I wish your recent interview had pushed much harder on this. It came across as politely not wanting to bring up how poorly this really went, even for what the engineer intended.
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.
On the contrary, we get to read hundreds of his comments explaining how the LLM in anecdote X didn't fail, it was the developer's fault and they should know better than to blame the LLM.
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.
(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.)
I literally see their posts every (other) day, and its always glazing something that doesn't fully work (but is kind of cool at a glance) or is really just hyped beyond belief.
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 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.
> 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 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.
> 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.
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.
What people take issue with is the claim that agents built a web browser "from scratch" only to find by looking deeper that they were using Servo, WGPU, Taffy, winit, and other libraries which do most of the heavy lifting.
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.
Did you read the comment that started this thread? Let me repeat that, ICYMI:
> "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.
You're right in the sense it didn't `use::servo`, merely Servo's CSS parser `cssparser`[0] and Servo's DOM parser `html5ever`[1]. Maybe that dog can do taxes after all.
Sorry, just to be clear, the defense that they pulled something out of their ass is that they linked to something that outed them? So they couldn't have actually have been overstating it?
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.
> 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.
I don't think those two statements are particularly inconsistent.
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.
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:
> But it was accompanied by a link to the GitHub repo, so you can hardly claim that they were deliberately hiding the truth.
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.
According to the twitter analytics you can see on the post (at least on nitter), the original
> 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.
The fact that the codebase is meaningless drivel has already been established, you don’t need to defend them. It’s just pure slop, and they’re trying to get people to believe that it’s a working browser. At the time he bragged about that `cargo build` didn’t even run! It was completely broken going back a hundred commits. So it was a complete lie to claim that it “kind of works”.
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.
Which part of their CEO saying "It kind of works" are you interpreting as "trying to get people to believe that it’s a working browser"?
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.
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.
It’s been fascinating, watching you go from someone who I could always turn into more sensible opinion about technology for the last 15 years, to a sellout whose every message drips with motivated reasoning.
Well I have watched the show adaptation of Shogun, which features authentic Japanese language, and enjoy the occasional Omakase (in Brooklyn), so I’d say I’m pretty qualified to comment on Japanese rail over the past sixty years.
That one doesn't reflect well on the airline IMO. There should be systems in place to help employees cope with mental health issues so that they don't end up hijacking their own plane.
Employees get options at common stock prices. The valuations you see, like $12bn, are for preferred stock. So no employees got stock priced at $12bn, but all of them get paid at a $5.15bn valuation.
Not saying they did well, but depending on the 409a valuations, they still might have made money.
Edit: friends, if you’re going to downvote please leave a comment as to why. It’s okay to disagree! There’s a lot of misleading FUD in these discussions about equity. It’s helpful for everyone to hear those sides.
Their options should be priced lower, but the common stock isn't valued according to the $5.15B. They raised $300M at $12B and $425M at $7.4B, which are both under water, so those shareholders will use their liquidation preference to get paid at least 1x. Assuming those rounds owned 7% of the company, there is at most $4.4B left for the remaining 93% of shareholders. That's about 8% less. If they deducted fees, legal services, or retention packages or had worse liquidation preferences or more underwater rounds, then it gets even lower.
More specifically, when employees are granted options contracts the strike price of those contracts is based on the last valuation of the company prior to the grant. If all is going well and the valuation is increasing those options are also increasing in value. Here we have a sale which values the company lower than the prior valuation. Recent option grants will likely be underwater, earlier grants would still be profitable.
> The valuations you see, like $12bn, are for preferred stock.
No, the valuation is for the whole company, all of its shares, preferred and common. How this value is distributed among shareholders depends on the deal, but generally there is a “seniority”, roughly: creditors (debt holders) are paid first, preferred shares next, then common shareholders last. This order can be negotiated as part of the sale.
> So no employees got stock priced at $12bn, but all of them get paid at a $5.15bn valuation.
It’s just not possible to know what each individual employee’s outcome is. We don’t know how much of that 5.5 billion will be left over for common shareholders including the employees. Note that employees have received salaries so their overall outcome is greater than zero dollars, but perhaps their total compensation outcome is lower than they hoped for the time they put in.
> Not saying they did well, but depending on the 409a valuations, they still might have made money.
Yes, some might have and some might have not. We just don’t know without more details.
Edit: singron’s answer (sibling comment) attempts to model the employee outcome in a rough but reasonable way.
The way they get to $12.5bn is multiplying the preferred share price by the total outstanding shares. But the common shares, while still included in that calculation, are not worth the same amount of money.
They have a different strike price for options that is set via a 409a.
It’s possible that employees got, at the peak, grants with strike prices at a $2bn 409a valuation. We don’t know. What we do know is that no employee ever got grants with a strike price of a $12.5bn valuation. That’s just not how this works.
Not a great analogy. I've had a far better experience with Claude for simple medical questions than googling or waiting for a response from a doctor. For example, last night I had a panic attack triggered by chugging a protein shake that was expired/gone bad. It was too late for any friends to be awake.
Talking with Claude was incredibly helpful. It gave concrete suggestions for managing the anxiety in the moment and explained what was likely happening with my body and nervous system. It was the correct tool for the job.
AGI would be able to exponentially improve at much, much better money making schemes like high frequency trading. It would beat every online business. It would run 24/7/365.26 farming out tens of thousands of conversations at once, customized to the person it's talking to, for sales, supplier negotiations, marketing, press, etc.
Its costs would be frighteningly low compared to human employees, so it's margins could remain fine at lower prices.
AI is not a bigger grift than crypto. Crypto produced basically nothing of value. If all model improvement stops today, Opus 4.5 with Claude Code is a huge leap in productivity building certain types of software.
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.
reply