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
  • 已置顶
    user avatar
    GitHub
    @github
    6月2日
    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.  ⬇️
    The image is a promotional graphic. It shows the GitHub Copilot app, CLI, SDK, and sandboxing. The central text reads "Let's build" with the GitHub logo. Each section has a unique design related to its specific tool.
    133K
  • user avatar
    GitHub
    @github
    2h
    Medium-depth reviews are now in public preview for GitHub Copilot code review. Increase the effort level from low to medium so reviews route to a higher-reasoning model for more thorough analysis. 🔍 Here's how to use it ⬇️
    00:00
    14.7K
  • user avatar
    GitHub
    @github
    6h
    ➡️ @AnthropicAI's Claude Fable 5 is now re-enabled and generally available in GitHub Copilot.
    user avatar
    GitHub
    @github
    6月9日
    📣 Claude Fable 5, the first in @AnthropicAI's Mythos model class, is now generally available and rolling out in GitHub Copilot. It is designed for long-horizon, autonomous coding and knowledge-work tasks. Try it out in @code or the GitHub Copilot app. ⬇️ github.blog/changelog/2026…
    00:00
    31K
  • user avatar
    GitHub
    @github
    9h
    Maintainers spend hours every week closing duplicate issues. 😮‍💨 That changes with duplicate detection. Surface up to 3 matching issues as you create one, before you hit submit.
    00:00
    27.2K
    user avatar
    GitHub
    @github
    9h
    Now in public preview 👇 github.blog/changelog/2026…
    Detecting Duplicate Issues in Public Preview and issue fields MCP support for GitHub Issues
    8K
  • GitHub reposted
    user avatar
    Sentry
    @sentry
    6月30日
    Seer, Sentry's AI debugger, analyzes your issues and finds the root cause. Now you can pass that analysis directly to a @github Copilot agent which picks up the context, generates a fix, and opens a pull request. Learn more in our latest video with @pauljaffre 👇
    00:00
    8.7K
  • user avatar
    GitHub
    @github
    6月30日
    The best thing about building in the open? Nothing gets lost. Anders Hejlsberg, creator of TypeScript and C#, on 12 years of issues and decisions, all searchable. "It didn't just disappear into some email I can't find anymore." Take a trip down memory lane and tell us: what was
    00:00
    31.3K
  • user avatar
    GitHub
    @github
    6月30日
    📣 @AnthropicAI's Claude Sonnet 5 is now generally available and rolling out in GitHub Copilot. Early testing for Claude Sonnet 5 showed: • strong results across a range of coding scenarios, particularly for performance on CLI-style tasks. • excellent prompt-cache utilization
    00:00
    132K
  • user avatar
    GitHub
    @github
    6月29日
    Git 2.55 is here with a new incremental repacking strategy, more flexible ways to edit history, and much more. Check out our highlights from the latest release ✨
    Highlights from Git 2.55
    From github.blog
    104K
  • user avatar
    GitHub
    @github
    6月29日
    GitHub Copilot turns 5 today! 🎂 Share the projects you've built with Copilot. 👇
    173K
  • user avatar
    GitHub
    @github
    6月28日
    We benchmarked the GitHub Copilot agentic harness against the harnesses that ship leading models natively. Holding the model and task fixed across SWE-bench Verified, SWE-bench Pro, SkillsBench, TerminalBench, and Win-Hill, the results were clear: ✅ Task resolution on par with
    Scatter plot titled "Resolution rate vs. cost per task," plotting resolution rate (pass@1, y-axis, 62–78%) against mean cost per task in USD (x-axis, $0.40–$1.40). Each marker is one agent × model configuration (mean of 5 runs on Terminal-Bench 2), surrounded by a shaded ±1σ ellipse. A legend identifies three agents by color: Copilot CLI (purple), Codex CLI (gray), and Claude Code (teal). The subtitle notes that up and to the left is better: higher resolution at lower cost. A dashed vertical line splits the points into two clusters: lower-cost GPT-family models (GPT-5.4 and GPT-5.5) on the left, and higher-cost Claude-family models (Sonnet 4.6 and Opus 4.7) on the right.
    69.9K
    user avatar
    GitHub
    @github
    6月28日
    Explore the data ⬇️
    Evaluating performance and efficiency of the GitHub Copilot agentic harness across models and tasks
    From github.blog
    16.4K
  • user avatar
    GitHub
    @github
    6月28日
    Using the /impeccable skill built into the GitHub Copilot app, @cassidoo gave her PocketCal app a design refresh! ✨ Enable in Settings > Experimental to try it out. gh.io/app?utm_source…
    00:00
    75.6K
  • user avatar
    GitHub
    @github
    6月27日
    Copilot code review now supports AGENTS.md files. 💡 Here's how to customize for more context-aware reviews. ▶️
    00:00
    91.8K
  • user avatar
    GitHub
    @github
    6月27日
    The story around AI used to be about generating more. For many neurodivergent professionals, the bigger benefit is offloading invisible labor: remembering what you promised, the dozen tabs open in your brain, the thread you meant to reply to. Senior director @ashleymcnamara
    I automated my job (and it made me a better leader)
    From github.blog
    42.1K

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