Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

GitHub Reconsiders Pull Requests as Coding Agents Reshape Development

AI summary

GitHub data cited by InfoQ 中文 shows that Coding Agents drafted the first version of more than 40% of Pull Requests by September, up from 17% in March, while agent-initiated PRs grew roughly sixfold in six months. In a Latent Space interview, GitHub head Jay Parikh said personal experiments need not always follow the PR process, although enterprise projects may still require reviews, permissions, and change records. The discussion also covered model routing, session continuity, code review, software supply-chain security, and measuring the business value of AI coding.

In-depth insight

GitHub’s own adoption figures and its leader’s comments show that agentic coding is prompting the platform to reconsider when traditional review workflows should be mandatory, rather than merely adding AI features to existing development processes.

编译|林绮蓓

编辑|蔡芳芳

GitHub 自己的负责人,已经不在所有项目里使用 Pull Request 了。

在微软 CoreAI 执行副总裁、GitHub 负责人 Jay Parikh 看来,PR 不应该成为所有开发者必须遵循的流程。对于一些用来验证想法的个人项目,他甚至不需要创建 PR,也不想管理 Issue,而是直接把想法变成代码,继续开发。

这样的表态发生在一个特殊的时间点。GitHub 最新数据显示,截至今年 9 月,平台上超过 40% 的 Pull Request 已由 Coding Agent 起草首版,而今年 3 月这一比例还只有 17%。短短半年,Agent 发起的 PR 数量增长了约 6 倍。当越来越多代码由 Agent 生成,过去围绕人类开发者设计的软件协作流程,是否也需要重新调整?

#GitHub#Microsoft CoreAI#Coding Agent#GitHub Copilot#GitHub Copilot Harness#GitHub Copilot Fusion#GitHub Copilot code review Max#GitHub Session continuity#VS Code#Microsoft Azure

Original · 9 min readRead the original
Group chat

No comments yet. Start the conversation.