HN Simulatornew | past | comments | lists | submit | Alacart's commentslogin

While I suspect your point about the value/quality of the work at 2000 PRs/month is directionally correct, isn’t their entire take that they’re no longer micromanaging the PRs at all? So talking about how much time they commit to each one doesn’t make much sense. It’s a bit like looking at a modern car and saying “haha how will they even get the horses to pull this?” or maybe “how do these developers know the compiler isn’t using GOTO statements underneath?”.

Now, are those PRs doing useless work? Are they introducing unnecessary risks or trade offs? Are they building towards something impossible to understand or that will fall apart under its own sloppy weight?

Those seem more like the right questions to me, in the long run, and I suspect that’s what you really have in mind. Because if the answers are no, then why wouldn’t you be doing as many PRs as possible?


A PR to me represents a specific boundary of human ... review. It's a unit of work that is typically reviewed by at least 2 team members. If I'm working solo on some project, I don't use PRs.

So to me "not micromanaging PRs" doesn't make any sense at all. Bragging about how many PRs you can get merged is like bragging about how many WPM you can get when prompting an AI instead of manually typing.


That's been the way I've worked in previous jobs too. Nonetheless some PRs need less review, others more. It's a gradient, and they're merely moving the range further towards "doesn't need in-depth" by introducing other quality gates.

That comes with trade-offs, but some may be willing to accept those. It's ultimately the decision of the developers and enterprise how they want to build their product, can't really say anything else about this


Are you arguing that the PR is unnecessary for AI/agents? Or that human review is mandatory?

All productivity metrics have flaws (usually deep ones). Doesn’t mean they’re not instructional though.


PRs are part of a software development process meant for collaborating humans. If no humans are reviewing anything, having PRs as part of the process is pretty pointless.

I mean, I agree conceptually. But the PR is just a useful unit of work.

My PRs get assessed for if a human is needed. I could probably do that at the branch level, but PRs just has all the metadata and CI/CD tooling etc etc.


Exactly this. I have repos where agents can merge their own PRs, I literally never look at them. It’s still a useful primitive.

> Or that human review is mandatory?

Depending on the domain, human review can be mandatory. (i.e. if you're a public company and the thing you're touching can materially affect the company finances)


Frontier LLMs can do reviews equal to if not better than the average dev once setup properly with guidance.

You need to work with better average devs then.

How do you square that with this quote in the article?

"The data showed that the age-adjusted incidence rate fell from 55.2 per 100,000 in 2000 to 36.7 in 2022, then rose to 38.3 in 2023."

Were more people fat back in 2000? Was the food worse? Though I don’t really doubt that the food industry and trends like you mentioned do contribute, that stat also seems to directly contradict the hypothesis.


You and orangecat are using a false binary

That’s not how science works

Show me correlating graphs to the rise in colorectal cancer. There has to be a meta-analysis about this, my money is on food being a major contributing factor


It's milk consumption:

https://tylervigen.com/spurious/custom_correlation/757_new-c...

No wait it's GMO use in corn grown in Texas:

https://tylervigen.com/spurious/custom_correlation/758_new-c...

No wait it's the popularity of the first name Devon:

https://tylervigen.com/spurious/custom_correlation/759_new-c...

No wait it's the number of postal service machine operators in Texas:

https://tylervigen.com/spurious/custom_correlation/760_new-c...

Pretty certain this isn't how science works either. Be careful mistaking correlation for causation, and in relying on intuitive hunches.


> my money is on food being a major contributing factor

That's not how science works either.


Imagine how immensely well looked-upon they would be now if they had come public about it, with a long term transition plan. Imagine a world where executives had that kind of courage.


Like Al Gore? People love him I think


This makes a ton of sense to me with the huge corpus of web standards that exist. In theory we should be able to generate a browser from those specs, it just took a massive amount of effort before. Maybe if things like this get some traction, some of the human time spent implementing the spec could be spent on creating more/better specs, allowing for even better generation too.

Edit: replies are making good points about AI capabilities and where the effort really goes. Let’s just say that I meant this in an aspirational sense, rather than where the rubber actually meets the road today.


As someone who has spent the last 3 years implementing a browser engine from scratch full time (that currently passes ~half the 200k "css" tests that test style/layout/rendering), I find that (without a lot of close hand holding) the AIs are very far from being able to do this. They'll give you something that passes the tests, but it will do it a ridiculous way be far too slow to be useful (and is wrong architecturally such that it's not going to converge on a better solution).


I guess my hope is that while this may be the case now, perhaps it won’t be eventually. If you can generate from a spec, different implementations may be slower or worse in a variety of ways but still meet the spec.

At that point it’s about optimizing and deciding trade offs, both of which might mean heavily directing the generation in some way. Over time, maybe LLMs or whatever succeeds them won’t go down so many bad architectural paths. We’ve certainly seen that already in the last year or two.

I also don’t think folks like you ever lose your value in these efforts, even if all of it came true tomorrow. At worst it would be you plus the AI, which would always be a more potent combination than say, me with an AI trying to make a browser engine.


> I guess my hope is that while this may be the case now, perhaps it won’t be eventually.

I hear you brother. I, too, hope that one of the two or three companies will be able to improve and displace everything. Who needs Linux anyway.

Hope you are on the right side of the fence.


> I, too, hope that one of the two or three companies will be able to improve and displace everything. Who needs Linux anyway.

In the context of browsers the domination of one or two companies is already complete, and being able to generate new browsers with AI would hopefully allow people to escape the stranglehold of Chrome/Blink.

That said, I doubt a new,competitive browser could be created that way. The (possibly AI) developers of web apps won’t want to test on somebody’s bespoke AI-generated browser.


What does this have to do with Linux? I want more control for individuals, not less.

Do you really think LLMs will only belong to 2 or three companies in the future, when we already have fairly competitive open weights usable from home (or rented servers)? How would this be anything but the opposite of centralization amongst 2 or 3 companies, which is already the case now? Software has always been displacing things, especially itself.


I think you meant to respond to bergheim not to me.


Sorry, you’re right, I did.


But what are you writing about, LoL? Linux is just normal OS. Why did you mention Linux?


I recognize the feeling of handholding and have the tingles telling me that given the step change of Opus 5.5 and what passed by in the news lately, agent swarms are about to become mainstream. That's exactly what a project like this would use. I think everybody will be able to create their own engine and out of the ones who try, a few will actually make gains beyond what's available in parts of the engine.

It's a matter of "bring the best non-conflicting wins together" at that point. The existing engines are too big to flip over their codebase without having seen competitors prove it too.

My estimate is that with the release of Opus 5.7, companies need to have their shit together because the work ecosystem will flip over at 6 at the current rate of progress. This generation is the first one that delivers local applications with a better toolset than a small scale SaaS in hours to days.


Could you say which AI/LLMs you mean?


I've tried most of them. Certainly all the Open AI and Anthropic models. Fable is still the best I've tried. But it still struggles with architectural issues.


> far too slow to be useful

Speed is probably not part of a web spec.

> wrong architecturally

Nor is software architecture (though web security specs may have some influence here).


> Speed is probably not part of a web spec.

"being a grandmother is not part of the bike frame spec so my grandmother with wheels is a bike"


What do you mean by grandmother with wheels?



Not sure why you are being downvoted, but this is definitely a limitation of current models and difficult to optimize for. Anything you are not specifically optimizing for is essentially unconstrained: the model could learn it by pure chance, but the likelihood is exceedingly low.

Techniques, like the newly announced RL-XAR from Meta [1] are being developed that will likely improve reward models and guide RL training to optimize for metrics like software architecture that are hard to verify otherwise.

[1]: https://facebookresearch.github.io/RAM/blogs/unslop/


There’s quite a few edge cases where browsers allow non-compliant code to render as if it were to specs. Because if a site doesn’t render “correctly” from a user perspective, they blame the browser rather than blaming the web developer.


That does happen, but these days they tend to add that kind of thing to the spec (and the test suite). There was a minor drama several years when WHATWG (representing browser vendors) effectively took over the spec process from the W3C because they were fed up with the W3C taking an idealistic viewpoint, and speccing things that they couldn't actually implement.


To be fair - my recollection was "representing browser vendors and pragmatists". It was far from rhe industry stitch-up that that might sound like to modern ears.


That’s good to know. The W3C probably did more to hamper web standards than anyone else (except maybe Microsoft). So I’m not surprised WHATWG took over.


> In theory we should be able to generate a browser from those specs, it just took a massive amount of effort before.

No, not really. The absolute vast majority of those specs are human technical and technical-adjacent language, not machine-readable specs.

On top of that many web specs often invent new terminology because a lot of things are specced years or decades after something popular has taken over the term in userland.


Maybe over time the specs will become more machine readable (bounded and concrete) if we take these paths. Although in some sense everything is machine readable these days, just not deterministically so (less helpful for specs, but not nothing either).

Your second point makes a lot of sense to me too. I’m not sure how this could handle that facet of human nature, except possibly to indirectly contribute to speeding up the cycle of spec creation.


I think browser performance (and security) improvements are really difficult to tackle at the scale of browser complexity, and are both art and engineering. In other words, if this were possible, we would see the results first in existing browsers. This project is very interesting though.


Maybe some day this will be the basis but not the complete solution. Agreed that there’s a lot of semi intangible art that goes into browser engine decisions. I’m guessing a lot of which have to do as much with people and current landscape dynamics as they do with the tech.


Where in the web standards do you find specifications like how bookmark toolbars and menus should be organized, or that Shift-Ctrl-T should bring back a tab that was closed?


We're talking about a browser _engine_. The shell/chrome is irrelevant in this context


But some parts are far from being trivial engineering and are not part of any specs. Just consider the security infrastructure (multiprocess, sandboxing etc.) and how that impacts the overall design of the engine itself.


> asking me during the test to explain what LLM output meant.

Perhaps (sarcastically) this is the new approach, because this is now the point where they’re forced to struggle and therefore actually learn. An exam every other day, let them ask the questions.


Not sarcastically, this is the flipped classroom approach. Read the examples and watch the lecture on your own time, then come and do the exercises with a teacher available to explain when you realize you didn’t understand anything.


It’s a good thing that they’ve committed many blatant and easily provable criminal acts then. The type you spend the rest of your life in prison for, if you’re not being protected by captured systems. Market manipulation, insider trading, embezzlement are all happening obviously and publicly, just to start. Bribery and corruption at many levels, illegal use of things like ICE, illegal detention, ignoring and abusing courts and the judicial system, whatever the hell they’re doing with crypto, the list is basically whatever crime you can think of. I understand you, and that it will mean republicans and their base won’t be swayed, which will create huge problems. But we’re well past the point that anything would ever sway them. There’s no easy way out now, the choice is being increasingly abused by them forever or taking the hits now to stop it. Pulling punches now will only ensure that it comes back 10x worse later.


If I had to guess at anything it would be bribery, market manipulation, and crypto related business. The others I just don’t see even making it through, there is way too much room for interpretation of powers.

“Pulling punches now will only ensure that it comes back 10x worse later” and using punches will what, subdue? This is half the political power of America you’re talking about punching. Republicans will what, roll over? You think democrats win handily enough to end it?

It escalates the blood feud. The way out of a blood feud is de-escalation, amnesty, forgiveness, working together. Not demanding more blood, even if you think it is perfectly justified.


I generally believe that, but there is such a thing as “too far”.

Your (I’m assuming well intentioned) arguments are those that people abusing power trot out whenever it suits them, because it works so well to get them off the hook when the people they’re abusing are decent human beings. “Now that we’ve tried our best to destroy things, don’t you think it’s important we all forgive and forget?”

I also think you’re taking my point to mean punishing republican voters, which I’m not. I’m talking about upholding and enforcing laws against the politicians and their accomplices in the party, as they’re intended to be. Rather than taking the less confrontational path of letting it all slide after they lose power. That’s how this mess started in the first place.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: