Best of GitHub — February 2026

1. 1
   Article

   Red Hat Developer·12w

   The uncomfortable truth about vibe coding

   Vibe coding—building software through AI conversations—enables rapid prototyping but creates unsustainable codebases that become unmaintainable after 3 months. Projects hit walls when changes break multiple features because prompts become obsolete and code lacks intent documentation. Spec-driven development solves this by treating specifications as the authoritative blueprint, maintaining version-controlled documentation, and enabling regeneration from a single source of truth. The most effective approach combines natural language efficiency for exploration with rigorous specifications for production systems, using unit tests to validate small scopes while specs govern larger architecture.

   478

   42
2. 2
   Article

   GitHub Changelog·11w

   Repository dashboard is now generally available

   GitHub's repository dashboard is now generally available after a public preview period. The GA release adds two new features: an Admin Access view that surfaces all repositories where you have admin permissions, and command palette integration for faster navigation. The dashboard lets users find, filter, and save custom views of repositories they have access to, with built-in views for contributions, personal repos, forks, and admin access. It's accessible via github.com/repos, the global navigation bar, or the command palette.

   299

   8
3. 3
   Article

   DEV·11w

   I feel lost on AI

   A 26-year veteran programmer from Mexico shares his honest emotional struggle with AI coding agents. While he appreciates Copilot as a productivity booster, he feels disoriented and empty when using agentic tools like Claude Code and Amazon Kiro to fully delegate coding tasks. He describes a personal experiment running two projects simultaneously — one coded manually with Copilot, one delegated to Claude Code — and reflects on the tension between efficiency gains and the loss of the craft he loves. The post resonates with many developers who feel the same but rarely admit it publicly.

   288

   30
4. 4
   Article

   daily.dev Changelog·11w

   A live leaderboard for AI coding tools

   The Arena is a real-time leaderboard on daily.dev that tracks developer mindshare for AI coding agents and LLMs using a custom metric called the D-Index, which combines mention volume and sentiment. It covers tools like Cursor, Claude Code, Copilot, Codex, Windsurf, and LLMs like Claude, GPT, DeepSeek, and Gemini. Five spotlight crowns highlight category leaders including Developer's Choice, Most Loved, Fastest Rising, Most Discussed, and Most Controversial. Rankings refresh every 60 seconds and include sentiment scores, 24h mention volume, momentum indicators, and 7-day sparklines. A live highlights feed surfaces notable developer posts with sentiment context.

   280

   48
5. 5
   Article

   Hackaday·15w

   How Vibe Coding Is Killing Open Source

   Research suggests LLM-assisted 'vibe coding' may harm open source ecosystems by reducing direct interaction with projects, decreasing website visits and documentation usage, and eliminating organic library selection. The practice replaces developer engagement with chatbot interactions, potentially starving projects of community participation, bug reports, and revenue from sponsorships. Studies show AI coding assistants introduce 41% more bugs and reduce experienced developer productivity by 19%, while degrading cognitive skills. The statistical nature of LLMs means only the most prevalent dependencies in training data get used, similar to how 80% of Spotify artists receive minimal plays and compensation.

   274

   49
6. 6
   Video

   Fireship·12w

   7 AI updates breaking the SaaS business model...

   Recent AI developments are threatening the traditional SaaS business model as major software companies lost $1 trillion in market cap. Seven key AI releases demonstrate this shift: OpenAI's Codex app and 5.3 model, Claude's Opus 4.6, Alibaba's Qwen 3 Coder Next, ZAI's GLM5, Minimax M2.5, GitHub Agent HQ, and Waymo's world model. These tools enable AI agents to replace multiple human seats, offer open-weight alternatives to expensive subscriptions, and automate entire development workflows. The core thesis: when AI intelligence becomes abundant and cheap, the per-seat pricing model that drives SaaS profit margins becomes obsolete.

   100

   17
7. 7
   Article

   System Design Newsletter·15w

   I struggled to code with AI until I learned this workflow

   AI coding assistants work best through an iterative workflow rather than one-shot prompts. The key is providing comprehensive context (project background, constraints, relevant code), requesting a plan before implementation, generating code in small steps with defined roles (planner, implementer, tester, explainer), reviewing output with AI-assisted tools, writing tests immediately, and debugging systematically. Common pitfalls include context drift in long conversations, API version mismatches, and over-reliance on AI without understanding the output. The workflow emphasizes treating AI like a new teammate who needs explicit briefing, keeping changes small and reviewable, and maintaining human oversight throughout the process.

   89

   3
8. 8
   Article

   The Art of Simplicity·12w

   I didn't notice this VS Code feature until it made me question how I code

   VS Code 1.103 introduced AI Statistics, a status bar feature that tracks the ratio of AI-generated code versus manual typing over the last 24 hours. The feature provides visibility into how much developers rely on AI coding assistants, helping them make more intentional decisions about when to use AI completions versus writing code manually. Enable it by searching for "AI stats" in settings.

   80
9. 9
   Article

   Ruby Flow·11w

   AI Assistance vs. Vibe Coding: The Two Modes of Modern Development

   Two distinct modes of AI-assisted development are emerging: Classic AI Assistance (staying in control, reading every line, using AI as a co-pilot for complex logic, debugging, and security) and Vibe Coding (delegating entirely to AI, verifying results visually rather than reading code, best for UI tweaks, boilerplate, and prototypes). The danger of pure vibe coding is accumulating an unmaintainable codebase. The recommended hybrid workflow is to start with vibe coding for the bulk of work, then switch to AI assistance to clean up, secure, and optimize the generated code. Knowing when to use each mode is framed as the key senior developer skill in 2026.

   56

   6
10. 10
    Article

    Hackaday·12w

    What About The Droid Attack On The Repos?

    Open source maintainers are increasingly overwhelmed by AI-generated 'slop' pull requests submitted by autonomous agents. Jeff Geerling and Daniel Stenberg (curl) are among those raising alarms, with GitHub now offering options to disable PRs entirely or restrict them to invited collaborators only. While the root cause is human behavior—someone configured the agent—the flood of low-quality AI submissions is eroding the collaborative openness that made open source strong. Maintainers may be forced to close off their projects, sacrificing the serendipitous contributions from unknown developers that historically helped squash bugs.

    56

    8
11. 11
    Article

    Zed·14w

    Choose Your Edit Prediction Provider — Zed's Blog

    Zed code editor now supports multiple edit prediction providers including Zeta, Mercury Coder, Sweep, Ollama, Codestral, and GitHub Copilot Next-Edit. The editor has implemented a pluggable provider architecture that simplifies adding new providers by handling state management, UI integration, and caching in the core while requiring only model-specific implementation. Users can configure their preferred provider in settings, with options ranging from cloud-based services to local models via Ollama. Zeta2, a faster and more accurate version of Zed's default model, is launching soon.

    54

    1
12. 12
    Article

    GitHub Changelog·12w

    GitHub Copilot support in Zed generally available

    GitHub Copilot now officially supports authentication with the Zed code editor through a formal partnership. Developers with paid Copilot subscriptions (Pro, Pro+, Business, or Enterprise) can sign in directly from Zed's settings and use their existing subscription without any additional AI license. Zed is a high-performance, multiplayer code editor built in Rust by the creators of Atom and Tree-sitter.

    49

    3
13. 13
    Article

    Code Like A Girl·14w

    I Became a Developer Again Without Meaning To

    A former developer returns to coding after 15+ years to build a gender diversity tracker for Substack's Technology leaderboards. The journey involves learning modern tools (VS Code, GitHub, Chrome extensions) with AI assistance (ChatGPT, Copilot), pivoting from UI scraping to API calls, and ultimately settling on a Python/SQLite/Streamlit stack. The project highlights both the challenges of being a beginner again and the accessibility of building with AI as a co-pilot.

    49

    2
14. 14
    Article

    GitHub Changelog·12w

    GitHub Projects: Import items based on a query and hierarchy view improvements

    GitHub Projects has received two notable updates. First, when creating a new project, users can now import items using a search query with full support for advanced filters (AND/OR keywords, nested queries) — not just by importing directly from a repository. Second, the hierarchy view (launched in public preview in January 2026) has been improved with inline sub-issue creation, drag-and-drop reordering and reparenting, and synchronized sub-issue ordering between issues and projects. Upcoming improvements include deduplication of issues in the hierarchy, persistent expand/collapse state, and filtering for sub-issues.

    44
15. 15
    Article

    Visual Studio Blog·14w

    Roadmap for AI in Visual Studio (February)

    Microsoft's February roadmap for AI in Visual Studio focuses on reliability and refinement rather than new features. Key improvements include better agent stability with enhanced progress indicators, failure handling, and diagnostics. The update introduces early work on a Planning Agent for multi-step tasks, continues Model Context Protocol (MCP) integration, and improves context management for large codebases. Editor experience enhancements address keyboard shortcuts, IntelliSense conflicts, and smoother Copilot integration. The team is also beginning experimental work to integrate Copilot CLI into Visual Studio.

    44
16. 16
    Article

    Lonely Programmer·14w

    Git vs GitHub

    43

    13
17. 17
    Article

    InfoWorld·14w

    Is AI killing open source?

    AI-generated pull requests are overwhelming open source maintainers with low-quality contributions that take seconds to create but hours to review. Tools like Claude Code can autonomously submit patches, creating an unsustainable asymmetry where maintainers drown in "slop PRs" lacking context and understanding. Small utility libraries are becoming obsolete as developers generate code on-demand instead of using dependencies. This shift is forcing projects toward stricter contribution barriers and smaller, more exclusive communities where human judgment and relationships matter more than volume. The future of open source may belong to projects that are hardest to contribute to, prioritizing care and curation over accessibility.

    39

    7
18. 18
    Article

    SD Times·13w

    This week in AI updates: GPT-5.3-Codex-Spark, GitHub Agentic Workflows, and more (February 13, 2026)

    OpenAI released GPT-5.3-Codex-Spark, a lightweight coding model delivering 1,000+ tokens per second through a Cerebras partnership. GitHub launched Agentic Workflows for repository automation using plain Markdown descriptions. Google added Automated Reviews to Conductor in Gemini CLI and upgraded Gemini 3 Deep Think mode for improved reasoning. GitHub Copilot testing for .NET reached general availability in Visual Studio 2026. Anthropic raised $30 billion in Series G funding at a $380 billion valuation, with run-rate revenue hitting $14 billion.

    28
19. 19
    Video

    bigboxSWE·12w

    You Can't Beat Linux

    A commentary piece arguing that Linux is winning by default as Microsoft and Apple stumble. Microsoft's recent troubles include GitHub outages, Copilot reliability issues, Windows bugs, and aggressive monetization. Meanwhile, Linux is gaining ground with Photoshop compatibility progress, gaming-focused distros like Bazzite seeing massive adoption, and Valve's continued investment in Steam OS. The core argument is that Linux's freedom from corporate and shareholder pressures makes it uniquely resilient and trustworthy as an operating system.

    28

    3
20. 20
    Article

    GitHub Blog·14w

    What the fastest-growing tools reveal about how software is being built

    TypeScript has overtaken JavaScript as the fastest-growing language on GitHub, driven by AI-assisted development workflows where type systems catch errors earlier. Python continues rapid growth, particularly for production AI systems beyond experimentation. The fastest-growing open source projects emphasize speed, reproducibility, and minimal friction. Typed languages are becoming the default for new development as AI code generation benefits from stronger type checking. Clear documentation and contributor guides remain the highest-leverage improvements for growing open source communities.

    24
21. 21
    Article

    All Things Open·14w

    Why 1.3 billion people depend on progress, not perfection

    GitHub is investing in open source accessibility to help 1.3 billion people with disabilities. The initiative focuses on three key areas: fixing foundational open source projects to create a multiplier effect downstream, enabling disabled developers to contribute and build careers, and supporting custom assistive technology development. GitHub's Open Source Accessibility Summit attracted 800 registrants, demonstrating strong community demand. The work emphasizes incremental progress over perfection, with resources available at gh.io/open-source-accessibility for developers at all skill levels to contribute.

    15

    2