🆕 Google AI's Gemini 4 Neon is now generally available in GitHub Copilot. It is designed for agentic coding, multistep tool use, and knowledge work. Google notes it delivers quality close to Gemini 4 Carbon at a lower token cost per task while responding faster and making fewer unrequested changes on coding tasks. Find it in the GitHub Copilot app, CLI, and Visual Studio Code. https://lnkd.in/eWFF7ibT
GitHub
Software Development
San Francisco, CA 6,872,673 followers
The home of software development
About us
As the global home for all developers, GitHub is the complete AI-powered developer platform to build, scale, and deliver secure software. Over 100 million people, including developers from 90 of the Fortune 100 companies, use GitHub to build amazing things together across 330+ million repositories. With all the collaborative features of GitHub, it has never been easier for individuals and teams to write faster, better code.
- Website
-
https://github.com
External link for GitHub
- Industry
- Software Development
- Company size
- 501-1,000 employees
- Headquarters
- San Francisco, CA
- Type
- Privately Held
- Founded
- 2008
Employees at GitHub
Locations
-
Primary
Get directions
88 Colin P Kelly Jr St
San Francisco, CA 94107, US
Updates
-
GitHub reposted this
Open source runs the world, but much of it is maintained by people who are already stretched thin. Meanwhile, AI is speeding up how fast code ships while web accessibility slides backward. How do we reverse that without handing maintainers another thankless compliance checklist? I sat down with GitHub's Ed Summers and Maria Lamardo on site at All Things Open to hear about the new Open Source Accessibility Framework, a community-built guide designed to meet maintainers where they are. Listen to the full episode: https://lnkd.in/gqErsPmk Explore the framework: https://lnkd.in/gUv8Ze-t
-
Copilot code review got major upgrades 🚀 What we announced at #MSIgnite 👇 🎯 Adaptive: The right review effort for each pull request How much review does each pull request need? A dependency bump may only need Lite, while a change to authentication logic benefits from Max. With the new Adaptive review depth, Copilot looks at each pull request's complexity and risk, then reviews it with Lite, Balanced, or Max. Each review shows which effort level Adaptive picked. 🔗 Cross-repository context for public repos Try cross-repository context to let Copilot code review read related repos during a review. That way, it can find code in other repos that depends on your change and use shared instructions and skills from a central repo. You choose which repositories Copilot can read. 🔐 Secret detection in reviews Copilot code review can now flag secrets in your pull requests, including secrets that don't follow a recognizable format. It uses GitHub's purpose-built model for secret detection and points out exposed credentials in review comments (so you can remove them before you merge). 📊 Track review outcomes by repo Repo Insights, a new page in each repository's Insights tab, shows how Copilot code review feedback lands in that repo, including how many comments are addressed and where merged pull requests skipped Copilot review. Now generally available. Learn more about the Copilot code review updates and how to get started ⬇️ https://lnkd.in/g35tt5FV
-
GPT-6.2 Astra and GPT-6.2 Sol from OpenAI are now generally available in GitHub Copilot. Designed for agentic coding and code review, both models demonstrate stronger coding judgment than earlier GPT-6 models. 🌌 GPT-6.2 Astra: In early testing, it caught significantly more issues in code review than GPT-6 Astra and completed agentic coding tasks using noticeably fewer tokens. ☀️ GPT-6.2 Sol: In early testing, it caught nearly twice as many real issues in code review as GPT-6.1 Sol while keeping its findings accurate. Try both in the GitHub Copilot app, CLI, and Visual Studio Code. https://lnkd.in/em2CUxZm
-
🆕 Microsoft AI's MAI Code 2 and MAI Code 2 Flash are now generally available in GitHub Copilot. MAI Code 2: A powerful, general purpose coding model built to help developers get from request to result with focused responses, practical code changes, and less unnecessary back and forth. Ideal for complex tasks like deep debugging, multi-file implementation, refactoring, and repository-wide reasoning. MAI Code 2 Flash: A lightweight, cost-efficient coding model optimized for everyday development workflows. Well suited for code explanations, targeted edits, routine fixes, and rapid iteration. Try them in the GitHub Copilot app, CLI, and Visual Studio Code. https://lnkd.in/e8WmsGva
-
New from Microsoft Ignite: Download the GitHub Copilot extension for Chrome 🌐 Ask Copilot to fill out forms, pull information from webpages, or test and debug the web app you’re building, right in the browser you’re already signed in to. Try it for Google Chrome and Microsoft Edge. Now in public preview ⬇️ https://lnkd.in/eTSG46tk
-
Just announced at Microsoft Ignite: the GitHub Copilot app now has Azure DevOps integration ☁️ Clone an Azure DevOps repo, and see the pull request through to completion right in the app: • track its status in the sidebar • click Fix on a review comment to have an agent address it • or turn on agent merge to let an agent fix CI failures and complete the pull request once your Azure DevOps checks and policies pass. Now in public preview ⬇️ https://lnkd.in/ePM6qvPQ
-
GitHub reposted this
Microsoft Copilot SDK 2.0 is here. Build and scale agents on the harness that powers Copilot, now with a faster Rust core and a shared runtime that lets you serve many users without starting a container for every conversation. The release gives you: > Lower startup time and memory use with native in-process execution > Isolated sessions with their own credentials, tools, and permissions > Durable conversations that resume across restarts and service instances > Sandboxed execution when your agents need a shell or files From chat assistants to multi-agent software factories, choose the architecture your application needs. Explore the code examples and six architectures you can build: https://lnkd.in/gCYFZ6hJ
-
-
Maintainers need fixes, not more AI bug reports. With Microsoft Security, we turned 9,791 raw AI security findings into 99 verified, private reports with suggested fixes for six open source projects. And maintainers are already shipping fixes. What we learned from Codename MDASH, a new security project 🔍 https://lnkd.in/ewUeZWAK
-
-
🆕 On Terminal-Bench 4.1, Copilot Fusion Max achieved a 71.2% resolution rate, 5.4 percentage points ahead of leading frontier models Opus 5.5 and Fable 5.2, while costing 88% less than Fable 5.2 and 57% less than Opus 5.5. https://lnkd.in/eHrxee9M
-
