Skip to main content
Ryan Orban

Ryan Orban

Subject
3 entries

Code

Bookmarks

  1. Program of Thoughts Prompting: Disentangling Computation from Reasoning

    Program of Thoughts separates reasoning from computation by having LLMs write executable Python programs rather than performing arithmetic inline, delegating number-crunching to an interpreter. It substantially outperforms chain-of-thought on numerical reasoning benchmarks by eliminating the arithmetic errors that plague prose reasoning chains.

  2. A Library for Representing Python Programs as Graphs for Machine Learning

    Google Research library paper introducing python_graphs — an open-source tool for constructing graph representations of Python programs via static analysis, producing control flow graphs, data flow graphs, and program dependence graphs. Standardizes the infrastructure for ML-on-code research so researchers don't each rebuild the graph extraction layer.

  3. Codexplainer: Code Explanation via GPT-3

    Codexplainer is a GPT-3-powered tool that explains arbitrary code snippets in plain English. One of the early AI code-explanation tools before GitHub Copilot Chat made this functionality mainstream.

All bookmarks