That was from a conversation here on Hacker News the other day: https://news.ycombinator.com/item?id=46624541#46709191
They were making claims without the level of rigor to back them up. There was an opportunity to learn some difficult lessons, but—and I don’t think this was your intention—it came across to me as kind of access journalism; not wanting to step on toes while they get their marketing in.
I only know this because on occasion I'll notice there was a comment from them (I only check the name of the user if it's a hot take) and I ctrl-F their username to see 20-70 matches on the same thread. Exactly 0 of those comments present the idea that LLMs are seriously flawed in programming environments regardless of who's in the driver seat. It always goes back to operator error and "just you watch, in the next 3 months or years...".
I dunno, I manage LLM implementation consulting teams and I will tell you to your face that LLMs are unequivocally shit for the majority of use cases. It's not hard to directly criticize the tech without hiding behind deflections or euphemisms.
Why would I say that when I very genuinely believe the opposite?
LLMs are flawed in programming environments if driven by people who don't know how to use them effectively.
Learning to use them effectively is unintuitive and difficult, as I'm sure you've seen yourself.
So I try to help people learn how to use them, through articles like https://simonwillison.net/2025/Mar/11/using-llms-for-code/ and comments like this one: https://news.ycombinator.com/item?id=46765460#46765940
(I don't ever say variants of "just you watch, in the next 3 months or years..." though, I think predicting future improvements is pointless when we can be focusing on what the models we have right now can do.)
Comments usually point out the issues or more grounded reality.
BTW I'm bullish on AI, going through 100s of millions of tokens per month.
The quality of whatever they put out as a result of it is yours to take into consideration.
The claims they made really weren't that extreme. In the blog post they said:
> To test this system, we pointed it at an ambitious goal: building a web browser from scratch. The agents ran for close to a week, writing over 1 million lines of code across 1,000 files. You can explore the source code on GitHub.
> Despite the codebase size, new agents can still understand it and make meaningful progress. Hundreds of workers run concurrently, pushing to the same branch with minimal conflicts.
That's all true.
On Twitter their CEO said:
> We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week.
> 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.
> It kind of works! It still has issues and is of course very far from Webkit/Chromium parity, but we were astonished that simple websites render quickly and largely correctly.
That's mostly accurate too, especially the "it kind of works" bit. You can take exception to "from-scratch" claim if you like. It's a tweet, the lack of nuance isn't particularly surprising.
In the overall genre of CEO's over-hyping their company's achievements this is a pretty weak example.
I think the people making out that Cursor massively and dishonestly over-hyped this are arguing with a straw man version of what the company representatives actually said.
> In the overall genre of CEO's over-hyping their company's achievements this is a pretty weak example
I kind of agree, but kind of not. The tweet isn't too bad when read from an experienced engineer perspective, but if we're being real then the target audience was probably meant to be technically clueless investors who don't and can't understand the nuance.
It's like claiming "my dog filed my taxes for me!" when in reality everything was filled out in TurboTax and your dog clicked the final submit button. Technically true, but clearly disingenuous.
I'm not saying an LLM using existing libraries is a bad thing--in fact I'd consider an LLM which didn't pull in a bunch of existing libraries for the prompt "build a web browser" to be behaving incorrectly--but the CEO is misrepresenting what happened here.
> "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."
It didn't use Servo, and it wasn't just calling dependencies. It was terribly slow and stupid, but your comment is more of a mischaracterization than anything the Cursor people have said.
[0] https://github.com/search?q=repo%3Awilsonzlin%2Ffastrender%2...
[1] https://github.com/search?q=repo%3Awilsonzlin%2Ffastrender+h...
https://github.com/DioxusLabs/taffy
Used here (I think): https://github.com/servo/servo/tree/c639bb1a7b3aa0fd5e02b40d...
It was originally a derivative of React Native's Yoga implementation of Flexbox, and is currently developed primarily as part of the Blitz engine.
But it was accompanied by a link to the GitHub repo, so you can hardly claim that they were deliberately hiding the truth.
If anything, that proves the point that they weren't rigorous! They claimed a thing. The thing didn't accomplish what they said. I'm not saying that they hid it but that they misrepresented the thing that they built. My comment to you is that the interview didn't directly firmly pressure them on this.
Generating a million lines of code in parallel isn't impressive. Burning a mountain of resources in parallel isn't noteworthy (see: the weekly post of someone with an out of control EC2 instance racking up $100k of charges.)
It would have been remarkable if they'd built a browser from scratch, which they said they did, except they didn't. It was a 50 million token hackathon project that didn't work, dressed up as a groundbreaking example of their product.
As feedback, I hope in the future you'll push back firmly on these types of claims when given the opportunity, even if it makes the interviewee uncomfy. Incredible claims require incredible evidence. They didn't have it.
I don't think directly accusing them of being misleading about what they had done would have supported that goal, so I didn't do it.
Instead I made sure to dig into things like what QuickJS was doing in there and why it used Taffy as part of the conversation.
> Honestly, grilling him about what the CEO had tweeted didn't even cross my mind.
Today:
> I don't think directly accusing them of being misleading about what they had done would have supported that goal, so I didn't do it.
I find it hard to follow how it didn't cross your mind while for the same interview you had also considered the situation and determined it didn't meet the interview goal.
It didn't cross my mind to grill him over his CEO's tweets.
I also don't think that directly accusing them of being misleading would support the goal of my interview - which was to figure out the truth of what they built and how.
If you like, I'll retract the fragment "so I didn't do it" since that implies that I thought "maybe I should grill him about what the CEO said... no actually I won't" - which isn't what happened.
So I guess you win?
I believe in the UK the term for this is actually fraudulent misrepresentation:
https://en.wikipedia.org/wiki/Misrepresentation#English_law
And in this context it seems to go against The Consumer Protection from Unfair Trading Regulations 2008 and the Digital Markets, Competition and Consumers Act 2024:
For starters, the language is highly subjective, and they'd be able to show vast amounts of discourse about software engineering where "from scratch" often does not involve starting with nothing, and they'd then go on to argue that the person suing haven't actually had any reason to believe that they would be able to replicate a setup that was described as a complex large-scale experiment without much more information.
The person suing would have an uphill battle showing that whatever assumptions they made were something that was reasonable to infer based on that statement.
And to have a case, a consumer would also then need to have relied on this as a significant factor in choosing to buy their services.
But even if we assume the court would agree it is fraudulent, the remedy is only "directly consequential losses".
In other words, I doubt anyone would lose sleep over this risk.
Well, yes and no; we live in an era where people consume headlines, not articles, and certainly not links to Github repositories in articles. If VCs and other CEOs read the headline "Cursor Agents Autonomously Create Web Browser From Scratch" on LinkedIn, the project has served its purpose and it really doesn't matter if the code compiles or not.
It's far more dishonest to search for contrived interpretations of their statements in an attempt to frame them as "mostly accurate" when their statements are clearly misleading (and in my opinion, intentionally so).
You're giving them infinite benefit of the doubt where they deserve none, as this industry is well known for intentionally misleading statements, you're brushing off serious factual misrepresentations as simple "lack of nuance" and finally trying to discredit people who have an issue with all of this.
With all due respect, that's not the behavior of a neutral reporter but someone who's heavily invested in maintaining a certain narrative.
> We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week.
tweet was seen by over 6 million people.
The follow up tweet which includes the link to the actual details was seen by less than 200000.
That's just how Twitter engagement works and these companies know it. Over 6 million people were fed bullshit. I'm sorry, but it's actually a great example of CEOs over hyping their products.
You only quoted the first line. The full tweet includes the crucial "it kind of works" line - that's not in the follow-up tweet, it's in the original.
Here's that first tweet in full:
> We built a browser with GPT-5.2 in Cursor. It ran uninterrupted for one week.
> 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.
> It kind of works! It still has issues and is of course very far from Webkit/Chromium parity, but we were astonished that simple websites render quickly and largely correctly.
The second tweet, with only 225,000 views, was just the following text and a link to the GitHub repository:
> Excited to continue stress testing the boundaries of coding agents and report back on what we learn.
> Code here: https://github.com/wilsonzlin/fastrender
You have a reputation. You don’t need to carry water for people who are misleading people to raise VC money. What’s the point of you language lawyering about the precise meaning of what he said?
“No no, you don’t get it guys. I’m technically right if you look at the precise wording” is the kind of silly thing I do all the time. It’s not that important to be technically right. Let this one go.
The reason I won't let this one go is that I genuinely believe people are being unfair to the engineer who built this, because some people will jump on ANY opportunity to "debunk" stories about AI.
I won't stand for misleading rhetoric like "it's just a Servo wrapper" when that isn't true.
this level of outrage seems absent when it's misleading in the pro-"AI" direction
https://github.com/wilsonzlin/fastrender/issues/98
A project that didn't compile at all counts as "kind of" working now?
> I won't stand for misleading rhetoric like "it's just a Servo wrapper" when that isn't true.
True, at least if it was a wrapper then it would actually kind of work, unlike this which is the most obvious case of hyping lies up for investors I've witnessed in the last... Well, week or so, considering how much bullshit spews out of the mouths of AI bros.
"This project is junk that doesn't even compile", for example.