Write a Blog >>
ICSE 2022
Sun 8 - Fri 27 May 2022

OpenAI’s Codex, a GPT-3 like model trained on a large code corpus, has made headlines in and outside of academia. Given a short user-provided description, it is capable of synthesizing code snippets that are syntactically and semantically valid in most cases. In this work, we want to investigate whether Codex is able to localize and fix bugs, a task of central interest in the field of automated program repair. Our initial evaluation uses the multi-language QuixBugs benchmark (40 bugs in both Python and Java). We find that, despite not being trained for APR, Codex is surprisingly effective, and competitive with recent state of the art techniques. Our results also show that Codex is slightly more successful at repairing Python than Java.

Thu 19 May

Displayed time zone: Eastern Time (US & Canada) change

11:30 - 11:45
Can OpenAI's Codex Fix Bugs? An evaluation on QuixBugsAPR at APR room
Can OpenAI's Codex Fix Bugs? An evaluation on QuixBugs
Julian Prenner Free University of Bozen-Bolzano, Hlib Babii Free University of Bozen-Bolzano, Romain Robbes Free University of Bozen-Bolzano
Live Q&A

Information for Participants