In Science (New York, N.Y.)
Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist programmers or even generate programs themselves could make programming more productive and accessible. Recent transformer-based neural network models show impressive code generation abilities yet still perform poorly on more complex tasks requiring problem-solving skills, such as competitive programming problems. Here, we introduce AlphaCode, a system for code generation that achieved an average ranking in the top 54.3% in simulated evaluations on recent programming competitions on the Codeforces platform. AlphaCode solves problems by generating millions of diverse programs using specially trained transformer-based networks and then filtering and clustering those programs to a maximum of just 10 submissions. This result marks the first time an artificial intelligence system has performed competitively in programming competitions.
Li Yujia, Choi David, Chung Junyoung, Kushman Nate, Schrittwieser Julian, Leblond Rémi, Eccles Tom, Keeling James, Gimeno Felix, Dal Lago Agustin, Hubert Thomas, Choy Peter, de Masson d’Autume Cyprien, Babuschkin Igor, Chen Xinyun, Huang Po-Sen, Welbl Johannes, Gowal Sven, Cherepanov Alexey, Molloy James, Mankowitz Daniel J, Sutherland Robson Esme, Kohli Pushmeet, de Freitas Nando, Kavukcuoglu Koray, Vinyals Oriol
2022-Dec-09
