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…
…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.
Well, now my question is “how many tokens did you use to generate an absurd amount of AI vibecoded slop that ‘sorta works’, and how many fatal security flaws does it have”?
Genuinely, how the fuck do these idiots expect to be taken seriously by anyone with more than the barest scintilla of technical knowledge? And yeah; the answer is unfortunately “they don’t care about that demographic, as long as people with zero technical knowledge are impressed”.


