Dear Microsoft,

I don’t want to have a love-hate relationship with Visual Studio Code, but you’re making it really hard. Once upon a time, Visual Studio Code was just an editor. You configured it with add-ons to make it do whatever job you needed. And that was great! I gravitated towards using VS Code for multiple jobs in various languages. I could set up a Python workflow with extensions to add database-wrangling functionality. I could put together an environment for digital book publishing. I could even set up a project for screenwriting! (Yes, I have a screenplay in progress. A man can dream.)

Now, it’s not like all this went away yesterday. I can still do all of the above. But literally every new feature in VS Code these days is all about agents, AI, and LLMs. It makes me wonder if there’s anyone left in the building who is working on the actual editor anymore. In the release notes for VS Code 1.127, literally every single new feature save one was about agents and AI. Ditto the version before that. The version before that was a little better, but the trend has been clear for some time now: Visual Studio Code is fast becoming an agent front end first, and everything else is a distant second.

One argument I’ve heard is that VS Code is now a mature project. Because there just isn’t much left to be done to improve the core, you have directed your attention towards other features that will attract new users. And because agent-and-AI mania is still burning through the enterprise (and everyone’s budgets), agent-and-AI features are the order of the day. But do these features really need to be IDE-level features? Instead of drastically retooling VS Code to support agents, and making AI features native elements of the IDE, shouldn’t the real mission be to support VS Code’s native extensibility? After all, VS Code was built to be extended, and thousands of AI add-ons — including GitHub Copilot and dozens of your own extensions — already take advantage of that.

Is all this really about what AI features VS Code can support natively, or is it more about making VS Code a default first point of contact for agents and AI — specifically GitHub Copilot? Is this less about developer convenience, and more about guaranteeing — however obnoxiously — that agents and AI tools always have a central place in VS Code?

Whatever the goal is, if you think every VS Code user wants an “agentic development environment” instead of an IDE, I think you’re dead wrong. No doubt AI tools are here to stay. But I do think they will experience a reckoning. Frontier models that do everything and six more things on top of that are becoming of real use only to the big vendors who stick API tollbooths in front of them and construct wetland-devouring data centers the size of the Vegas strip to power them. The future looks more like smaller, locally-hosted models that handle highly specialized tasks and require far fewer resources to train, deploy, and serve. (Even you seem to be moving in that direction, with the Aion on-device models.)

The deeper we go into that reckoning, the less it makes sense to have cart-before-the-horse arrangements like VS Code’s native AI features. How long before these features get hoisted back out of VS Code and moved to an add-on (albeit one we get nagged to install every time we fire up our IDE)? Sooner rather than later, I’d bet. Still, until that fine day comes, I’m resigning myself to the idea that my current favorite editor will be stuffed with more and more AI features, whether or not they even make sense in my use case, for a long, wearying time to come. At least I can turn all that stuff off. For now.

As I was writing this (in VS Code, no less), I got an update to VS Code 1.128. There’s one nice feature in there I could see myself using quite widely: the ability to register OS-level keyboard shortcuts. But the rest? All AI, all agents, all the time. This relentless focus raises important questions about the direction of the editor. VS Code’s extensibility model was its greatest strength, allowing the community to build tools for every conceivable workflow. By making AI features native, Microsoft risks alienating users who prefer a lightweight, customizable environment. Moreover, the reliance on cloud-based AI models introduces latency, privacy concerns, and ongoing costs that may not be justified for many developers.

History shows that attempts to force-fit a single paradigm onto a diverse user base often backfire. For instance, when features like telemetry or forced updates were pushed too aggressively, users simply migrated to forks or alternatives. VS Code, being open source only in name (the core is MIT-licensed but the binary is proprietary), already faces forks like Cursor and VSCodium that strip out telemetry and Microsoft-specific integrations. If the AI push becomes too intrusive, we may see a splintering of the community into those who embrace the AI features and those who prefer a more traditional editor.

Furthermore, the argument that the core editor is complete is debatable. There are always improvements to be made in performance, accessibility, language support, debugging, and version control integration. Many users still rely on VS Code’s built-in Git support, terminal, and debugging capabilities, all of which could benefit from incremental improvements. Instead, those resources are being diverted to building AI agents that, while impressive, often generate inaccurate code or require heavy oversight.

Another dimension is the cost. Running AI features at scale requires significant server infrastructure, and that cost is eventually passed on to users—either through subscription fees for GitHub Copilot or through data collection that funds the service. Smaller development teams and independent developers may find that the value proposition does not justify the expense, especially when free or cheaper alternatives exist. Meanwhile, Microsoft’s deep investment in AI is apparently paying off, as the company continues to integrate AI into every product, from Office to Azure to Windows. But VS Code is a developer tool, and developers are notoriously finicky about having their workflows dictated by corporate strategy.

Finally, the author’s point about a reckoning for large models is prescient. The environmental and financial costs of training and running huge models like GPT-5 are staggering. It’s inevitable that more efficient, specialized models will dominate in specific domains, including code generation. When that happens, VS Code’s native AI features may become obsolete, replaced by lighter, more targeted extensions. The editor would be better served by maintaining a robust extension API that allows such innovation to flourish without tying the core experience to a particular AI vendor or architecture.

In the meantime, users who value control over their development environment have a few options: disable AI features via settings, switch to a fork like VSCodium, or explore alternative editors like Neovim, Emacs, or JetBrains IDEs. Each has its own trade-offs, but all offer less AI intrusion. For many, the editor should be a blank canvas, not a painted one. For now, I’ll keep my AI features turned off and hope that Microsoft remembers that the “editor” in “IDE” still matters.

Source:InfoWorld News