4 papers
FlowBook: Enforcing Reproducibility in Computational Notebooks
Stephen N. Freund, Emery D. Berger, Cormac Flanagan +1
Computational notebooks are notoriously prone to reproducibility failures. By permitting out-of-order cell execution, notebooks accumulate hidden state and implicit dependencies th…
ChatDBG: Augmenting Debugging with Large Language Models
Kyla H. Levin, Nicolas van Kempen, Emery D. Berger +1
Debugging is a critical but challenging task for programmers. This paper proposes ChatDBG, an AI-powered debugging assistant. ChatDBG integrates large language models (LLMs) to sig…
Flowco: Rethinking Data Analysis in the Age of LLMs
Stephen N. Freund, Brooke Simon, Emery D. Berger +1
Conducting data analysis typically involves authoring code to transform, visualize, analyze, and interpret data. Large language models (LLMs) are now capable of generating such cod…
Effective LLM-Driven Code Generation with Pythoness
Kyla H. Levin, Kyle Gwilt, Emery D. Berger +1
The advent of large language models (LLMs) has paved the way for a new era of programming tools with both significant capabilities and risks, as the generated code lacks guarantees…