Copilot

GitHub to Deprecate Selected Copilot Models by October 2026

GitHub announced it will deprecate certain Copilot models across all experiences, including Copilot Chat and code completions, effective October 2, 2026. This change affects multiple modes such as inline edits and agent modes.

Why it matters: Developers using GitHub Copilot should prepare for this transition to ensure continuity in their coding workflows. Understanding which models will be deprecated helps in planning for updates or migrations to supported versions.

Gemini 3.8 Flash integrated into GitHub Copilot for enhanced coding

Google's Gemini 3.8 Flash model is now available in GitHub Copilot, showing strong performance on complex terminal-based coding tasks. Early tests indicate it handles rigorous coding challenges effectively.

Why it matters: Integrating Gemini 3.8 Flash into GitHub Copilot could improve developer productivity by providing more capable AI assistance for complex coding scenarios. This update reflects ongoing advancements in AI-powered developer tools.

GitHub Copilot App Now Supports Running Multiple Agents in Parallel

The GitHub Copilot app introduces the ability to run several agents simultaneously, enhancing user experience and productivity. This feature aims to make the tool feel more powerful and less intimidating for beginners.

Why it matters: Running multiple agents at once allows developers to handle parallel tasks more efficiently within the Copilot app. This improvement can streamline workflows and make AI-assisted coding more accessible.

GitHub Copilot improves AI coding cost efficiency without lowering quality

GitHub explains how shorter AI-generated code outputs can increase costs and how Copilot minimizes wasted work throughout coding tasks. This approach enhances cost efficiency while maintaining task quality.

Why it matters: Reducing wasted work in AI-assisted coding can lower expenses for developers and organizations. Maintaining task quality ensures that cost savings do not come at the expense of code reliability or effectiveness.

GitHub Copilot App Automates Dependabot Pull Request Triage

The GitHub Copilot app can automate the management of Dependabot pull requests, reducing the manual effort involved in handling library updates. This helps streamline the process of triaging and merging dependency updates.

Why it matters: Automating Dependabot pull request triage saves developers time and reduces repetitive tasks, allowing them to focus on more complex coding work. It enhances efficiency in maintaining up-to-date and secure dependencies.

GitHub Copilot App Introduces 'My Work' Pane for Session Management

GitHub Copilot's app now includes a 'My work' pane to help users track multiple sessions, showing what's in progress, completed, and upcoming. This feature aims to streamline managing coding tasks within the app.

Why it matters: Managing multiple AI-assisted coding sessions can be challenging, and this new pane helps developers stay organized and focused. Improved session tracking can enhance productivity when using GitHub Copilot.

How canvases make agentic workflows visible, steerable, and cost-efficient

Chat is great for intent, but agent work gets lost in the scroll. Here is how I use canvases with my agentic workflows—and why your workflow also deserves a canvas. The post <a href="https://github.blog/ai-and-ml/github-copilot/how-canvases-make-age...

Microsoft 365 Copilot Agent Playbook Livestream Series Launches

Microsoft has introduced a practical livestream series called the Copilot Agent's Playbook to help developers build better declarative agents for Microsoft 365 Copilot. These agents integrate organizational knowledge and workflows directly into users' work processes.

Why it matters: As Microsoft 365 Copilot agent capabilities expand, developers need clear guidance to effectively create agents that enhance productivity. This series aims to provide that practical support, facilitating smoother adoption and innovation within enterprise workflows.

Let’s Learn GitHub Copilot App – Free Virtual Training Event

Join us for a free online event series kicking off July 16 to learn how to get started with the GitHub Copilot App! The post Let’s Learn GitHub...

Model upgrades can increase token use and reduce output quality

A comparison of Claude Sonnet 4.6 and Claude Sonnet 5 models revealed that the newer model used 12 times more tokens for the same tasks while delivering worse results. This was observed across 150 agent tasks in 15 scenarios using GitHub Copilot.

Why it matters: This highlights that newer AI model versions may not always improve efficiency or output quality despite better benchmarks and lower pricing. Developers should carefully evaluate model upgrades before switching to avoid unexpected performance regressions.

LLMs and GenAI Pose Growing Risks to Cybersecurity and Platform Integrity

Large Language Models (LLMs) and generative AI systems like ChatGPT and Gemini are transforming digital platforms but also raising significant cybersecurity, privacy, and platform integrity challenges. Notably, LLM-assisted malware is projected to increase from 2% in 2021, highlighting escalating r...

Why it matters: As LLMs become more integrated into various sectors, their misuse in malware and scams threatens digital trust and safety. Understanding these risks is crucial for developing effective safeguards in AI deployment.