Get the latest tech news
AI in software engineering at Google: Progress and the path ahead
June 6, 2024 Satish Chandra, Principal Engineer, and Maxim Tabachnyk, Senior Staff Software Engineer, Core Systems and Experiences Progress of AI-based assistance for software engineering in Google’s internal tooling and our projections for the future. Quick links In 2019, a software engineer — at Google or indeed anywhere else — would have heard of advances in machine learning, and how deep learning has become remarkably effective in fields such as computer vision or language translation.
In this blog, we present our newest AI-powered improvements within the context of the continuing transformation of Google’s internal software development tools, and discuss further changes that we expect to see in the coming 5 years. Encouraged by our successes so far, we are doubling down on bringing the latest foundation models ( Gemini series) infused with the developer data (as part of DIDACT, mentioned above) to power existing and new applications of ML to software engineering in Google. Deep gratitude goes to contributors to the various features: Adam Husting, Ahmed Omran, Alexander Frömmgen, Ambar Murillo, Ayoub Kachkach, Brett Durrett, Chris Gorgolewski, Charles Sutton, Christian Schneider, Danny Tarlow, Damien Martin-Guillerez, David Tattersall, Elena Khrapko, Evgeny Gryaznov, Fredde Ribeiro, Gabriela Surita, Guilherme Herzog, Henrik Muehe, Ilia Krets, Iris Chu, Juanjo Carin, Kevin Villela, Kristóf Molnár, Lera Kharatyan, Madhura Dudhgaonkar, Marcus Revaj, Nimesh Ghelani, Niranjan Tulpule, Pavel Sychev, Siddhant Sanyam, Stanislav Pyatykh, Stoyan Nikolov, Ugam Kumar, Tobias Welp, Vahid Meimand, Vincent Nguyen, Yurun Shen, and Zoubin Ghahramani.
Or read this on Hacker News
