaturization. Writing in Nature, Mankowitz et al.1 reveal a key role for deep learning in this process, by showing that code generated by artificial intelligence (AI) can improve the efficiency with which the C++ programming language sorts items in a list. Although seemingly mundane, this task is needed in computer programs the world over, and the AI version is now baked into a widely used implementation of the C++ library. Perhaps even more remarkably, the AI system can improve the code without any previous knowledge of the problem itself.

Access Nature and 54 other Nature Portfolio journals

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

$29.99 / 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

Get just this article for as long as you need it

$39.95

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

Nature 618, 240-241 (2023)

doi: https://doi.org/10.1038/d41586-023-01812-5

Mankowitz, D. J. et al. Nature 618, 257–263 (2023).

Article Google Scholar

Bacon, D. F., Graham, S. L. & Sharp, O. J. ACM Comput. Surv. 26, 345–420 (1994).

Article Google Scholar

Balaprakash, P. et al. Proc. IEEE 106, 2068–2083 (2018).

Article Google Scholar

Vuduc, R. W. in Encyclopedia of Parallel Computing (ed. Padua, D.) 102–105 (Springer, 2011).

Google Scholar

Frigo, M. ACM SIGPLAN Not. 34, 169–180 (1999).

Article Google Scholar

Whaley, R. C., Petitet, A. & Dongarra, J. J. Parallel Comput. 27, 3–35 (2001).

Article Google Scholar

Püschel, M. et al. Proc. IEEE 93, 232–275 (2005).

Article Google Scholar

Franchetti, F. & Püschel, M. Proc. Int. Parallel Distributed Process. Symp. (IEEE, 2003).

Google Scholar

Alur, R. et al. in Formal Methods in Computer-Aided Design 2013 1–8 (IEEE, 2013).

Google Scholar

Barthe, G., Crespo, J. M., Gulwani, S., Kunz, C. & Marron, M. ACM SIGPLAN Not. 48, 123–134 (2013).

Article Google Scholar

Schkufza, E., Sharma, R. & Aiken, A. in Proc. 18th Int. Conf. Archit. Support for Program. Lang. Oper. Syst. 305–316 (IEEE, 2013).

Google Scholar

Devlin, J. et al. in Proc. 34th Int. Conf. Mach. Learn. Vol. 70 (eds Precup, D. & Teh, Y. W.) 990–998 (JMLR, 2017).

Google Scholar

Li, Y. et al. Science 378, 1092–1097 (2022).

Article PubMed Google Scholar

Ellis, K. et al. in Proc. 33rd Neural Inf. Process. Syst. (eds Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F. & Fox, E. B.) 9169–9178 (Curran Associates, 2019).

Google Scholar

Download references

A.S.-L. consults very sporadically with Google X (about 10 hours in the past year). Its parent company, Alphabet, is the same as that of DeepMind.

Read the paper: Faster sorting algorithms discovered using deep reinforcement learning

Artificial intelligence finds faster algorithms for multiplying matrices

Artificial intelligence aids intuition in mathematical discovery

See all News & Views

Why Nature will not allow the use of generative AI in images and video

Editorial 07 JUN 23

DeepMind AI creates algorithms that sort data faster than those built by people

News 07 JUN 23

ChatGPT: standard reporting guidelines for responsible use

Correspondence 06 JUN 23

DeepMind AI creates algorithms that sort data faster than those built by people

News 07 JUN 23

Faster sorting algorithms discovered using deep reinforcement learning

Article 07 JUN 23

Health system-scale language models are all-purpose prediction engines

Article 07 JUN 23

Southern University of Science and Technology (SUSTech) is a public research university funded by Shenzhen city. Widely regarded as a pioneer and i...

Shenzhen

Southern University of Science and Technology (SUSTech)

Chinese Academy of Sciences, seeks exceptional, creative scientists to join its faculty.

Shanghai, China

The Institute of Neuroscience,Center for Excellence in Brain Science and Intelligence Technology,CAS

Situated in the historical and cultural city of Nanjing, CPU seeks talented scientists from the globe.

Nanjing, Jiangsu, China

China Pharmaceutical University

Summary A postdoctoral position is immediately available in the laboratory of Dr. Jun Yang in the Department of Surgery, St. Jude Children's Resear...

Memphis, Tennessee

St. Jude Children's Research Hospital (St. Jude)

Texas

The University of Texas Health Science Center at San Antonio (UT Health Science Center at San Antonio)