https://www.theregister.com/2026/01/26/cursor_opinion/ # # Sign in / up The Register # # # Topics Security Security All SecurityCyber-crimePatchesResearchCSO (X) Off-Prem Off-Prem All Off-PremEdge + IoTChannelPaaS + IaaSSaaS (X) On-Prem On-Prem All On-PremSystemsStorageNetworksHPCPersonal TechCxOPublic Sector (X) Software Software All SoftwareAI + MLApplicationsDatabasesDevOpsOSesVirtualization (X) Offbeat Offbeat All OffbeatDebatesColumnistsScienceGeek's GuideBOFHLegalBootnotesSite NewsAbout Us (X) Special Features Special Features All Special Features Agentic AI The Future of the Datacenter AWS Re:invent SC25 Supercomputing Month Cloud Infrastructure Month Datacenter Networking Nexus The State of Storage European Supercomputing AI Infrastructure Month Spotlight on RSAC AI Software Development Week Disaster Recovery Week Nvidia GTC Ransomware in Focus Cybersecurity Month VMware Explore Vendor Voice Vendor Voice Vendor Voice All Vendor Voice HERE and AWS Guidewire InsuranceNow Intel Core Ultra Processors: Powering business-ready AI PCs ZTE Nutanix: Scale Kubernetes. Not Chaos. Money Movement Hub The BigQuery Difference AWS Global Partner Security Initiative Amazon Web Services (AWS) New Horizon in Cloud Computing (X) Resources Resources Whitepapers Webinars & Events Newsletters [agenticai] Agentic AI 17 comment bubble on white When AI 'builds a browser,' check the repo before believing the hype 17 comment bubble on white Autonomous agents may generate millions of lines of code, but shipping software is another matter icon Steven J. Vaughan-Nichols Mon 26 Jan 2026 // 12:01 UTC # Opinion AI-integrated development environment (IDE) company Cursor recently implied it had built a working web browser almost entirely with its AI agents. I won't say they lied, but CEO Michael Truell certainly tweeted: "We built a browser with GPT-5.2 in Cursor." He followed up with: "It's 3M+ lines of code across thousands of files. The rendering engine is from-scratch in Rust with HTML parsing, CSS cascade, layout, text shaping, paint, and a custom JS VM." That sounds impressive, doesn't it? He also added: "It *kind of* works," which is not the most ringing endorsement. Still, numerous news sources and social media chatterboxes ran with the news that AI built a web browser in a week. [agenticai] Too bad it wasn't true. If you actually looked at Cursor engineer Wilson Lin's blog post about FastRender, the AI-created web browser, you won't see much boasting about a working web browser. Instead, there's a video of a web browser sort of working, and a much less positive note that "building a browser from scratch is extremely difficult." [agenticai] [agenticai] The thing about making such a software announcement on GitHub is that while the headlines are proclaiming another AI victory, developers have this nasty trick. They actually git the code and try it out. Developers quickly discovered the "browser" barely compiles, often does not run, and was heavily misrepresented in marketing. [agenticai] As a techie, the actual blog post about how they tried and didn't really succeed was much more interesting. Of course, that Cursor sicced hundreds of GPT-5.2-style agents which ran for a week to produce three million lines of new code, to produce, at best, a semi-functional web browser from scratch, doesn't make for a good headline. According to Perplexity, my AI chatbot of choice, this week-long autonomous browser experiment consumed in the order of 10-20 trillion tokens and would have cost several million dollars at then-current list prices for frontier models. I'd just cloned a copy of Chromium myself, and for all that time and money, independent developers who cloned the repo reported that the codebase is very far from a functional browser. Recent commits do not compile cleanly, GitHub Actions runs on main are failing, and reviewers could not find a single recent commit that was built without errors. [agenticai] Where builds succeeded after manual patching, performance was abysmal, with reports of pages taking around a minute to load and a heavy reliance on existing projects like Servo, a Rust-based web rendering engine, and QuickJS, a JavaScript engine, despite "from scratch" claims. Lin defended the project on Y Combinator, saying, for instance: "The JS engine used a custom JS VM being developed in vendor/ecma-rs as part of the browser, which is a copy of my personal JS parser project vendored to make it easier to commit to." If it's derived from his personal JavaScript parser, that's not really from scratch, is it? Nor is it, from the sound of the argument, written by AI. * Just because Linus Torvalds vibe codes doesn't mean it's a good idea * The Microsoft 365 Copilot app rebrand was bad, but there are far worse offenders * The most durable tech is boring, old, and everywhere * What the Linux desktop really needs to challenge Windows Gregory Terzian, a Servo maintainer, responded: "The actual code is worse; I can only describe it as a tangle of spaghetti... I can't make much, if anything, out of it." He then gave the backhanded compliment: "So I agree this isn't just wiring up of dependencies, and neither is it copied from existing implementations: it's a uniquely bad design that could never support anything resembling a real-world web engine." Now that's a burn. From where I sit, what makes the Cursor case more dangerous than just a failed hack-week project is that the hype is baked into its methodology. The "experiment" wasn't presented as what it really was: an interesting, but messy, internal learning exercise. No, it was rolled out as a milestone that conveniently confirmed the company's long-running autonomous agent advertising. Missing from the story were basics any senior engineer would demand: passing Continuous Integration (CI), reproducible builds, and real benchmarks that show the browser doing more than limping through a hello-world page. Zoom out, and CEOs are still predicting that AI will write 90 percent of code in a year, while most enterprise AI pilots still fail to deliver meaningful return on investment. We're now in a kind of AI uncanny valley for developers. Sure, tools like Cursor can be genuinely helpful as glorified autocomplete and refactoring assistants, but marketing keeps insisting junior engineers can take whole projects from spec to shipping. When you start believing your own sizzle reel, you stop doing the tedious validation work that separates a demo from a deliverable. Enough already. The hype has grown cold. Sarah Friar, OpenAI's CFO, recently blogged that in 2026, its focus would be on "practical adoption." Let's see real-world practical results first, and then we can talk about practical AI adoption. (r) Get our Tech Resources # Share More about * AI * Web Browser More like these x More about * AI * Web Browser Narrower topics * AIOps * Brave * Chrome * cookies * DeepSeek * Firefox * Gemini * Google AI * GPT-3 * GPT-4 * HTTP * Internet Explorer * Large Language Model * Machine Learning * MCubed * Microsoft Edge * Neural Networks * NLP * Opera * Retrieval Augmented Generation * Safari * Star Wars * Tensor Processing Unit * TOPS * Vivaldi Broader topics * Self-driving Car * Software More about # Share 17 comment bubble on white COMMENTS More about * AI * Web Browser More like these x More about * AI * Web Browser Narrower topics * AIOps * Brave * Chrome * cookies * DeepSeek * Firefox * Gemini * Google AI * GPT-3 * GPT-4 * HTTP * Internet Explorer * Large Language Model * Machine Learning * MCubed * Microsoft Edge * Neural Networks * NLP * Opera * Retrieval Augmented Generation * Safari * Star Wars * Tensor Processing Unit * TOPS * Vivaldi Broader topics * Self-driving Car * Software TIP US OFF Send us news --------------------------------------------------------------------- Other stories you might like AWS's inevitable destiny: becoming the next Lumen The cloud giant talks loudest about what scares it most. Here's what should terrify it PaaS + IaaS26 Jan 2026 | Canva among ~100 targets of ShinyHunters Okta identity-theft campaign Atlassian, RingCentral, ZoomInfo also among tech targets Cyber-crime26 Jan 2026 | How one developer used Claude to build a memory-safe extension of C feature Robin Rowe talks about coding, programming education, and China in the age of AI Devops26 Jan 2026 | 2 The AI PC needs to deliver more than performance - it needs to deliver security Scanning the future Sponsored Feature [agenticai] Microsoft's Maia 200 promises Blackwell levels of performance for two-thirds the power Inference-optimized chip 30% cheaper than any other AI silicon on the market today, Azure's Scott Guthrie claims Systems26 Jan 2026 | 1 US ownership of TikTok off to a rocky start as outage continues into second day The new US-based joint venture blamed a datacenter power outage, but hasn't elaborated SaaS26 Jan 2026 | 9 Claude can now disgorge interface elements from other apps An official Model Context Protocol extension Agentic AI26 Jan 2026 | 2 Tech employees demand their leaders take a stand against ICE But CEOs remain frozen in place Public Sector26 Jan 2026 | 47 AI adoption at work flatlined in Q4, says Gallup Points to a use-case problem AI + ML26 Jan 2026 | 9 Keep it simple, stupid: Agentic AI tools choke on complexity Even agents checking other agents can still get it wrong Agentic AI26 Jan 2026 | 2 Internet spent Q4 '25 losing fights with cables, power, and itself Latest data from Cloudflare shows cable cuts, power failures, and network faults drive steady run of internet outages Networks26 Jan 2026 | 1 KDE Plasma 6.6 beta ships a login manager that won't log in without systemd Bad luck, BSDs - although alternatives still work OSes26 Jan 2026 | 17 The Register icon Biting the hand that feeds IT About Us* * Contact us * Advertise with us * Who we are Our Websites* * The Next Platform * DevClass * Blocks and Files Your Privacy* * Cookies Policy * Privacy Policy * Ts & Cs * Do not sell my personal information Situation Publishing Copyright. All rights reserved (c) 1998-2025 no-js