1. X
  2. GitHub
Log inSign up
GitHub
10.7K posts
user avatar
GitHub
@github
The AI-powered developer platform to build, scale, and deliver secure software.
San Francisco, CA
github.com
Joined February 2008
333
Following
2.6M
Followers
AffiliatesAffiliatesRepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • 已置顶
    The next frontier of agentic development is here, and you are in control.  Today we announced releases that will keep you in the flow with your agents, all on the GitHub platform.  ⬇️
    16万
  • user avatar
    GitHub
    @github
    2h
    Stay connected to your Copilot CLI sessions from anywhere. GitHub Mobile now supports live notifications for remote Copilot CLI sessions. Track progress, know when input is needed, and jump back into session logs to unblock right from your phone.
    New release: Live notifications now support remote Copilot CLI sessions in GitHub Mobile
    2.3万
    Download the app ⬇️ github.com/mobile?utm_sou…
    7339
  • user avatar
    GitHub
    @github
    7月13日
    Get faster, more reliable coding sessions in GitHub Copilot CLI. We implemented smarter subagent delegation that cut tool failures 23%, search failures 27%, and edit failures 18%, with no quality regression.
    Table 1. Production A/B test outcomes

A three-column table with headers "Dimension," "Metric," and "Delta."

Rows: Reliability / Tool failures per session / 23% reduction; Reliability / Search tool failures / 27% reduction; Reliability / Edit tool failures / 18% reduction; Responsiveness / Total user wait time at P95 / 5% lower; Responsiveness / Total user wait time at P75 / 3% lower; Quality / Quality metrics / No regression.
    5万
    Update to v1.0.42+ with /update. github.blog/ai-and-ml/how-…
    1.2万
  • With GitHub Issue Fields, you can add structured, typed metadata (like priority, effort, dates, and custom values) to issues across your repos. Get key details at a glance without opening each issue. GitHub Issue Fields are now generally available to everyone. 🎉
    5.6万
  • "Code is the language that we use to understand physics." 💻 ⚛️ With billions of particle collisions happening at the Large Hadron Collider, @CERN research fellow Batoul Diab explains why software developers are more crucial to modern science than ever before.
    8.3万
  • user avatar
    GitHub
    @github
    7月10日
    New open source dataset for your next build. 📊 The GitHub Multilingual Repositories Dataset spans 40M+ repos and 80M+ classification rows, showing where non-English READMEs, issues, and PRs live. Korean tops issue text; Portuguese tops READMEs (3M+ repos).
    7.3万
    user avatar
    GitHub
    @github
    7月10日
    Get the numbers 👇
    github.blog
    Accelerating researchers and developers building multilingual AI with a new open dataset
    A new repository-level dataset, published on GitHub under CC0-1.0, helps researchers and developers discover multilingual developer content.
    1.5万
  • user avatar
    GitHub
    @github
    7月10日
    Replying to @github
    The result: roughly 20% lower average review cost, while maintaining the same review quality. ✅ The bigger lesson: for an agent, tool instructions are as load-bearing as your API docs. Here's how we traced the regression to the instructions ⬇️
    Better tools made Copilot code review worse. Here's how we actually improved it.
    From github.blog
    7690
  • user avatar
    GitHub
    @github
    7月10日
    Replying to @github
    We rewrote them to mirror how a reviewer actually reads a pull request: ask, narrow, read, decide.
    Figure 2: After — a simplified illustration of the review-shaped behavior the prompt guided toward: stay anchored to the diff, narrow with grep and glob, then read focused ranges with view.
    7370
  • user avatar
    GitHub
    @github
    7月10日
    Replying to @github
    The tools were fine. Their instructions were written for a different job, so the agent browsed the repo instead of investigating the pull request.
    Figure 1: Before — a simplified illustration of the general-purpose behavior we observed: widening the search, guessing paths, and accumulating context.
    1.1万
  • user avatar
    GitHub
    @github
    7月10日
    Replying to @github
    We swapped Copilot code review onto the same shared tools that power the Copilot CLI (grep, glob, view), expecting a clean upgrade. Instead, reviews did more work and caught fewer issues. 👀
    A comparison table with three columns: "Old Copilot code review," "GitHub Copilot CLI," and "Purpose." Rows: list_dir maps to glob for discovering candidate files and directories; search_file and search_dir map to grep for searching code for matching text, symbols, or call sites; read_code maps to view for reading relevant file contents once a path or range is known.
    1.1万
  • Better tools didn't improve Copilot code review. Rewriting their instructions did. 🧵
    6.5万
  • RT @pierceboggan: From an issue on GitHub.com, you can now open the GitHub Copilot app to start working on a fix with one-clic…
    5899
  • RT @moraes_c_: Release pages just got an upgrade 🚀 📋 New sidebar table of contents for easier navigation 📊 Download counts per asset now v…
    6134
  • 📣 @OpenAIDevs's GPT-5.6 family is now generally available and rolling out in GitHub Copilot. GPT-5.6 comes in three variants: ☀️ GPT-5.6 Sol: the highest reasoning ceiling in the family. Best for complex reasoning over large codebases and demanding, long-running agentic work.
    16万