A Survey Assessing Github Copilot

In this episode, we are joined by Jenny Liang, a PhD student at Carnegie Mellon University, where she studies the usability of code generation tools. She discusses her recent survey on the usability of AI programming assistants.

Jenny started by discussing how she got into the intersection of LLMs and HCI. At the core of her survey, she and her coauthors are interested in developing techniques for code-generation tools that align with what developers want. She shared how code generation tools such as Copilot have progressed since its inception in 2021.

Jenny discussed the method she used to gather people to complete her survey. She also shared some questions in her survey alongside vital takeaways. She shared the major reasons for developers not wanting to us code-generation tools. She stressed that the code-generation tools might access the software developers' in-house code, which is intellectual property.

Jenny gave her thoughts on the future of software engineering in the face of LLMs. She also mentioned features that the survey respondents wished for in code-generation tools. Concluding, she shared the next phase of her research. Follow Jenny on Twitter at @jennytliang. You can also learn more about her work on her website.