News

Abstract: Many are asking will Generative AI and Large Language Models (LLMs) put programmers out of business? Will it displace my research and make it irrelevant? This talk provides a fresh perspective on how Generative AI is helping with the 9 hardest things programmers have to do, and our crucial role as computing researchers in this new era. We first present upcoming services in leading IDEs that enable developers to use Generative AI to (i) explain code, bug fixes, summarize recent changes, (ii) generate documentation, commit messages, name suggestions, etc. A top concern remains the trustworthiness of the solutions provided by Generative AI. While many solutions resemble the ones produced by expert developers, LLMs are known to produce hallucinations, i.e., solutions that seem plausible at first, but are deeply flawed. To help software developers trust LLM solutions, we developed novel research that synergistically combines the creative potential of LLMs with the safety of static and dynamic analysis from program transformation systems. Our current results show that our approach is effective: it safely automates code changes and is 14x more effective than previous state of the art that relies solely on static analysis. Moreover, our approach produces results that expert developers trust: we submitted patches generated by our LLM-powered tools to famous open-source projects whose developers accepted most of our contributions. This shows the usefulness of our novel approach and ushers us into a new era when LLMs become effective AI assistants for developers. We hope to inspire you with ideas on how LLMs can help you and your research go even further.