[getnormality]

This weird trend reached an apex in a Feb 2026 OpenAI blog post [1], recently on the front page [2], which describes the process for building... something... written 100% by agents.

There is no description of what the thing is, no indication of what value it provides its users. The closest it gets is "the product has been used by hundreds of users internally, including daily internal power users".

But the fact that the thing has a million lines of code is repeated twice in the first few hundred words.

[1] https://openai.com/index/harness-engineering/

[2] https://news.ycombinator.com/item?id=48416264

[DrewADesign]

> "the product has been used by hundreds of users internally, including daily internal power users".

My guess is it’s an email filter.

> million lines of code

> written 100% by agents

Yeah, probably an email filter. Or maybe a JS menu for a departmental wiki that basically recreates jquery using MS JScript and transpiles it into JS 5.

[pyrale]

> My guess is it’s an email filter.

It may also be an email generator.

The email filter team is trying to match the pace of innovation of the email generation team. At stakes is the ability for the employees to process the billions of mission-critical generated emails each of them receives each day.

[DrewADesign]

It’s true. They’re all go-getters destined for big things. Look at those token burn rates!

[getnormality]

Your hilariously specific hypotheses remind me of how little I know about technology.

[DrewADesign]

> how little I know about technology.

Probably because you smoked too much weed in school.

Remember, this is the tech industry! An abject lack of knowledge is no impediment for people with boundless confidence in their assumptions!

[QuercusMax]

Ya gotta start smoking weed after you're done with school, that's the way to success

[selicos]

The best strategy is to figure out what you are going to do after smoking weed before you smoke weed. So, draft your prompt and send it before lighting up.

[wiml]

Tokenmax while you tokemax.

[packetlost]

And trash your short-term memory? Nah, smoking weed is straight up bad for most people.

[DrewADesign]

Plot twist: they weren’t even enrolled in that school.

[JCTheDenthog]

The entire Linux kernel is about 40 million LoC, and only something like 16 million LoC after you remove drivers. I have a hard time imagining whatever OpenAI was talking about there having anywhere close to 6% as much utility as the Linux kernel, despite having 6% as many lines of code. And I have a hard time imagining it's anywhere close to maintainable, regardless of how powerful their LLMs might be.

[esperent]

To be fair, few things of any number of LOC have as much utility as the Linux kernel, and it's also a particularly dense example of code. There's plenty of other examples that have higher LOC / utility ratio without being vibe coded. For example, Google's monorepo famously has 2 billion LOC, which is a statistic I've heard long before LLM coding took over.

[jeffbee]

Clarification: Google claimed to have 2 billion lines of code in their repo ten years ago, and a commit rate of 50,000 changelists per day, both on exponential growth trends.

[zaphar]

That's a monorepo with hundreds if not thousands of different applications. It's not even close to an apples to apples comparison.

[jeffbee]

That's certainly a way to look at it. And that repo contains a "third party" directory which itself contains Linux, LLVM, and much of the rest of the open source world. But I would suggest that the largest of those thousands of applications probably has a transitive closure of hundreds of millions of lines of code.

[zaphar]

I'm aware. I worked on that specific project (assuming we are talking about the same one) back in the day. :-)

There are certainly very large applications in that repo in the hundreds of millions of lines of code. But comparing the entire repo to single applications is not an apt comparison.

[strulovich]

The Linux kernel is not in any way at top of big projects. A kernel, as the name suggests, deals with specific issues and tries to remain small.

The world’s biggest software is usually built over endless adapters of different data and a need to reconcile endless edge cases with laws, regulations and real world complexities.

[dist-epoch]

Chrome has 50 mil LoC

https://openhub.net/p/chrome/analyses/latest/languages_summa...

[skydhash]

Chrome is basically reinventing each OS API and libraries. One day they’ll have their own tcp stack and packet filter.

[getnormality]

It kinda makes sense given that one of their major products is a computer that runs an operating system literally called ChromeOS.

[jeffbee]

Arguably with QUIC it already does.

[robotresearcher]

Chrome still has a way to go until Zawinski's Law is satisfied natively.

http://www.catb.org/jargon/html/Z/Zawinskis-Law.html

[m463]

When I was young, I remember a (joke) program from a book or magazine, called something like report writer or something. It was written in basic and you typed it in.

You would run it and it would say:

how many pages? _

You would type in a number, and it would generate that many pages of a complex-sounding report.

something like "the subsystem design interface is ..." blah blah

similar?

[prodigycorp]

The reality distortion field is strong around anthropic. Anthropic posts tons of equally bullshit blog posts, written entirely by AI, saying absolutely nothing, to the front page and they consistently average many hundreds of upvotes.

[malfist]

I have to wonder if HN is astroturfed. Anthropic and OpenAI can post about a new model and it gets over to HN instantly and is full of glowing reviews of supposedly real people who supposedly have had prior access to it who supposedly think it's the best model yet.

[prodigycorp]

Feels doubly so for Anthropic. There's just unbelievable level of glaze, and insane upvote velocity for "blog posts" that are essentially fluffed up feature documentation.

Somehow everything boris says has become the word of God. The dude is just an engineer, like you and me, who gets unlimited tokens for free.

[malfist]

Yeah, I sometimes catch these posts minutes after they were submitted and they're full of highly upvoted glowing reviews that maintain their momentum on the top of the page.

And this is hacker news. A place where famously the most upvoted comment is the one critical of the post.

[JackFr]

Upvoter here. Nothing special -- I like Claude a lot. I found it more ergonomic to work with, and I think its models are state of the art. I believe I'm more productive especially in legacy crufty codebases.

I may not be representative of the universe or have a controlled, randomized study to back it up, but that's not what upvotes are for are they?

[prodigycorp]

That's a fair point. To play devils advocate to myself, it's possible that the huge upvote share is due to a much bigger marketshare among our community.

[mrandish]

Yeah, that was my guess too. Still a little disappointing to see fellow HNers reflexively fanboying a company that's the overwhelming dominate player in LLM coding.

I try to reserve my reflexive fanboy company/project votes for underdogs who need and deserve the help.

[lispisok]

HN is astroturfed. Not just AI and also before AI took off. It's so easy and so valuable to astroturf HN

[joe_the_user]

The tech field has always been full of naive technology boosters. HN might be heavily astroturfed for all I know but I am sure there are many real people in a state of constant excitement over the progress of AI.

[coffeefirst]

Heavily. There’s an amount of true believers who actually think RSI is going to happen any day now, but you can spot patterns amongst brand new booster accounts…

I real life I meet people who like AI and people who hate it, but nobody who’s on a personal mission to defend Anthropic from anyone that dares to question their hyperbolic marketing.

[selcuka]

HN is probably astroturfed, but it is also one of those places where a lot of actual subject experts frequent. I don't find it unusual that a new model gets instantly posted here. It is also not unexpected that the most recently released model is the best model.

[monkpit]

Sorry, was it not this?

https://github.com/openai/symphony

[nhinck3]

That does not appear to have a million lines of code

[benj111]

Oh god why did you make me read that.

>We intentionally chose this constraint so we would build what was necessary to increase engineering velocity by orders of magnitude

What kind of wanky bs is "engineering velocity". Maybe the post was written by AI?

[habinero]

It's a real term. It's a Agile metric for measuring how much a team is shipping over time.

Whether or not the whole concept is wanky bs depends on who you ask lol. It's useful if you measure it over time, not so much otherwise.

[pramodbiligiri]

Yeah it was very disappointing that so few details were provided. One of the reasons I think it's going to be an open source project or effort that is going to show, sooner or later, how effective these things actually are.

In their podcast interview, they mention that it's an Electron app that users download, and so they periodically create a new build. See section "Autonomous Merging Flow" here: https://www.latent.space/p/harness-eng