The revolutionary aspect of the new wave of Language Model Interfaces (LLM) lies in the chat interface which allows for a seamless interaction without the need to switch contexts like moving to a browser. Shifting from slash commands to chat interactions enables users to start dialogues with the AI and discover various policies, code guidelines, and code bases. This chat experience marks a significant advancement as it makes it possible to interact with a certain degree of reliability, providing a beneficial way for users to communicate with the AI. While not everything needs to be chat-based, incorporating chat interfaces is seen as a step in the right direction. As accuracy of suggestions improves and better tools emerge, the chat interface is expected to evolve further, offering faster feedback cycles and experimenting with new interaction patterns. The forgiving nature of chat interfaces allows users to refine prompts, provide more context, and eventually obtain the desired answers, making them an effective tool for interacting with models and achieving desired outcomes.
GitHub Copilot is an AI tool to assist software developers by autocompleting code. It is no understatement to say it has already transformed how developers write code.
Adrián Mato Gondelle leads the Design team for GitHub Copilot. In this episode, recorded in 2023, Adrián joined the podcast to talk about his work.
Jordi Mon Companys is a product manager and marketer that specializes in software delivery, developer experience, cloud native and open source. He has developed his career at companies like GitLab, Weaveworks, Harness and other platform and devtool providers. His interests range from software supply chain security to open source innovation. You can reach out to him on Twitter at @jordimonpmm
The post Design at GitHub Copilot with Adrián Mato Gondelle appeared first on Software Engineering Daily.