Adam Kalai presents "Recursive Self-improving Code Generation" at the DIMACS Workshop on Foundation Models, Large Language Models, and Game Theory held at Rutgers University on October 19 - 20, 2023.

Abstract: An old idea is to design AI systems that improve themselves. We show how to take first steps towards this goal by designing recursively self-improving systems for generating code. That is, starting with a short seed program that improves code at some given task using a language model, the code is used to generate a better improver. We discuss safety concerns and discuss how it may be framed as a game.

The DIMACS Workshop on Foundation Models, Large Language Models, and Game Theory explored work at the intersection of foundation models and game theory. It looked at both how to use game theory to address some of the issues arising from the use of foundation models and how to advance game theory through the use of foundation models.The workshop brought together researcher working on foundation models, natural language processing (NLP), and game theory and facilitated an exchange of ideas among them.