[Video] Can AI Fix Bugs? Inside the Benchmarking Effort

Hey Community!

We're happy to share the next video in the "Code to Care" series on our InterSystems Developers YouTube:

⏯  Can AI Fix Bugs? Inside the Benchmarking Effort

https://www.youtube.com/embed/OHi2yo8E7g4
[This is an embedded link, but you cannot view embedded content directly on the site because you have declined the cookies necessary to access it. To view embedded content, you would need to accept all cookies in your Cookies Settings]

This video explores whether generative AI can automatically fix software bugs, using a benchmarking dataset called Software Engineering Bench (SWENCH). This dataset includes 2,294 real bug reports, fixes, and related automated tests from 12 popular Python GitHub repositories such as Django and Flask. Each case contains the original codebase, the problem description, and the human-written fix, along with new tests to validate the solution. The aim is to evaluate if large language models can generate accurate fixes without breaking existing functionality, potentially reducing the high costs of bug resolution in software development.

🗣 Presenter: @Don Woodlock, Head of Global Healthcare Solutions, InterSystems

Enjoy watching, and subscribe for more videos! 👍