Competitive programming with AlphaCode

Solving novel problems and setting a new milestone in competitive programming

Creating solutions to unforeseen problems is second nature in human intelligence – a result of critical thinking informed by experience. The machine learning community has made tremendous progress in generating and understanding textual data, but advances in problem solving remain limited to relatively simple maths and programming problems, or else retrieving and copying existing solutions.

As part of DeepMind’s mission to solve intelligence, we created a system called AlphaCode that writes computer programs at a competitive level. AlphaCode achieved an estimated rank within the top 54% of participants in programming competitions by solving new problems that require a combination of critical thinking, logic, algorithms, coding, and natural language understanding.

Published on the cover of Science, our paper details AlphaCode, which uses transformer-based language models to generate code at an unprecedented scale, and then smartly filters to a small set of promising programs.