The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Jan. 27, 2026
Filed:
Feb. 02, 2023
Gdm Holding Llc, Mountain View, CA (US);
Yujia Li, London, GB;
David Hugo Choi, London, GB;
Junyoung Chung, London, GB;
Nathaniel Arthur Kushman, Cambridge, GB;
Julian Schrittwieser, London, GB;
Rémi Leblond, Cachan, FR;
Thomas Edward Eccles, London, GB;
James Thomas Keeling, Haddenham, GB;
Felix Axel Gimeno Gil, London, GB;
Agustín Matías Dal Lago, London, GB;
Thomas Keisuke Hubert, London, GB;
Peter Choy, London, GB;
Cyprien De Masson d′Autume, London, GB;
Esme Sutherland Robson, Petworth, GB;
Oriol Vinyals, London, GB;
GDM Holding LLC, Mountain View, CA (US);
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating computer code using neural networks. One of the methods includes receiving description data describing a computer programming task; receiving a first set of inputs for the computer programming task; generating a plurality of candidate computer programs by sampling a plurality of output sequences from a set of one or more generative neural networks; for each candidate computer program in a subset of the candidate computer programs and for each input in the first set: executing the candidate computer program on the input to generate an output; and selecting, from the candidate computer programs, one or more computer programs as synthesized computer programs for performing the computer programming task based at least in part on the outputs generated by executing the candidate computer programs in the subset on the inputs in the first set of inputs.