Christian Schaller, a leader of the Fedora Desktop Team and the desktop systems development group at Red Hat, published the results of evaluating the suitability of large language models in the development of graphical applications for Linux. As an experiment, he used the AI assistant Claude to translate the outdated graphical application Xtraceroute to current technologies.
The Xtraceroute application, which visualizes the path of network packets on a 3D globe, was originally written using GTK1 and OpenGL, and was ready to be ported to GTK2 in the early 2000s, remaining unupdated for 20 years. Thanks to the use of the AI assistant, it took Christian about five hours to port this application to GTK4 and the Vulkan graphic API.
Régebben:
Most:
Then, Christian used AI to create a new application based on the prepared port, demonstrating the locations of Red Hat offices on the globe and displaying company news at the bottom of the window. Christian also suggested using AI to automate the verification of GNOME Shell extensions and to generate patches considering changes made in new GNOME Shell releases.
In Christian's opinion, there is skepticism and negativity in the community regarding the use of AI, and with his experiment, he aimed to show other open-source developers that they should not ignore the opportunities AI provides to simplify the development process. For example, AI saves time by eliminating the need to sift through API documentation, track changes in the API, and select the correct calls, as well as significantly simplifies writing tests.
At the same time, AI is viewed as a tool to assist in development, but it does not absolve responsibility for the added code and requires quality checking and control. An example is shown with an attempt to generate code to embed PDF document display support in an application. AI suggested code using the WebKit browser engine for rendering, which worked but added a huge new dependency. After clarifying the task, AI provided code that used the lightweight libpoppler library for rendering PDFs.
Currently, leading AI assistants operate in the form of external online services, which raises concerns related to biztonság és adatvédelemA probléma megoldása érdekében a Red Hat saját kódgeneráló eszközén, a Granite.code-on dolgozik, amely a Granite nyílt nagynyelvű modellre épül, lehetővé téve az AI-modell futtatását a fejlesztő számítógépén. Ez a projekt egyelőre lemarad a Claude, Gemini és ChatGPT rendszerek lehetőségeihez képest, de megoldja az adatátadás problémáját harmadik fél részére, és megszünteti a munkafolyamatok külső szolgáltatásokra való támaszkodását.
Forrás: opennet.ru
