GitHub

The AI-powered developer platform to build, scale, and deliver secure software.

[GitHub @github]

https://t.co/LThxnd7Fcf

[David Poll @depoll]

A much-needed refresh of the repo pull requests page landed in public preview yesterday. Very much in line with the rework we did on https://t.co/0R2KvCaqjs earlier this year: queries that can do AND/OR and nesting, content assist while you type, a filter sidebar, a compact mode, and check status and unread updates inline. We've all got a deluge of PRs these days, so we're working to make them easier to manage.

https://t.co/RVKcXGiCwo

Try it out and give us feedback!

[GPS @madebygps]

We shipped the ability to attach images and videos to your pr/issues/comments via the gh cli :)

[GitHub @github]

➡️ Happening now: GPT-5.6 Sol is 30% off ​in GitHub Copilot for Pro+ and Max subscribers.

Offer ends September 13 at 00:00 UTC.

[GitHub @github]

📣 @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.

🌎 GPT-5.6 Terra: the balanced default. A strong all-round choice for everyday interactive and agentic coding.

🌕 GPT-5.6 Luna: a lightweight, cost-efficient variant for smaller, faster tasks and the lowest-cost option in the family.

Try one, two, or them all in @code or the GitHub Copilot app.
https://t.co/FnzDLTHP6z

[Andrea @acolombiadev]

HydraFusion in Copilot CLI isn’t another model in the picker. You select it once. It decides whether the task is a single pass, a cheap draft with a quality gate, or draft → critique → revise.
Wrote it up in plain English https://t.co/JSfe0t2lp3

[Dan Wahlin @DanWahlin]

From error to app update to PR - Using GitHub Copilot App

I used Copilot App to debug a WebSocket failure in Zingit, bump the SDKs, run tests, and open a PR -without jumping back and forth between different apps.

Walkthrough in the video.

[GitHub @github]

🎉 Celebrate GitHub Copilot Day for a chance to win $100 in GitHub Shop credit!

To enter:
1. Create something with the GitHub Copilot app or GitHub Copilot CLI
2. Share your creation publicly on X, Instagram, or LinkedIn
3. Include #githubcopilotdaycontest and #sweepstakes

No purchase necessary. One entry per person. Enter by September 13, 2026, at 11:59 p.m. PT. Three winners will receive $100 in GitHub Shop credit each.

18+ and additional eligibility restrictions apply. See the Official Rules for details. 👇
https://t.co/X8rPPYwSTv

[Pierce Boggan @pierceboggan]

We have an internal feedback channel for the GitHub Copilot app that has thousands of folks providing feedback on their experience.

Now, we just @GitHub directly in Slack to explore the issue and propose a fix. The person who reported the bug can even participate in shaping the solution :)

https://t.co/7dZgK4jxOh

[GitHub @github]

@o_kwasniewski Ship it

[Julia Muiruri @juliamuiruri4]

HydraFusion Explained.

Part I: How does the Copilot engine know what to optimize for?

Your prompt is evaluated across 4 dimensions:
➡ Does it require deep reasoning? (aka. reasoning depth)
➡ Is it a sophisticated problem? (aka. code generation complexity)
➡ Is it untangling a complicated mess? (aka. debugging difficulty)
➡ Is it dominated by tool-use? (aka. tool orchestration needs)

Based on this evaluation, a HyDRA score is assigned to determine the capability profile your task needs the most and to establish a quality bar.

Part II: How does it choose a model?
Note: It doesn' t pick one model to handle the entire job e2e, (that's Auto mode). Instead, it selects 1 of 3 execution workflows and assigns the best model at different stages based on the HyDRA score:

1️⃣ Single
⚙️ How it works: A single model completes the task from start to finish.
⚖️ Rationale: The task comfortably meets the quality bar with one model. Multi-model orchestration would add latency and cost with no meaningful quality gain.

2️⃣ Cascade
⚙️ How it works: A lightweight, cost-efficient model generates the solution. This draft is evaluated against a quality gate and if it falls short of the quality bar, the entire task escalates to a stronger, frontier model.
⚖️ Rationale: Only bring in the big guns when there is concrete evidence that a lightweight model won't meet the quality threshold.

3️⃣ Critique
⚙️ How it works: A lightweight model drafts the initial code and tool interactions. An independent, read-only frontier model reviews that draft and provides feedback. The original lightweight model then performs any targeted revision(s) before the final response is sent to the user.
⚖️ Rationale: Writing code (output tokens) is expensive while reviewing code (input tokens) is cheap. Instead of incurring the cost of a powerhouse writing hundreds of lines from scratch, a cost-efficient model writes the first draft, and the frontier model just reviews it and points out fixes.

HydraFusion is available in experimental preview on the GitHub Copilot CLI: /experimental on, /model and select Hydrafusion (Research Preview)

[GitHub @github]

Tomorrow: GitHub Copilot Day 🎉

New releases, real workflows, and live coding, directly from the team who builds it and the developers who put it to work.
https://t.co/LThxnd7Fcf

[GitHub Enterprise @GitHubEnt]

A pilot often starts with excitement, strong adoption, and increased productivity. But why do those results sometimes fall flat when organizations try to scale?

GitHub’s Agentic Engineering System helps organizations understand the conditions that make scaling agents successful. This way, they can set realistic expectations and improve the odds of seeing similar results at scale.

Learn more ⬇️
https://t.co/XMJMhoJ6Fy

[GitHub @github]

84% of a PR’s open-to-merge lifecycle is spent waiting for approval. Once it gets the green light, it takes a median of 10 minutes to merge.

Instead of waiting for someone to sign off, you can now get an approval as soon as Copilot reviews your pull request.
https://t.co/DBTvw6wceG

[GitHub @github]

You get the chance to chat to three people of your choosing at #GitHubUniverse. Who would be on your list?

[GitHub @github]

The 5 commands to use in GitHub CLI (token-free) 👀

[GitHub @github]

Using more tokens doesn’t always mean better results. 👀

The real measure of AI coding efficiency is whether an agent has the context it needs to move work forward (without wasting time or resources).

Here’s how we optimized GitHub Copilot to reduce unnecessary work while maintaining task quality.
https://t.co/UmHk7hrVe0

[GitHub @github]

➡️ Get ready for GitHub Copilot Day. Live demos from the team on everything Copilot, including the app, CLI, and the new research preview HydraFusion.

Coming September 10. Set your reminder 🔔
https://t.co/JVhS1fPeIE

[GitHub @github]

Organize your issue labels, find the right one faster, and keep your lists tidy. 🗂️

Got a repo with a long and growing list of labels? Suggested Labels and Archive Labels are here to help.
https://t.co/Rh5xsIcJfy

[GitHub @github]

Stop scrolling...

...through those agent chats.

Canvases give your workflow a durable, shared surface to track what ran, changed, and needs review.

How it works 👇
https://t.co/pMwe9YhsuS