Answers are grounded in this paper and cite their sources.
In this paper, we present AI Programmer, a machine learning (ML) system that can automatically generate full software programs, while requiring only minimal human guidance. At its core, AI Programmer uses a genetic algorithm (GA), coupled with a tightly constrained programming language that minimizes the overhead of its ML search space. Part of AI Programmer's novelty stems from (i) its unique system design, including an embedded, hand-crafted interpreter for efficiency and security and (ii) its augmentation of classic GA to include instruction-gene randomization bindings and programming language-specific genome construction and elimination techniques. We provide a detailed examination of AI Programmer's system design, several examples detailing how the system works, and experimental data demonstrating its software generation capabilities and performance using only mainstream CPUs.
No takes yet. Share an insight, caveat, or question.
Becker et al. (2021) studied this question.