Last week, Nvidia CEO Jensen Huang sat down for an interview with Citadel Securities and dropped a statement that should make every developer pay attention: “100% of our software engineers and chip designers use Cursor.”
Not “some teams are trying it.” Not “we’re evaluating it.” One hundred percent.
Then he listed five other AI companies shaping the future of work: OpenAI, Harvey, OpenEvidence, Replit, and Lovable. Six startups total. These aren’t random picks. This is Nvidia’s CEO, someone who sees the entire AI landscape, calling out the tools his engineers actually use to build some of the world’s most complex software.
Cursor stood out. Not just mentioned, but specifically highlighted as the tool that’s achieved total adoption across Nvidia’s engineering organization.
I’ve been using Cursor for about a year now. When I heard Huang’s statement, my reaction wasn’t surprise. It was recognition. He’s describing what I’ve been experiencing every day.
What Huang Actually Said#
The interview with Citadel Securities, published on October 15, focused on how AI will reshape workforces. Huang has been saying for months that future companies will have both human and “digital” employees working together. He’s been calling it the age of “agentic AI,” where AI assistants handle specific tasks as part of integrated teams.
When talking about what that looks like in practice, he pointed to six companies: “Some of them will be OpenAI-based, and some of it would be Harvey-based or Open Evidence or Cursor or Replit or Lovable.”
OpenAI builds the foundation models that power much of this AI revolution. Harvey focuses on legal work, OpenEvidence on healthcare. Replit, Cursor, and Lovable are what Huang called “vibe coding” tools. AI-powered coding environments where you describe what you want and watch it materialize.
But Cursor got special attention. That 100% adoption number. And then this: “Productivity gains, the work that we do is so much better.”
Not just faster. Better.
That distinction matters. Plenty of tools make you faster while producing worse results. Cursor is apparently doing both: speed and quality improvements.
Why I Agree With Huang#
I’m not going to pretend to have Nvidia’s scale or complexity. But I’ve been building software for years, and I’ve tried most of the AI coding assistants that have emerged in the last two years. Cursor isn’t just incrementally better than alternatives. It’s fundamentally different in ways that matter.
When I start working on a feature, Cursor understands the entire codebase. Not just the file I’m editing, but the patterns I’ve used elsewhere, the architecture I’m following, the dependencies that exist. It’s context-aware in a way that GitHub Copilot never was.
I can highlight a section of code and ask “why would this fail if the user uploads a file larger than 10MB?” and get an actual answer based on my specific implementation. I can describe a feature in natural language and watch Cursor scaffold the entire thing, following my existing patterns, using my preferred libraries, matching my code style.
The result: I spend less time writing boilerplate and more time thinking about architecture. Less time debugging syntax and more time catching edge cases. Less time searching documentation and more time making design decisions.
This is what Huang meant by “better work.” The cognitive load shifts from mechanical tasks to judgment calls. From typing to thinking.
The UI/UX Is Legitimately Good#
Let me be specific about why Cursor’s interface works.
First, it’s built on Visual Studio Code. This isn’t a new interface you have to learn. If you know VS Code, you know Cursor. All your extensions work. Your keybindings work. Your color themes work. The learning curve is essentially zero.
Second, the AI features are integrated without being intrusive. There’s a sidebar where you can chat with the AI about your code. There’s inline suggestions that appear as you type. There’s the ability to highlight code and ask questions or request changes. All of it feels native, not bolted on.
Third, the AI understands scope. When I ask it to refactor something, it knows what files are related. When I ask it to implement a feature, it suggests which files to create or modify. It doesn’t just generate code in isolation. It thinks about the system.
Fourth, it shows you what it’s doing. When Cursor makes changes, you see a diff. You can accept, reject, or modify. You’re never locked into AI decisions. The AI is a collaborator, not a black box.
The interface respects the developer. You’re always in control. The AI makes suggestions, you make decisions. That balance is hard to get right, and Cursor nails it.
Compare this to some other AI coding tools. Some feel like chatbots awkwardly embedded in an IDE. Some generate code you can’t see until you accept it. Some fight with your existing workflow instead of enhancing it. Cursor got the UX right from the start.
The Pricing Problem Nobody Wants to Talk About#
Here’s the uncomfortable truth: for the last year, the main reason people leave Cursor isn’t the product. It’s the pricing.
In mid-2025, Anysphere (the company behind Cursor) changed their Pro plan from a fixed request model to a usage-based credit system. The $20 monthly subscription still exists, but now it covers a variable amount of work depending on which AI models you use and how intensively you use them.
Some users suddenly found themselves burning through credits faster than expected. Others got surprise bills. The confusion was real enough that Anysphere’s CEO, Michael Truell, issued a public apology and offered refunds to affected users.
Then in July, they introduced a $200-per-month “Ultra” plan for heavy users. The jump from $20 to $200 is steep. The justification is that the Ultra plan offers 20 times more usage than Pro, but the messaging was unclear. People felt blindsided.
I’ve watched developers I know switch away from Cursor specifically because of pricing uncertainty. Not because the tool wasn’t valuable. Not because they found something better. Because they couldn’t predict their monthly costs.
This is the one area where Cursor is consistently failing. The product is excellent. The pricing model is a mess.
The irony: if Nvidia is willing to pay for 100% of their engineers to use Cursor, the value must be obvious at enterprise scale. But individual developers and small teams are jumping ship over billing confusion.
Anysphere needs to fix this. Transparent, predictable pricing. Clear tiers. No surprise bills. If they don’t, competitors will use pricing clarity as a wedge to steal market share, even if their products are technically inferior.
The Six Companies That Matter#
Let’s go back to Huang’s list: OpenAI, Harvey, OpenEvidence, Cursor, Replit, and Lovable.
This is a CEO who sees the entire AI industry. He’s not picking companies because they have good marketing. He’s picking companies that are actually changing how work gets done.
OpenAI is obvious. They build the foundation models that power much of the AI revolution. GPT-4 and its successors are infrastructure for the AI age.
Harvey focuses on legal work. It’s an AI assistant specifically trained on legal documents, case law, and legal reasoning. Big law firms are adopting it because it actually understands legal context in ways general-purpose AI doesn’t.
OpenEvidence does the same thing for healthcare. It helps clinicians find relevant medical research and evidence-based guidance. In a field where being wrong can kill people, having AI that understands medical literature matters.
Replit is an online IDE with AI assistance. You can build and deploy entire applications from a browser. It’s lower friction than local development, which makes it powerful for prototyping and learning.
Lovable (formerly GPT Engineer) lets you describe an app and generates the entire codebase. It’s “vibe coding” taken to the extreme. Specify what you want, get a working application.
And Cursor, which sits between Replit’s simplicity and traditional development’s power. You get a full IDE, but the AI understands what you’re building deeply enough to be genuinely helpful.
What these six companies have in common: they’re not trying to replace humans. They’re building tools that let humans operate at a higher level of abstraction. Lawyers still make legal decisions, but Harvey handles research. Doctors still diagnose patients, but OpenEvidence surfaces relevant studies. Developers still architect systems, but Cursor handles implementation details.
That’s the pattern Huang sees. That’s the future he’s betting on.
Why Cursor Hits the Mark#
I’ve used GitHub Copilot. I’ve tried Amazon CodeWhisperer. I’ve tested Tabnine and Kite and a dozen other AI coding assistants. Cursor is the one that stuck.
Here’s why:
It understands projects, not just files. Most AI coding assistants look at the file you’re editing and maybe a few related files. Cursor understands the entire repository. It knows your architecture, your patterns, your dependencies. This context awareness is the difference between “here’s generic boilerplate” and “here’s code that fits your specific system.”
It handles complex tasks. I can ask Cursor to implement a multi-file feature, and it will suggest creating new files, modifying existing files, and updating configuration. It thinks at the feature level, not the line level.
It learns your style. After working in a codebase for a while, Cursor generates code that looks like code I would write. Same patterns, same naming conventions, same structure. It’s not just correct. It’s consistent.
It explains what it’s doing. When Cursor suggests a change, I can ask why. It doesn’t just generate code and move on. It can walk through the reasoning, point out edge cases, explain trade-offs.
It gets out of the way. When I don’t need AI assistance, Cursor is just a normal editor. The AI features don’t interrupt or distract. They’re there when needed, invisible when not.
This combination is why Nvidia’s engineers use it. Not because someone mandated it. Because it actually makes their work better.
The Evolution Continues#
Anysphere raised $900 million at a $9.9 billion valuation in mid-2025. They’re not treating Cursor as a finished product. They’re investing heavily in making it better.
Recent updates have added support for more AI models, better context handling, improved multi-file editing, and features specifically for reviewing AI-generated code. They acquired Supermaven, another AI coding tool, in late 2024 to enhance capabilities.
The trajectory is clear: Cursor is evolving toward being a development environment where AI assistance is native, not added on. Where the default mode is collaborating with AI, and the AI is good enough that you want to.
This is what I meant when I said it feels like Cursor is on the right path. Every update makes the product more capable and more usable. The core interaction model is solid. They’re building on a strong foundation.
If they fix the pricing confusion, there’s no reason Cursor shouldn’t become the standard development environment for anyone building software with AI assistance.
What This Means for Developers#
When the CEO of Nvidia says his entire engineering organization uses a tool, pay attention. Nvidia builds some of the most complex software and hardware in the world. Their engineers are not easily impressed. If they’ve standardized on Cursor, it’s because Cursor delivers value at the scale and complexity they operate at.
I’ve seen this personally. The features I build now are more ambitious than what I would have attempted a year ago because I know Cursor can handle the implementation details. I spend more time thinking about what to build and less time fighting with syntax.
This is the future Huang is describing. Not AI replacing developers, but AI enabling developers to work at a higher level of abstraction. To be more ambitious. To focus on design and architecture while AI handles the mechanical work.
Cursor is the tool making that possible today. Not perfectly. The pricing issues are real and frustrating. But the core product is so good that even with pricing confusion, it’s achieving the kind of adoption Huang described.
The Bottom Line#
Jensen Huang called out six companies shaping the future of work. Cursor was the only one he said has 100% adoption at Nvidia. That’s not a casual mention. That’s an endorsement from someone who sees the entire AI landscape and knows what actually works at scale.
I agree with him. After a year of using Cursor, I understand why Nvidia chose it. The UI is intuitive. The AI is capable. The integration is seamless. The productivity gains are real.
The pricing model needs work. That’s the one significant weakness, and it’s causing users to leave even though they value the product. Anysphere needs to fix this before competitors use pricing clarity to steal market share.
But the core insight remains: Cursor has figured out how to build an AI-assisted development environment that enhances rather than replaces developer judgment. It’s the tool that lets developers operate at the level Huang is describing, where AI handles implementation and humans focus on design.
That’s the innovation. That’s why it matters. And that’s why, despite the pricing frustrations, I keep using it every day.