How GitHub Copilot is getting better at understanding your code

EngineeringProductHow GitHub Copilot is getting better at understanding your codeWith a new Fill-in-the-Middle paradigm, GitHub engineers improved the way GitHub Copilot contextualizes your code. By continuing to develop and test advanced retrieval algorithms, they’re working on making our AI tool even more advanced. To make working with GitHub Copilot feel like a meeting of the minds between deve

[YassLab]

"So, our challenge is to figure out not only what data to feed the model, but also how to best order / It all comes down to prompts, which are compilations of IDE code and relevant context that’s fed to the model. Prompts are generated by algorithms in the background, at any point in your coding."

[eichisanden]

リポジトリ全体の内容をベクトルデータベース化して使うようになればタブで開いておく必要なくて安定してサジェストされそう。ただGitHubにpushが必要となると使い勝手が悪いからそれはやめて欲しい

[misshiki]

「GitHub Copilot がコードをどのように理解できるようになったのか」“Transformer LLM は、点と点を結び、全体像を考えるのが得意。” 学びがあった。気になる人にはお勧め。