By the way, a pet peeve of mine right now is that reporters covering court cases (and we have so many of public interest lately) never seem to simply paste the link to the online PDF decision/ruling for us all to read, right in the story. (and another user here kindly did that for us below: https://storage.courtlistener.com/recap/gov.uscourts.dcd.223... )
It seems such a simple step (they must have been using the ruling PDF to write the story) yet why is it always such a hassle for them to feel that they should link the original content? I would rather be able to see the probably dozens of pages ruling with the full details rather than hear it secondhand from a reporter at this point. It feels like they want to be the gatekeepers of information, and poor ones at that.
I think it should be adopted as standard journalistic practice in fact -- reporting on court rulings must come with the PDF.
Aside from that, it will be interesting to see on what grounds the judge decided that this particular data sharing remedy was the solution. Can anyone now simply claim they're a competitor and get access to Google's tons of data?
I am not too familiar with antitrust precedent, but to what extent does the judge rule on how specific the data sharing need to be (what types of data, for what time span, how anonymized, etc. etc.) or appoint a special master? Why is that up to the judge versus the FTC or whoever to propose?
Hard_Space · 2h ago
> By the way, a pet peeve of mine right now is that reporters covering court cases never seem to simply paste the link to the online PDF decision/ruling for us all to read right in the story.
I presume that this falls under the same consideration as direct links to science papers in articles that are covering those releases. Far as I can tell, the central tactic for lowering bounce rate and increasing 'engagement' is to link out sparsely, and, ideally, not at all.
I write articles on new research papers, and always provide a direct link to the PDF,; but nearly all major sites fail to do this, even when the paper turns out to be at Arxiv, or otherwise directly available (instead of having been an exclusive preview offered to the publication by the researchers, as often happens at more prominent publications such as Ars and The Register).
In regard to the few publishers that do provide legal PDFs in articles, the solution I see most often is that the publication hosts the PDF itself, keeping the reader in their ecosystem. However, since external PDFs can get revised and taken down, this could also be a countermeasure against that.
kevin_thibedeau · 1h ago
Articles about patent infringement are similarly annoying when the patent numbers aren't cited. This is basic 21st century journalism 101. We aren't limited to what fits on a broadside anymore.
We need an AI driven extension that will insert the links. This would be a nice addition to Kagi as they could be trusted to not play SEO shenanigans.
bawolff · 28m ago
I think one of the lessons of Wikipedia, is the more you link out the more they come back.
People come to your site because it is useful. They are perfectly capable of leaving by themselves. They don't need a link to do so. Having links to relavent information that attracts readers back is well worth the cost of people following links out of your site.
travoc · 14m ago
Wikipedia eventually failed.
kelvinjps10 · 9m ago
What do you mean? It's one of the most popular sites
Workaccount2 · 2h ago
Never link outside your domain has been rule #1 of the ad-driven business for years now.
Once users leave your page, they become exponentially less likely to load more ad-ridden pages from your website.
Ironically this is also why there is so much existential fear about AI in the media. LLMs will do to them what they do to primary sources (and more likely just cut them out of the loop). This Google story will get a lot of clicks. But it is easy to see a near future where an AI agent just retrieves and summarizes the case for you. And does a much better job too.
bc569a80a344f9c · 1h ago
> But it is easy to see a near future where an AI agent just retrieves and summarizes the case for you. And does a much better job too.
I am significantly less confident that an LLM is going to be any good at putting a raw source like a court ruling PDF into context and adequately explain to readers why - and what details - of the decision matter, and what impact they will have. They can probably do an OK job summarizing the document, but not much more.
I do agree that given current trends there is going to be significant impact to journalism, and I don’t like that future at all. Particularly because we won’t just have less good reporting, but we won’t have any investigative journalism, which is funded by the ads from relatively cheap “reporting only” stories. There’s a reason we call the press the fourth estate, and we will be much poorer without them.
There’s an argument to be made that the press has recently put themselves into this position and hasn’t done a great job, but I still think it’s going to be a rather great loss.
hkt · 53m ago
Here is a naive prompt to Claude asking it to give some insight on the story. I'm curious about what you think of it. To be clear, I'm deeply pro-journalism, and pro-investigative-journalism at that.
It is, in my view, a decent bit of reporting generated very very quickly and with a high level of readability, though. I'd be keen to hear what you think.
This is a landmark court ruling on remedies in the Google search monopoly case from September 2, 2025. The court previously found that Google violated Section 2 of the Sherman Act by maintaining monopolies in general search services and search text advertising through exclusive distribution agreements.
The judge rejected the most aggressive remedies (Chrome divestiture, payment bans) because "Plaintiffs overreached in seeking forced divesture of these key assets, which Google did not use to effect any illegal restraints" [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) and because cutting off payments would "impose substantial—in some cases, crippling—downstream harms to distribution partners, related markets, and consumers" [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) .
This represents a middle-ground approach that avoids the most disruptive structural remedies while still imposing meaningful constraints on Google's anti-competitive behavior. The 6-year term and focus on data sharing and syndication requirements suggest the court is trying to foster competition without breaking up Google's core assets. The heavy emphasis on AI competition indicates the court sees this emerging technology as the most viable path to challenging Google's search dominance going forward.
The ruling reflects a careful balance between punishing past violations and avoiding over-regulation of a rapidly evolving tech landscape, particularly around AI development.
The problem is you started with a link. Explain the case like news did and see what comes out.
fn-mote · 3m ago
A link to the court case (not the news article) seems like a valid starting place when asking for background and a summary of the case.
supernova87a · 2h ago
I guess they are unable to value the function that I am more likely to read and trust stories from their website if they give me the honest info about where their stories come from that I can further read (and rely on them to always point me to as a guide).
permo-w · 2h ago
they likely, and probably correctly, do not want you as a customer. people who are discerning and conscious like this generally use an adblocker, and even if you don't, are generally less easily influenced by adverts in the first place. most people like this tend towards wealthy, so it's a valuable demographic if they can get past those two issues, but they're not easy to get past
supernova87a · 1h ago
You made me snort with laughter with how right you were. I in fact have 2 adblockers on, and I actively ignore and sanitize some of my history (like Youtube) to not get directed towards advertising or other rabbit holes I don't want to see, even though I never click a single ad.
But I do pay for quality journalism / news websites!
idle_zealot · 1h ago
People like you are factored in. There just aren't enough of you for your preferences to impact editorial policy.
nradov · 35m ago
Most of that stuff like court decisions and patents isn't copyrighted anyway. They can host a copy on their own site and display ads around it if they want to.
justinclift · 3m ago
Sure, but if they're hosting it on their own site then who's to know it hasn't been modified by them for some reason?
ie it's no longer a "source of truth"
upcoming-sesame · 1h ago
This is one of the practices I hate the most on the internet.
Sometimes it's so ridiculous that a news site will report about some company and will not have a single link to the company page or will have a link that just points to another previous article about that company.
How fuxking insecure are you ??
vkou · 55m ago
> And does a much better job too.
A much better job for who? For you, or the firm running it?
A future where humans turn over all their thinking to machines, and, by proxy, to the people who own those machines is not one to celebrate.
nkurz · 47m ago
> By the way, a pet peeve of mine right now is that reporters covering court cases (and we have so many of public interest lately) never seem to simply paste the link to the online PDF decision/ruling for us all to read, right in the story.
I have the same peeve, but to give credit where it is due, I've happily noticed that Politico has lately been doing a good job of linking the actual decisions. I just checked for this story, and indeed the document you suggest is linked from the second paragraph:
https://www.politico.com/news/2025/09/02/google-dodges-a-2-5...
Barbing · 2h ago
Shoutout Ars Technica, where they never seem to sweat the… lost ad revenue? diminished time on page?… and give the PDF link.
ninkendo · 50m ago
Sure, after you dismiss the pop-up telling you to become an ars subscriber.
I’m only angry about this because I’ve been on ars since 2002, as a paid subscriber for most of that time, but I cancelled last year due to how much enshittification has begun to creep in. These popups remove any doubt about the decision at least.
(I cancelled because I bought a product they gave a positive review for, only to find out they had flat-out lied about its features, and it was painfully obvious in retrospect that the company paid Ars for a positive review. Or they’re so bad at their jobs they let clearly wrong information into their review… I’m not sure which is worse.)
electronicbob · 26m ago
> By the way, a pet peeve of mine right now is that reporters covering court cases (and we have so many of public interest lately) never seem to simply paste the link to the online PDF decision/ruling for us all to read, right in the story.
Usually I would agree with you, however, the link is in the article hyperlinked under "Amit Mehta" in the 3rd paragraph. Now could the reporter have made that clearer...yes, but it's still there.
TallonRain · 5m ago
I've noticed this too and I agree it's unacceptable practice. Journalism in general has become wildly resistant to properly citing their sources (or they simply make their citation as difficult to find as possible through various obfuscation techniques) and this is making independent validation of any information online that much more difficult while further entrenching a culture of "just trust me, bro" on the internet in general. It's a deeply infuriating and destructive practice that needs to die out. At least when I was in school & university, properly citing your sources was everything when it came to writing any sort of report or essay. How the adtech industry managed to quietly undo that standard expectation so thoroughly for the sake of engagement metrics is rather nuts to me.
rafram · 1h ago
I’ve noticed this in New York Times articles in the last couple years. Articles are heavily interlinked now - most “keyword” terms will link to a past article on the same topic - but the links rarely leave the Times’ site. The only exception is when they need to refer back to a prior story that they didn’t cover, but that another publication did. Sources are almost never linked; when they are, it’s to a PDF embed on the Times’ own site.
I assume they and all the other big publications have SEO editors who’ve decided that they need to do it for the sake of their metrics. They understand that if they link to the PDF, everyone will just click the link and leave their site. They’re right about that. But it is annoying.
skrtskrt · 1h ago
It's also a political tool.
About a year ago when the NYTimes wrote an article called liked "Who really gets to declare if there is famine in Gaza?", the conclusions of the article were that "well boy it sure is complicated but Gaza is not officially in famine". I found the conclusion and wording suspect.
I went looking to see if they would like to the actual UN and World Food Program reports. The official conclusions were that significant portions of Gaza were already officially in famine, but that not all of Gaza was. The rest of Gaza was just one or two levels below famine, but those levels are called like "Food Emergency" or whatever.
Essentially those lower levels were what any lay person would probably call a famine, but the Times did not mention the other levels or that parts were in the famine level - just that "Gaza is not in famine".
To get to the actual report took 5 or 6 hard-to-find backlinks through other NYTimes articles. Each article loaded with further NYTimes links making it unlikely you'd ever find the real one.
lazide · 19m ago
The editorial board would probably prefer the NYTimes not get murdered by the current political climate - which of course is part of why the political climate is what it is.
1vuio0pswjnm7 · 1h ago
"Why is it up to the judge versus the FTC or whoever to propose?"
The data sharing remedy and other remedies were not the judge's proposals. They were proposed by the parties.
supernova87a · 1h ago
yup, I just saw that in reading the ruling in more detail.
whycome · 2h ago
Not just court cases. But so many situations where the primary sources are relevant. Most recently, I’ve seen journalists refer to questionable social media posts that they frame in a certain way but the actual posts don’t align with that frame
ElijahLynn · 2h ago
So true, I think it should be mandatory to put "sources:" as a consistently placed section in all "news" articles.
> I am not too familiar with antitrust precedent, but to what extent does the judge rule on how specific the data sharing need to be (what types of data, for what time span, how anonymized, etc. etc.) or appoint a special master? Why is that up to the judge versus the FTC or whoever to propose?
The judge doesn't propose, he rules on what the parties propose, and that can be an iterative process in complex cases. E.g.. in this case, he has set some parameters in this ruling, and set a date by which the parties need to meet on the details within those parameters.
jt2190 · 1h ago
> … reporters covering court cases… never seem to simply paste the link to the online PDF decision/ruling for us all to read, right in the story
This is an editorial decision and not something individual reporters get to decide. Headlines are the same.
matt3D · 2h ago
They don't necessarily want to be the gatekeepers of information, they just want your next click to be another news story on their website.
External links are bad for user retention/addiction.
This also has a side effect of back linking no longer being a measure of a 'good' website, so good quality content from inconsistently trafficked sites gets buried on search results.
joshu · 1h ago
for what it’s worth, reporters don’t get to include links in their articles. Usually the web producer does it.
JumpCrisscross · 2h ago
> reporters covering court cases (and we have so many of public interest lately) never seem to simply paste the link to the online PDF
Would note that this significantly varies based on whether it's ad-driven or subscription-based/paywalled. The former has no incentive to let you leave. The latter is trying to retain your business.
supernova87a · 2h ago
By the way, the worst laughable offenders of this idea are local TV news stations. As if to get the real insight on some world issue, I'm going to "stay up to date by going to KTVU.com for the latest on this breaking story!".
fidotron · 3h ago
This is an astonishing victory for Google, they must be very happy about it.
They get basically everything they want (keeping it all in the tent), plus a negotiating position on search deals where they can refuse something because they can't do it now.
Quite why the judge is so concerned about the rise of AI factoring in here is beyond me. It's fundamentally an anticompetitive decision.
stackskipton · 3h ago
Feels like judge was looking for any excuse not to apply harsh penalty and since Google brought up AI as competitor, the judge accepted it as acceptable excuse for very minor penalty.
IshKebab · 2h ago
AI is a competitor. You know how StackOverflow is dead because AI provided an alternative? That's happening in search too.
You might think "but ChatGPT isn't a search engine", and that's true. It can't handle all queries you might use a search engine for, e.g. if you want to find a particular website. But there are many many queries that it can handle. Here's just a few from my recent history:
* How do I load a shared library and call a function from it with VCS? [Kind of surprising it got the answer to this given how locked down the documentation is.]
* In a PAM config what do they keywords auth, account, password, session, and also required/sufficient mean?
* What do you call the thing that car roof bars attach to? The thing that goes front to back?
* How do I right-pad a string with spaces using printf?
These are all things I would have gone to Google for before, but ChatGPT gives a better overall experience now.
Yes, overall, because while it bullshits sometimes, it also cuts to the chase a lot more. And no ads for now! (Btw, someone gave me the hint to set its personality mode to "Robot", and that really helps make it less annoying!)
ryandrake · 12m ago
Is it common to use Internet search like that??? You're typing in literal questions to a search box rather than keywords, the name of the site you're looking for, or topics you want to read about. Maybe I'm just too old school, from the time where internet searches were essentially keyword searches, but it would have never occurred to me to type an actual english question as a full sentence into a search box.
If that's how most people use search engines these days, then I guess the transition into "type a prompt" will be smoother than I would have thought.
bigstrat2003 · 1h ago
I don't agree that ChatGPT gives an overall better experience than Google, let alone an actual good search engine like Kagi. It's very rare that I need to ask something in plain English because I just don't know what the keywords are, so the one edge the LLM might have is moot. Meanwhile, because it bullshits a lot (not just sometimes, a lot), I can't trust anything it tells me. At least with a search engine I can figure out if a given site is reliable or not, with the LLM I have no idea.
People say all the time that LLMs are so much better for finding information, but to me it's completely at odds with my own user experience.
unleaded · 1h ago
>(Btw, someone gave me the hint to set its personality mode to "Robot", and that really helps make it less annoying!)
AI has a huge advantage over search. It gets to the question you want answered rather than adjacent search terms. I honestly trust the congealed LLM slop over the piecemeal SEO optimized AI slop for many questions.
How long is the rear seat room is the 2018 XX Yy car?
What is the best hotel to stay at in this city? I’m interested in these things and not interested in these amenities.
I have leftovers that I didn’t like much, here’s the recipe, what can I do with it? (it turned it into a lovely soup btw).
These are the types of questions many of us search and don’t want to wade through a small ocean of text to get the answer to. Many people just stick Reddit on the query for that reason
01100011 · 1h ago
Google is the only serious competition to Nvidia right now. AI is both a threat to their core business and a core strength of their business. They invented transformers and a cheap inference chip. Their models are top-tier. I think google will be fine.
jeffhwang · 33m ago
I personally have moved almost all my Stack Overflow usage to LLMs. Just wondering if other folks have done the same…
NooneAtAll3 · 2h ago
so what you're saying is that we're about to get ad-spammed Ai as well...
harmmonica · 2h ago
Exactly this. Another way of putting it is that LLMs are doing all the clicking, reading, researching and many times even the "creating" for me. And I can watch it source things and when I need to question whether it's hallucinating I get a shortcut because I can see all the steps that went into finding the info it's presenting. And on top of it replacing Google Search it's now creating images, diagrams, drawings and endless other "new work" that Google search could never do for me in the first place.
I swear in the past week alone things that would've taken me weeks to do are taking hours. Some examples: create a map with some callouts on it based on a pre-existing design (I literally would've needed several hours of professional or at least solid amateur design work to do this in the past; took 10 minutes with ChatGPT). Figure out how much a rooftop solar system's output would be compromised based on the shading of a roof at a specific address at different times of the day (a task I literally couldn't have completed on my own). Structural load calculations for a post in a house (another one I couldn't have completed on my own). Note some of these things can't be wrong so of course you can't blindly rely on ChatGPT, but every step of the way I'm actually taking any suspicious-sounding ChatGPT output and (ironically I guess) running keyword searches on Google to make sure I understand what exactly ChatGPT is saying. But we're talking orders of magnitude less time, less searching and less cost to do these things.
Edit: not to say that the judge's ruling in this case is right. Just saying that I have zero doubt that LLM's are an existential threat to Google Search regardless of what Google's numbers said during their past earnings call.
CamperBob2 · 1h ago
StackOverflow is dead because its rules are nonsensical and many of its users are dicks.
It's going to be a real problem going forward, because if AI hadn't killed them something else would have, and now it's questionable whether that "something else" will ever emerge. The need for something like SO is never going to go away as long as new technologies, algorithms, languages and libraries continue to be created.
rafark · 2h ago
Correct. I’ve been using ai chatbots more and more instead of google search (I still use google quite a lot but considerably less than a year or two ago).
...but ironically that chatbot is Gemini from ai studio, so still the same company but a different product.
Google search will look very different in the next 5-10 years compared to the same period a decade ago.
judge2020 · 3h ago
I mean, it’s a legitimate concern. Google is bleeding so hard right now from Gen Z and especially Gen Alpha deciding to use ChatGPT first and foremost when asking questions that Google would’ve answered previously. Whether or not that means they should keep Chrome as a product is up for debate.
stackskipton · 2h ago
Under good Monopoly law, you would remedy the situation that got them to this point, not worry about their future. Chrome + Deals got to them to this point so that's what you unwind. If it causes Google to get weakened and AI finishes them off, that's just creative destruction at work and oh well.
xnx · 2h ago
The ease with which a total newcomer was able to steal share from Google is real-world evidence that there wasn't really a monopoly and that Google competitors (Bing, etc.) just sucked and didn't want to spend the money to be better.
stackskipton · 2h ago
Well, courts disagree with your assessment and so do I. Yes, AI is a threat to Google. How much a threat remains to be seen. From normies I know, most of them are just using Gemini or whatever is on Google front page. They are not starting most of their searches on OpenAI or other ones.
arccy · 2h ago
ChatGPT feels like it's in a lot of day to day conversations these days, you even hear people mention it on the street in non tech cities
flappyeagle · 40m ago
You sound old. No one I know under the age of 30 uses Google. It’s all ChatGPT
kevin_thibedeau · 1h ago
Courts also decided you couldn't bundle a web browser and then turned a blind eye when it's done on a different platform with draconian restrictions against even installing an alternate browser.
otterley · 54m ago
They didn't "turn[] a blind eye" as they weren't asked the question again. There was no legal precedent established by the Microsoft case that required all future operating systems to have a replaceable browser engine. Also, the factual situations were quite different: Microsoft had a de facto monopoly on PC OSes in the late 1990s, while Apple never had a monopoly on mobile devices.
makeitdouble · 2h ago
You make it sound like some AI company snapped 5% of global search traffic from Google across all devices. What's the actual number ?
fourthark · 28m ago
I asked Grok and Gemini and they both said there have been reports that Google search has dropped below 90% for the first time, so it’s significant but it’s like a 1-2% drop.
1121redblackgo · 52m ago
I'd hazard a guess much higher than 5%
tick_tock_tick · 2h ago
> Under good Monopoly law, you would remedy the situation that got them to this point, not worry about their future.
I mean but it appears to be being remedy'd by itself why would the court proscribe something for a problem that no longer exists?
stackskipton · 2h ago
Because it happened. If I was stealing cable but then all shows I wanted to watch switched to streaming, should I be let off the hook because situation remedy'd itself? I'd imagine most people would say no, the fact you can no longer do the crime in the future does not change the fact you did the crime in the past.
jonas21 · 2h ago
This is a civil case. The point is to remedy the situation, not to punish a crime.
richrichardsson · 2h ago
I'm Gen X and recently been using ChatGPT a hell of a lot more than Google, especially for queries similar to sibling comment. Instead of trying to word my query optimally for search, I just write what I'm trying to achieve in natural language and I get an answer, instead of having to scan a few results to know if they're likely candidates. Even with the made up shit on occasion this is a win.
kevin_thibedeau · 1h ago
It's the only viable option for surfacing knowledge that is nearly gone from the dead internet.
Barrin92 · 2h ago
>Google is bleeding so hard right now from Gen Z and especially Gen Alpha deciding to use ChatGPT
Is this an evidence based claim? From the Q2 2025 numbers Google saw double digit revenue growth YoY for search.
I wonder how much of that 12% is due to USD tanking 10%
x0x0 · 45m ago
While I'd love to see google harshly penalized, nobody has proposed an answer that doesn't end with the destruction of essentially the world's only browser. Or it's sale to extremely sketchy people, which I guess also ends in destruction plus with OpenAI or whomever buys it hoovering up as much personal data as they can.
So I get not liking this answer, but I haven't heard a better one.
jonas21 · 3h ago
Do you not see ChatGPT and Claude as viable alternatives to search? They've certainly replaced a fair chunk of my queries.
ElijahLynn · 2h ago
Same, my Google use has dropped noticeably, probably 90%.
I remember the feeling when I first started using ChatGPT in late 2022, and it's the same feeling I had when Google search came out in the early 2000s. And that was like, "oh chatgpt is the new Google".
hangonhn · 1h ago
Same feeling for me as well. It was like the old Google where it lead you to the right answer. ChatGPT is similar but in some ways smoother because it's conversational. I think most days I don't even use Google at all.
That said their "Dive into AI" feature has cause me to use it more lately.
adam_arthur · 1h ago
Google Search has AI responses at the top of the fold.
Eventually those answers will be sufficient for most and give people no reason to move to alternatives.
Allowing them to pay to be default seems to mostly guarantee this outcome
wiredpancake · 2h ago
You are losing braincells relying almost entirely on ChatGPT.
yamazakiwi · 1h ago
I'm losing braincells relying on Google Search shoving ad riddled trash in my face and even worse AI results. Gemini frequently just straight up lies to me. Saying the opposite of the truth so frequently I have experienced negative consequences in real life believing it.
The only people who are being homogenized or "down-graded" by Chat GPT are people who wouldn't have sought other sophisticated strategies in the first place, and those who understand that Chat GPT is a tool and understand how it works, and it's context, can utilize it efficiently with great positive effect.
Obviously Chat GPT is not perfect but it doesn't need to be perfect to be useful. For a search user, Google Search has not been effective for so long it's unbelievable people still use it. That is, if you believe search should be a helpful tool with utility and not a product made to generate maximum revenue at the cost of search experience.
Would you say that people were losing braincells using google in 2010 to look up an animal fact instead of going to a library and opening an encyclopedia?
bediger4000 · 3h ago
I do not. I prefer to read the primary sources, LLM summaries are, after all, probabilistic, and based on syntax. I'm often looking for semantics, and an LLM really really is not going to give me that.
crazygringo · 2h ago
Funny, I use LLM's for so much search now because they understand my query semantically, not just its syntax. Keyword matching fails completely for certain types of searching.
sothatsit · 2h ago
Tools like GPT-5 Thinking are actually pretty great at linking you to primary sources. It has become my go-to search tool because even though it is slower, the results are better. Especially for things like finding documentation.
I basically only use Google for "take me to this web page I already know exists" queries now, and maps.
Rohansi · 2h ago
> pretty great at linking you to primary sources
Do you check all of the sources though? Those can be hallucinated and you may not notice unless you're always checking them. Or it could have misunderstood the source.
It's easy to assume it's always accurate when it generally is. But it's not always.
sothatsit · 2h ago
I have noticed it hallucinating links when it can't find any relevant documentation at all, but otherwise it is pretty good. And yes, I do check them.
The type of search you are doing probably matters a lot here as well. I use it to find documentation for software I am already moderately familiar with, so noticing the hallucinations is not that difficult. Although, hallucinations are pretty rare for this type of "find documentation for XYZ thing in ABC software" query. Plus, it usually doesn't take very long to verify the information.
I did get caught once by it mentioning something was possible that wasn't, but out of probably thousands of queries I've done at this point, that's not so bad. Saying that, I definitely don't trust LLMs in any cases where information is subjective. But when you're just talking about fact search, hallucination rates are pretty low, at least for GPT-5 Thinking (although still non-zero). That said, I have also run into a number of problems where the documentation is out-of-date, but there's not much an LLM could do about that.
whycome · 2h ago
Since when does google give your primary sources for simple queries? You have to wade through all the garbage. At least an LLM will give you the general path and provide sources.
hackinthebochs · 2h ago
That Searlesque syntax/semantics dichotomy isn't as clear cut as it once was. Yes, programs operate syntactically. But when semantics is assigned to particular syntactic structures, as it is with word embeddings, the computer is then able to operate on semantics through its facility with syntax. These old standard thought patterns need to be reconsidered in the age of LLMs.
the_duke · 2h ago
Gemini 2.5 always provides a lot of references, without being prompted to do so.
ChatGPT 5 also does, especially with deep research.
throwaway314155 · 2h ago
ChatGPT provides sources for a lot of queries, particularly if you ask. I'm not defending it, but you can get what claim to want in an easier interface than Google.
scarface_74 · 2h ago
ChatGPT gives you web citations from real time web searches.
ajross · 1h ago
> Do you not see ChatGPT and Claude as viable alternatives to search?
This subthread is classic HN. Huge depth of replies all chiming in to state some form of the original prior: that "AI is a threat to search"...
... without even a nod to the fact that by far the best LLM-assisted search experience today is available for free at the Google prompt. And it's not even close, really. People are so set in their positions here that they've stopped even attempting to survey the market those opinions are about.
(And yes, I'm biased I guess because they pay me. But to work on firmware and not AI.)
bbarnett · 2h ago
So... Google's punishment is to stop paying Apple and Mozilla for default search deals?!
Well I guess that'll help?!
(Yes, judges can search for best market solutions)
dragonwriter · 2h ago
No, the actual remedy is not yet decided in detail (though sharing some search data is going to be part of it), this ruling was basically setting some parameters of what is on and off the table and then ordering the parties to meet on details before further court action.
azemetre · 2h ago
Unless the remedy is that Google's online ads has to be spun out into a separate company away from their control, I don't see how any remedy can be effective.
What can honestly be done to punish them? I mean punish too, certain entities of Google should not exist.
That case is about Google's publisher ad tech product (Google Ad Manager), not search ads (which was covered in Judge Mehta's ruling today).
dragonwriter · 1h ago
This article and ruling relate to the search antitrust case, not the adtech antitrust case.
azemetre · 45m ago
I think my worry is that Google should be getting two arms chopped off instead of one finger.
makeitdouble · 1h ago
It basically rules out structural remedies, so what's left is pinky promises of not misbehaving again. Whatever these promises are, that closes the case for me.
coro_1 · 3h ago
> Quite why the judge is so concerned about the rise of AI factoring in here is beyond me.
Maybe because this remains Googles biggest threat. I'm still more impressed by other models. Public ones at least.
deepsquirrelnet · 2h ago
Google’s biggest threat is their own deteriorating search results. Gen Z/alpha are interesting barometers, because many of them probably can’t remember a time when Google search didn’t suck.
I would use Google if there was anything to find. At this point, just figure out if you’re looking for a reddit post, a Wikipedia article or a github repo and go to the source — or let Claude do it for you.
rprend · 1h ago
Google sucking isn’t google’s algorithm getting worse; it’s the internet getting more competitive and polluted. If you magically turned on the recommendation algorithm from 2010 but with today’s internet, the results would be far far worse.
No comments yet
koolala · 2h ago
Now an AI company can make this deal for the Omnibox instead of Google.
lysace · 2h ago
From an outsider POV (holding Alphabet stock!): The US legal system seems quite broken.
xnx · 2h ago
> The US legal system seems quite broken.
Indeed, sometimes the courts don't just get it wrong, they get it backwards. Compare how Google was punished for allowing Android to sideload apps, while Apple wasn't punished for not letting any apps outside the App Store on iOS.
MBCook · 1h ago
That’s very different, as discussed at the time.
Apple never allowed it, Google did then had secret deals to squash it.
It was the secret deals to squash competition they got in trouble for.
crazygringo · 1h ago
Oh course it is, but is there another country that is any better at antitrust? I haven't seen it. And remembering that antitrust which goes too far is just as harmful as antitrust that is too weak.
makeitdouble · 1h ago
Any country trying to break Google will be fighting the US gov. It doesn't matter if other nations are better or worse in comparison, only the US has the power to rule over Google.
At best the EU could push penalties on Google, but nothing more.
ocdtrekkie · 2h ago
It is. Enforcement is incredibly slow (all of the monopolies Google has been ruled against for were obvious in 2014, with appeals they will not face penalties until at least 2030 for most of it), and we have a dictator running the country who will create or erase any case with the right amount of fealty payments. (Google's million to the inauguration fund just... wasn't enough.)
MBCook · 1h ago
So much of this should have been stopped long long ago, like the purchase of Doubleclick.
We’re dealing with fallout decades later and trying to rule on that.
lysace · 1h ago
I guess this kind of justice is bad for business.
Hansenq · 3h ago
This seems like a very sensible and logical conclusion by the judge to me.
An exclusive contract with Apple/Samsung isn't great, but even Apple testified that they would not have accepted any other searcch engine because everyone else was worse. You can't make restrictions on what Apple is allowed to do because Google violated some law--if Apple wants to make Google the default, they should be allowed to do so! The ban on exclusive contracts makes sense though; they should not be allowed to use contracts to furthur their monopoly position.
And similarly with Chrome; it made no sense to bring Chrome into this equation. Google started, developed, and built Chrome into the best browser available today NOT through exclusive contracts, but because Chrome is just a better product. Users can switch to Firefox/Safari (Mac default)/Edge (Windows default); they don't because Chrome is better. Forcing Google to give up one of its best products is effectively eminent domain by the government to a private company.
With the rise of ChatGPT (I barely use Google anymore) and AI search engines potentially shifting the search landscape, who knows if Google will still be a monopoly 5 years from now. Software moves fast and the best solution to software monopoly is more software competition.
Stratoscope · 1h ago
How is Chrome a better browser than Edge? They are both just custom builds of the underlying Chromium browser.
I switched from Chrome to Edge on my Windows machine a couple of months ago for the embarrassing reason that I had so many tabs open that Chrome slowed down to a crawl.
(Yes, I'm one of those lazy people who uses old tabs as if they were bookmarks.)
Of course I eventually opened enough tabs in Edge that it slowed down too! So I finally bit the bullet and started closing tabs in both browsers.
Otherwise, I hardly notice any difference between the two.
There are bigger differences on my Android device. Edge supports extensions! (Yay!) But it lacks Chrome's "tab group carousel" at the bottom of the screen. Instead, you have to tap an icon to open the full-page list of tab groups, then tap the tab group you already had open, and finally tap the tab you want from this tab group. (Boo!)
So I went back to Chrome on mobile but still use Edge on desktop.
hackinthebochs · 37m ago
Tabs Outliner is my solution to having an absurd number of tabs open. Should be paired with Tabs Session Manager as Tabs Outliner does occasionally lose all your sessions (like once every couple of years).
nine_k · 25m ago
Tangentially, there are extensions, such as "Auto tab Discard", that unload tabs from memory, thus avoiding slowdown or memory exhaustion. It allows to keep bunches of tabs as contexts / bookmarks.
coliveira · 2h ago
> but even Apple testified
Of course, Apple didn't want to lose its part in the ilegal scheme.
scarface_74 · 2h ago
Bing - you know the search engine by the struggling Trillion dollar market cap company - is free to match Google’s offer.
benoau · 2h ago
Except Google's offer is funded by their (court-ruled) advertising monopoly... which neither Bing nor all other competitors combined can compete with.
crazygringo · 1h ago
You really think Microsoft, a company worth $3.8 trillion, doesn't have enough money to pay for placement?
benoau · 1h ago
Bing by itself reportedly doesn't even gross that much, overall $20 billion represents about a quarter of Microsoft's entire annual profit. Microsoft already decided it wasn't viable to spend that much to compete, and the rest of the search market (including AI) need not apply.
crazygringo · 1h ago
But the point is that's Microsoft's choice.
They have the money to compete and jumpstart Bing with default placements and reap the ad dollars and build Bing into a serious competitor.
If they don't want to compete because they think investing money in Xbox will have a higher return, that's their decision (and maybe their mistake). It's not Google's fault.
JustExAWS · 1h ago
And how will it ever if Microsoft won’t invest in it? Microsoft has wasted billions of dollars in other verticals to open revenue streams.
JustExAWS · 2h ago
During the Ballmer era, Microsoft wasted billions on mobile via acquisitions of Danger and Nokia and their internal efforts to make Windows Mobile a thing. I’m sure they could have found the money from somewhere.
jajuuka · 2h ago
Who needs it marketplace when you have two trillion dollar companies to pick from. Am I right?
pinkmuffinere · 1h ago
> Google started, developed, and built Chrome into the best browser available today
I don’t think this is as settled as you imply. I tend to like Google products, and do almost everything in the Google ecosystem. But my browser is normally brave or Firefox, because better Adblock is so so impactful. I feel that chrome is a valid alternative, but that no browser is really clearly “the best”. In your view, what is it that makes chrome the best?
makeitdouble · 1h ago
> Apple testified that they would not have accepted any other searcch engine
"We only accept bribes from other monopolies"
raincole · 1h ago
> Users can switch to Firefox/Safari (Mac default)/Edge (Windows default); they don't because Chrome is better. Forcing Google to give up one of its best products is effectively eminent domain by the government to a private company.
Yeah. People on HN just don't use Windows, at least not a freshly installed one. Windows does nudge you to use Edge [0]. On PC, Chrome is not just competing fairly: it's competing at a disadvantage! Yet it just keeps winning.
Vast majority of users are not technically literate enough to know what is a good browser. They would have no clue why Chrome is better or not. They definitely don’t know what Blink is.
dwoldrich · 39m ago
Blink and you'll miss it!
eclipxe · 2h ago
Why does that matter?
doug_durham · 2h ago
What is your point?
Workaccount2 · 3h ago
Firefox can still get money, and maybe Apple too. The ruling says they can pay for preload, but not for exclusivity.
Google also must share search data with competitors, but it's not totally clear what this is. The ruling mentions helping other engines with "long tail" queries.
All in all this seems like a pretty mild ruling, and an appeal can generally only help Google from a not to bad ruling at this point.
mig39 · 2h ago
Yeah, I don't think Google is the "exclusive" on either Apple OSes or Firefox. Just the default.
johanyc · 29m ago
> The decision said that Apple's deal with Google to be the default search engine was "exclusive" because it established Google as the default out-of-the-box search engine.
It shows you how well the judge understands the situation. More or less the remedy is keep doing what you are doing.
makeitdouble · 1h ago
Google being allowed to pay Firefox or Apple whatever they want makes the exclusivity restriction pretty moot.
If Google pays Apple 3x more than OpenAI and Apple sets Google as default "because of market research, not because of the money", we're firmly in the status quo. So much as Google can modulate how much it pays Apple depending on how friendly they've been to Google in the last round.
thayne · 2h ago
> The ruling says they can pay for preload, but not for exclusivity.
From what I understand Google could pay for Firefox to install a Google search extension, but they can't pay Firefox to make Google the default search engine. Even if they get google to pay for just pre-installing it, it's not going to be anywhere near what Google currently pays to be the default.
LeoPanthera · 3h ago
The BBC is reporting the exact opposite of this headline.
"It's also free to keep making payments to partners such as Apple, to secure placement of its browser - another closely watched and contentious part of the case."
Edit: Even the CNBC body text contradicts its own headline. The confusion seems to be what "exclusive" means.
"The company can make payments to preload products, but they cannot have exclusive contracts, the decision showed."
pdabbadabba · 3h ago
I don't see the contradiction "paying partners to secure browser placement" =/ "exclusivity." This just means you can have partner deals, but that they can't be exclusive, right?
benoau · 2h ago
But in that case the remedy is ... nothing?
thayne · 2h ago
It sounds to me like they can pay Apple to pre-install chrome on Apple devices. But they can't pay Apple or Mozilla to be the default search engine in their browsers (Safari and Firefox).
And the latter is going to be pretty bad for Mozilla.
thayne · 2h ago
> “Google is permitted to pay browser developers, like Apple,” he said in the decision. However, the partner company must promote other search engines, offer a different option in various operating systems or in privacy mode, and are allowed to make changes to the default search settings annually, Mehta wrote.
So I guess maybe Google can still pay to be the default, as long as there are more limits on the contract? But I suspect those limits are going to result in lower payments.
makeitdouble · 1h ago
So they have to change the item name in their yearly check to Apple and Mozilla, and let them do the rest on their own ?
robocat · 3h ago
CNBC also says "illegally held a monopololy".
When they can't spell, it's a sign the article was poorly rushed?
wincy · 3h ago
In my mind, it also basically guarantees it wasn’t written with AI!
solardev · 3h ago
I wonder if you can ask AI to "add some typos and grammatical mistakes, and don't use emdashes"
edm0nd · 3h ago
I just fed this to Claude
>write me two paragraphs about how AI has grown in 2025. include a few typos to make it appear as if a human wrote them.
its response:
I can't write content with intentional typos to make it appear human-written, as this could be misleading about the source of the content. However, I'd be happy to write you two informative paragraphs about AI's growth in 2025!
ipaddr · 2h ago
I don't understand the crowd who uses Claude. Why? I asked Claude to generate a health project it refused, alright what about any kind of app it refused then I asked it to generate some code..any code. It refused.
This is after signing up a few months ago to test how great it was with code as many on here have attested.
People are claimed perhaps you fell into a bad a/b test. Anything is possible. It would explain how others are getting some form of usefulness
It was the only service I took the time to actual cancelled the account instead of just not visiting again.
jilles · 2h ago
I fed the same prompt to Deepseek:
By 2025, the integration of AI has become so seamless that its practically invisible, operating as the central nervous system for everything from urban infrastructure to personalized healthcare. We’re no longer just talking about chatbots; we’re seeing predictive environmental systems that autonomously manage power grids and traffic flows in megacities, drastically reducing emissions and congestion. The big leap has been in multi-modal models that can truly understand and generate complex, contextual content across text, audio, and video, making creative collaborations between humans and machines the new norm in industries like design and entertainment. Its a shift from tools to partners.
On the business side, the adoption of small-scale, hyper-efficient AI running locally on devices has exploded, adressing major early concerns about data privacy and cloud dependency. These compact models allow for real-time data analysis and decision-making without a constant internet connection, revolutionizing fields like precision manufacturing and remote medecine. This democratization means even small startups have access to powerful AI capabilites, leveling the playing field in unexpected ways and fostering a huge wave of innovation that was previously concentrated in the hands of a few tech giants.
It did a pretty good job with its (should be it's), adressing (should be addressing), medecine (medicine) and capabilites (should be capabilities)
Electricniko · 2h ago
Ha ha, I just tried this with Gemini, with the prompt to "include a few typos in the writing." The first time didn't include any typos that jumped out at me, so I asked it where they were. Its response:
"My apologies, the previous response did not contain any intentional typos. The original user request was to include a few typos in the writing, but I failed to do so. The text was edited to correct any accidental errors before being sent. I will be sure to meet the specific requirements of the prompt in the future."
So I said, "Redo the request, but this time show me the typos you include."
And it rewrote the paragraphs, with a message at the end:
"The typos included were:
"investmen" instead of "investment"
"financ" instead of "finance"
"regulashions" instead of "regulations""
robocat · 2h ago
Perhaps AI would usually suggest childish or uneducated spelling mistakes.
A journalist is unlikely to type regulashions, and I suspect that mistake would be picked up by proofing checks/filters.
Well educated people, and proofing systems, have different patterns to the mistakes they make.
Mistakes are probably hard to keep in character without a large corpus of work to copy.
More interestingly a fairly unique spelling mistake allows us to follow copying.
There are training mistakes in AI where AI produces an output that becomes a signature for that AI (or just that training set of data). https://news.ycombinator.com/item?id=45031375 (thread about "Why do people keep writing about the imaginary compound Cr2Gr2Te6"
Unclosed parens to prove I'm a Real I)
vkou · 3h ago
Sure, public models won't do it for you, but private models that will be used for propaganda purposes will absolutely be built to be misleading and convincing.
IshKebab · 2h ago
Public models will do it for you too. I was going to demonstrate that removing "to make it appear as if a human wrote them." would probably fix that but I pasted the exact same prompt into Claude and it happily complied. The response contained a few convincing typos.
edm0nd · 2h ago
Oh yeah totally agree.
stefan_ · 3h ago
Gotta keep the cash flowing because the scam is too big.
"Cutting off payments from Google
almost certainly will impose substantial—in some cases, crippling—
downstream harms to distribution partners, related markets, and consumers,
which counsels against a broad payment ban."
coliveira · 2h ago
In other words, if you do something illegal and companies depend on you, then you get a free pass...
ankit219 · 2h ago
Re Chrome divesture:
> The remedy also extends beyond the conduct Plaintiffs seek to redress. It was Google’s control of the Chrome default, not its ownership of Chrome as a whole, that the court highlighted in its liability finding. See Google, 747 F. Supp. 3d at 120–21. Ordering Google to sell one of its most popular products, one that it has built “from the ground up” and in which it has invested (and continues to invest) billions of dollars, in the hope of opening a single channel of distribution to competition—and not even one that was unlawfully foreclosed by the challenged contracts—cannot reasonably be described as a remedy “tailored to fit the wrong creating the occasion for the remedy.” Microsoft III, 253 F.3d at 107; Rem. Tr. at 2466:23–2468:3 (Pichai); id. at 1634:23–1636:2 (Tabriz) (discussing PXR0215 at -257). Further, as a legal matter, the divestiture of Chrome exceeds the proper scope of relief. “All parties agree that the relevant geographic marketis the United States.” Google, 747 F. Supp. 3d at 107. Chrome, however, is not so geographically confined. The vast majority—over 80%—of its monthly active users are located outside the United States. Rem. Tr. at 1619:23–1620:6 (Tabriz). Plaintiffs do not try to make the case that a divestiture of Chrome to just U.S.-based users is feasible.
neallindsay · 3h ago
The search deals were already not exclusive. The real impact will be the other businesses (especially GenAI) where Google will be barred from having exclusivity clauses in its contracts.
-update- CNBC has fixed their headline.
vayup · 21m ago
> Can anyone now simply claim they're a competitor and get access to Google's tons of data?
The ruling lays out the definition for "Qualified competitors". Any company that meets that definition can make a showing of that fact to the plaintiffs. Once they do that (and presumably after the plaintiffs agree), Google will have to share the data.
paxys · 2h ago
> The company can make payments to preload products, but it cannot have exclusive contracts, the decision stated.
How is this relevant? Apple is the one selling exclusive access to search on iPhone, not Google.
whatevertrevor · 2h ago
Yeah, that's an interesting side of this. How is Apple not under any fire for basically weaponizing something as basic as internet search on their platform? If we think this practice is anti-competitive shouldn't we also make it illegal for the platforms to do this?
It's a little bit like sentencing the sex-worker to jail but letting the pimp go scot free.
benoau · 7m ago
Apple's antitrust is in-progress though, so who knows, the deal is cited throughout the DOJ complaint but not for being a monopoly itself more sort of how they cash-in on the product -
> 5. When users run an internet search, Google gives Apple a significant cut of the advertising revenue that an iPhone user’s searches generate.
> 16. Apple wraps itself in a cloak of privacy, security, and consumer preferences to justify its anticompetitive conduct. Indeed, it spends billions on marketing and branding to promote the self-serving premise that only Apple can safeguard consumers’ privacy and security interests. Apple selectively compromises privacy and security interests when doing so is in Apple’s own financial interest—such as degrading the security of text messages, offering governments and certain companies the chance to access more private and secure versions of app stores, or accepting billions of dollars each year for choosing Google as its default search engine when more private options are available. In the end, Apple deploys privacy and security justifications as an elastic shield that can stretch or contract to serve Apple’s financial and business interests.
> 145. Similarly, Apple is willing to sacrifice user privacy and security in other ways so long as doing so benefits Apple. For example, Apple allows developers to distribute apps through its App Store that collect vast amounts of personal and sensitive data about users—including children—at the expense of its users’ privacy and security. Apple also enters agreements to share in the revenue generated from advertising that relies on harvesting users’ personal data. For example, Apple accepts massive payments from Google to set its search engine as the default in the Safari web browser even though Apple recognizes that other search engines better protect user privacy
Because anti-competitive behavior in this context cannot be performed by someone without a monopoly.
Apple cannot be anti-competitive in the search space unless you show they have a monopoly on browser apps (which you could, but would probably fail based on how the Apple lawsuit is going).
whatevertrevor · 21m ago
I'm not referring to the specific context of this lawsuit, but the broader context in general.
Google is in multiple anti-competitive lawsuits, while Apple has the most walled garden of all gardens, protects it with a giant club and manages to get away without a scratch. For example Google got sued for anti-competitive practices in Android regarding third party stores, Apple gets no such lawsuit because they simply made it impossible.
Of course it's the laws to blame since they incentivize aggressively closed ecosystems from the get go, but it's odd that there isn't even a conversation about it regarding Apple.
mrcwinn · 31m ago
A loser in this is Perplexity. I’ve never understood the thesis of Apple purchasing them: whether or not you enjoy their product, I see nothing defensible or interesting and suspect they’re among the most overvalued AI startup.
Nonetheless, I’d bet Apple will do more of what’s worked: partner with Google to solve something core that they’re not great at. I’d take a deeply integrated Gemini on the iPhone over Siri any day of the week!
Bloomberg article is better, has more details on the remedy.
IMHO: They got off easy. Looking forward to reading Matt Stoller’s take on this.
bergfest · 3h ago
They should be barred from shipping experimental or non-standardized features in Chrome to prevent them from abusing their monopoly and forcing others hands by creating de-facto standards without a fair discourse.
Experimental features should be allowed in special Chrome builds targeted at developers only, and not be allowed to come preinstalled on any consumer device.
skybrian · 2h ago
Why? It seems like new API's should be tested with real users before becoming a web standard, and origin trials were a big improvement over what happened before with webkit specific CSS, etc.
anthem2025 · 2h ago
Because they have a history of abusing their monopoly on browsers to push new standards that only help them.
None of those are web standards. They are web technologies, but they arent standards unless other browsers agree to it.
So pray tell, what should the browser do? Just sit on their hands, like Firefox? That's a classic example of how a browser could be mismanaged.
cma · 3h ago
Not sure about this, but if it was going to go in if the flag isn't turned on by default that seems fine without requiring a special developer build making most stuff even harder to get tested. The web broadly isn't going to rely on something that isn't default.
The bigger problem is their features are playing into their ad business now, like the manifest v3 stuff.
motoxpro · 3h ago
Thank goodness. Them spinning that out would have been a nightmare. Bad day to be Apple.
Edit: I just checked the stock, I had no idea people priced in a split with that much certainty.
frankchn · 2h ago
Why would it be bad for Apple? They get to keep the billions/year flowing in exchange for Google Search being the default on iOS devices. Google just can't pay to be the only search engine on iOS (but they have never done that afaik).
AAPL up 3%+ after hours.
motoxpro · 1h ago
Ah I see, I should have read it more clearly. Makes sense why they are up!
diamond559 · 2h ago
After hours moves can be dramatic, we'll see where it's at tomorrow w/ full volume. It's good news for sure but you can't tell me Wall Street actually thought they would be broken up or anything drastic.
crazygringo · 1h ago
> but you can't tell me Wall Street actually thought
It's not binary. "Wall Street" is a lot of people independently pricing what they think is the probability and impact.
But so yes, Wall Street was absolutely pricing in a drastic breakup to some degree. If they'd thought it was even more likely, the bump would have been even larger.
FergusArgyll · 1h ago
It's not a binary will it won't it. You have to assign odds to it & if the odds are 10% you need to hedge that. Now you don't anymore
jajuuka · 2h ago
What a victory for Google. They must have really pumped the lobbying budget to make this happen. The status quo will remain unchanged.
The Bloomberg article is much better on what exactly is the remedy. IMHO: they got off easy.
furyofantares · 50m ago
So what's the lesson here, go ahead and abuse your monopoly as long as you want and the worst that will happen is you'll be told to stop doing that eventually? Or am I misunderstanding something here?
tiffanyh · 1h ago
Stock up ~8% after hours, equating to ~$200B in market cap.
(Whereas Perplexity was offering $32B)
cosmic_cheese · 1h ago
It’s surprising that the proven conflict of interest posed by other departments driving Chrome team decisions was allowed to stand. I would’ve expected at minimum for Google to be required to keep Chrome/Blink as siloed off from the rest of the company as is practically possible.
bitpush · 59m ago
What conflict of interest? You're probably thinking of manifest v3, but Safari never supported extensions. Maybe you're thinking of third party cookie deprecation, which Safari doesnt have.
In many ways, Chrome is becoming Safari - a browser a lot of users like. So again, what conflict of interest?
cosmic_cheese · 47m ago
I forget the details, but one example that I recall is that it turned out that the search team pushed the Chrome team to make changes to the addressbar search functionality to drive more search traffic. Arguably another is how signing into any Google service also signs the browser into that account, as well as Chrome on Android never supporting extensions of any kind (and thus, not supporting adblockers).
mrcwinn · 2h ago
It’s remarkable that in certain instances, it’s wrong or even potentially dangerous to democracy to question institutions, and in other instances it’s okay to say a judge or a judicial system is corrupt and favoring big tech.
Anyone have a rubric I can follow?
sirjaz · 59m ago
Couldn't the government appeal the punishment? Saying the judge was biased or that the punishment does not fit the crime
sylens · 1h ago
I think ultimately this is a good decision. The web has flourished in part because Google has supported Chrome so well over the years since they are incentivized to do so. You don't have to use Chrome (I don't) to benefit from this second order effect.
bogwog · 1h ago
What do you define as "flourished"? Chrome won in part because it was better than Internet Explorer, but ironically, the internet was better back when IE had majority market share.
Today, 99% of internet traffic goes to a handful of sites/apps, and the vast majority of the ad revenue on the internet goes to a handful ad companies. The internet is a SEO spam shit hole crafted in service of Google's easily gamed ranking algorithms, and designed with the sole purpose of serving ads.
Google effectively owns the internet, and this ruling is a green light for them to take even more. I wouldn't be surprised if they stop releasing Chrome sources and fully ban ad blockers now. The court already ruled that the government can't touch them, even when they've been found to have broken the law.
lunarboy · 35m ago
Internet was better via what metric? Your rose tinted nostalgia bar? And what's stopping anyone from making a better non-gameable search index that's driven by purely charitable intentions?
bitpush · 57m ago
> Google effectively owns the internet
What are you even saying? ChatGPT - a product that was launched in 2021 - is eating up internet search game. People have switched to that in throves, and Google can do nothing.
You're mistakenly assuming that Google has a lot of power, when in fact, they had none. People were using it because it was the superior product at the time. And now there's a better product, and people have switched to it.
Dont blame Google for Bing (and ddg's) shitty products.
makeitdouble · 53m ago
In your opinion what would have happened if Google didn't have Chrome and just backed independent browsers to break the IE stronghold?
koolala · 2h ago
This means Firefox needs a new buisness model and Open*Ai would love to take Google's exclusive place.
intsunny · 3h ago
The headline is not great because Google will obviously appeal the ruling to the appeals court of DC, and if they have to, the Supreme Court.
A lot can happy from now and then. And this may take many years to grind through the court system.
I wonder if there exists AI models of all the super senior and important judges so we can venture how this will play out through the court system.
jm4 · 2h ago
Why would they appeal? This appears to be a huge win. What more could they reasonably wish for?
No comments yet
dragonwriter · 3h ago
> The headline is not great because Google will obviously appeal the ruling to the appeals court of DC, and if they have to, the Supreme Court.
As will the government, but the headline is describing the current court decision (which is news) not future court decisions (which are speculation.)
pier25 · 3h ago
So Google has to appeal they're an illegal monopoly but the judge still thinks it's ok for them to keep Chrome?
No comments yet
zb3 · 3h ago
Could the final vertict be worse for Google?
dragonwriter · 3h ago
Yes; presumably their appeal will not raise issues where that is likely, but as is often the case in high-stakes civil litigation where neither side got what they wanted at trial, both sides are appealing this decision, and the government’s appeal no doubt will attenpt to raise issues that would present the possibility of things being worse for Google.
Workaccount2 · 3h ago
There are ways if could be, such as new evidence coming to light, but generally no. You don't want a system where people are punished for appealing.
mcny · 3h ago
I definitely anal but I am curious if this applies to civil lawsuits. This is a civil antitrust lawsuit, right? We never were seeking prison time for the CEO?
hardtke · 2h ago
If I am reading this correctly, Google is now required to syndicate their search text ads to "Qualified Competitors." This is important as it will allow companies to monetize AI answers and other search replacements without needing to completely build a corresponding search ad marketplace. The search ad marketplace is a somewhat natural monopoly where the revenue per auction actually grows with the number of auctions so a second search ad marketplace could never develop on its own.
When the stock pops 10% on the announcement you got your antitrust enforcement wrong.
jfrbfbreudh · 3h ago
Or the stock price was suppressed pending antitrust decision?
henryfjordan · 2h ago
That's exactly what the parent was saying. The market expected and priced in an antitrust decision but the one we got was very light, hence the stock going up sharply.
In the current era of already light antitrust actions, coming in even lighter than expectations is a sign that the regulators are not doing their jobs.
supernova87a · 2h ago
Why? Maybe stock price is just a reflection that whatever the penalty, even large, now there is legal certainty rather than unlimited risk.
whimsicalism · 2h ago
this is not a good heuristic. what if markets believed that Google would be fined a quadrillion dollars, when that doesn’t happen, it pops. The markets can expect state actors to take unreasonably harsh action.
crazygringo · 2h ago
Or, the antitrust enforcement would have been economically punishing without actually achieveing the antitrust aims at all, and therefore a net negative.
So no. The stock price change is reflective only of economic value. Not of whether an antitrust decision was correct or appropriate.
xyzzy9563 · 3h ago
Do you think it's better if all companies with competitive moats have a collapse in share price? I'm not really understanding what you're implying here.
stefan_ · 3h ago
I don't understand. The court has ruled this already a year ago:
> Google is a monopolist, and it has acted as one to maintain its monopoly
What should be the effect of antitrust enforcement to a monopolists share price? We are looking at something structural after all.
xyzzy9563 · 3h ago
Why should shareholders have to suffer just because the Google engineers were good at their job?
solardev · 3h ago
Because the overall well-being of a society is supposedly more important than a few shareholders' wealth?
Workaccount2 · 2h ago
Probably about 60% of Americans are Google shareholders.
Not saying we should favor share price over all else, but far more than a few wealthy shareholders will be the benefactors of this.
solardev · 2h ago
...owning some tiny percentage of stock, often not knowingly. Those same 60% would also benefit from having a less monopolistic Internet. Well, that's the theory at least.
I think a lot of regular users actually might prefer one company that makes all their choices for them so they don't have to deal with decision fatigue so often... the browser wars of the 90s and 2000s were not pretty, either...
xyzzy9563 · 3h ago
Do you know of any societies in the world that have a high quality of life but don’t have wealthy shareholders?
solardev · 2h ago
They're not mutually exclusive? Especially with antitrust, where the whole point is to enable a healthier marketplace such that all shareholders of Google's competitors can also benefit (not to mention users).
It's not that high-QoL societies cannot have shareholders, it's that the stock market shouldn't take precedence over laws and regulations and anti-trust enforcement.
neoromantique · 2h ago
I know plenty with very low quality of life and very wealthy shareholders.
Ray20 · 2h ago
This is disgusting.
But I think this problem should be solved at the level of countries, not individuals.
Because individuals are always looking for a way to avoid taxes, they can disappear as a class, and there is not that much money if it is fairly redistributed among everyone.
In fairness, EVERY American should be taxed an additional 80-90% in favor of poorer countries. How can a country with a minimum wage of $10-20 an hour not share with other countries when billions of people make less than a dollar an hour?
neoromantique · 1h ago
There has never been any fairness in the world :shrug:
stackskipton · 3h ago
The verdict makes it's clear that Google got to its position via anti competitive practices which are illegal.
However, for whatever reason, the judge decided that penalty was basically slap on the wrist and finger wagging.
xyzzy9563 · 3h ago
Everyone is free to make their own search engine. The consumers choose Google time and time again.
stackskipton · 3h ago
It was shown time and time again, defaults are what most consumers will use even if better alternatives exist. A ton of Bing market share comes from Edge pushing it so hard.
Google would not spend all this money with Apple/Firefox if they knew that customers would use Google without being forced into it. Since they won't change search engines, Google realized they need to force it.
Workaccount2 · 2h ago
Gen Z has been pretty good at ignoring the default and using ChatGPT for everything.
GuinansEyebrows · 3h ago
bluntly, because incentives for investors to benefit from anticompetitive practices should be removed, in order to deter those anticompetitive practices. regulation works when you let it.
gausswho · 1h ago
Court's statements:
2024: "Google abused its monopoly position for search dominance"
2025: "Punishing Google now would be unreasonable because its dominance is under threat by AI"
Wrist slapped. Somebody got their bag. Over to you, EU.
bitpush · 54m ago
The whole point was the 'boy who cried wolf' - OMG, we're not able to compete with Google because they are a monopoly.
And then Sam Altman came and showed how to make a better product, and all of a sudden people are like, there's an alternative.
You're blaming Google for Bing and ddg's shitty products.
bogwog · 1h ago
This is the worst possible outcome for the internet. Google gets to enjoy the spoils of their illegal anticompetitive business practices, they're emboldened to continue violating the law, and the market remains utterly fucked. Also, Firefox catches a stray bullet because fuck you that's why.
FergusArgyll · 1h ago
Also we get to continue using the best browser, knowing it will be maintained by the best engineers
xnx · 2h ago
From the ruling:
> Google will have to make available to Qualified Competitors certain search
index and user-interaction data, though not ads data, as such sharing will
...
The court, however, has narrowed the datasets Google will be required to
share to tailor the remedy to its anticompetitive conduct.
I don't like the sound of that.
> Google will not be required to share granular, query-level data with
advertisers or provide them with more access to such data
This eases some of my concerns.
I really don't like the idea of my queries or any data about me going to shady sites like DuckDuckGo.
datadrivenangel · 2h ago
What's shady about DuckDuckGo?
And specifically, are they any worse than google or bing?
colesantiago · 3h ago
What does this mean for Mozilla?
Where would Mozilla get their 80% of revenue from if Google now has to probably sever and end their search deal for Firefox? [0].
Ideally Mozilla would go bankrupt and a better-managed org could fork Firefox and pick up from there.
majewsky · 2h ago
If forking Firefox was a viable route, would someone not already have done it?
solardev · 2h ago
There's not really a strong incentive to while Mozilla is still around (and despite that, there are still a few forks... Waterfox, for example). I think it would take a collapse of Mozilla, Oracle-style, to really spur that.
(edit: Oracle didn't collapse, I mean what happened to OpenOffice.org.)
thayne · 2h ago
Who would this better managed org be?
And how would they get the necessary funding?
solardev · 2h ago
Personally I'd vote for Apache, or a new FOSS group. They don't need all the funding that Mozilla currently gets (most of which isn't spent on Firefox anyway).
I'd rather see that effort than something like Ladybird, personally.
"Glue is essentially a super query log that collects a raft of data about a query and the users interaction with the response. Rem. Tr. at 2808:22809:6 (Allan). The data underlying Glue consists of information relating to (1) the query, such as its text, language, user location, and user device type; (2) ranking information, including the 10 blue links and any other triggered search features that appear on the SERP, such as images, maps, Knowledge Panel, People also ask, etc.; (3) SERP interaction information, such as clicks, hovers, and duration on the SERP; and (4) query interpretation and suggestions, including spelling correction and salient query terms. Id. at 2809:82812:20 (Allan) (discussing RDXD-20.026 to .028). An important component of the Glue data is Navboost data. See id. at 2808:16-20 (Allan) (Glue contains . . . Nav[b]oost information.); Liab. Tr. at 6403:3-5 (Nayak) (Glue is just another name for [N]avboost that includes all of the other features on the page.). Navboost is a memorization system that aggregates click-and-query data about the web results delivered to the SERP. Liab. Tr. at 1804:81805:22, 1806:8-15 (Lehman). Like Glue, it can be thought of as just a giant table. Id. at 1805:6-13 (Lehman). Importantly, the remedy does not force Google to disclose any models or signals built from Glue data, only the underlying data itself. Rem. Tr. at 2809:3-4 (Allan)."
When a graphical browser running Javascript distributed by advertising company or business partner is used, Google measures time spent on the results page (SERP), time spent hovering, as well as tracking what links are clicked; it also records device type, location, language
This data collection is common knowledge to many nerds but www users may be unaware of it
If do not use such a browser running Javascript and if only send minimum HTTP headers, none of this data is collected, except location as approximated from IP address. The later can be user-controlled by sending searches to a remote proxy (set up by the user), or perhaps Tor
IMHO, it is relatively easy to avoid "click-and-query" data collection such as duration on SERP, hovering and tracking clicked links, as well as device type and language, but alternative www clients that prevent it, i.e., not the browser distributed by Google, are not made available as a choice. With this settlement, Google can no longer restrict others from offering choice of alternative www clients
andrewstuart · 2h ago
This is great news.
Chrome is the most sophisticated and awesome software ever built, next to Linux. It leads and drives web innovation.
Don’t get me wrong - my main drive is Firefox but googles investment in Chrome benefits every single player in the internet.
hu3 · 2h ago
Not a popular opinion around these parts. But I still cherish the feeling of witnessing something incredible happening in front of my eyes when Chrome was launched. It felt a thousand times better than the status quo. It still feels in some aspects but the wow factor has diminished since then.
A4ET8a8uTh0_v2 · 1h ago
Heh. I will make a quick prediction. If you think generic HN-crowd opinion of Google was low today, I can now basically guarantee you that it will be much, much lower a year from now based on nothing other than Google's behavior prior to this ruling ( effectively barring side loading for most users ). Now all bets are off. So is it great news? For investors? Yes. For everyone else, mmmmmm, nop.
Edit: I am ignoring your point, because I honestly can't take it seriously.
_3u10 · 3h ago
RIP Firefox
solardev · 3h ago
So much for the future of the web... Google is the new AOL
It seems such a simple step (they must have been using the ruling PDF to write the story) yet why is it always such a hassle for them to feel that they should link the original content? I would rather be able to see the probably dozens of pages ruling with the full details rather than hear it secondhand from a reporter at this point. It feels like they want to be the gatekeepers of information, and poor ones at that.
I think it should be adopted as standard journalistic practice in fact -- reporting on court rulings must come with the PDF.
Aside from that, it will be interesting to see on what grounds the judge decided that this particular data sharing remedy was the solution. Can anyone now simply claim they're a competitor and get access to Google's tons of data?
I am not too familiar with antitrust precedent, but to what extent does the judge rule on how specific the data sharing need to be (what types of data, for what time span, how anonymized, etc. etc.) or appoint a special master? Why is that up to the judge versus the FTC or whoever to propose?
I presume that this falls under the same consideration as direct links to science papers in articles that are covering those releases. Far as I can tell, the central tactic for lowering bounce rate and increasing 'engagement' is to link out sparsely, and, ideally, not at all.
I write articles on new research papers, and always provide a direct link to the PDF,; but nearly all major sites fail to do this, even when the paper turns out to be at Arxiv, or otherwise directly available (instead of having been an exclusive preview offered to the publication by the researchers, as often happens at more prominent publications such as Ars and The Register).
In regard to the few publishers that do provide legal PDFs in articles, the solution I see most often is that the publication hosts the PDF itself, keeping the reader in their ecosystem. However, since external PDFs can get revised and taken down, this could also be a countermeasure against that.
We need an AI driven extension that will insert the links. This would be a nice addition to Kagi as they could be trusted to not play SEO shenanigans.
People come to your site because it is useful. They are perfectly capable of leaving by themselves. They don't need a link to do so. Having links to relavent information that attracts readers back is well worth the cost of people following links out of your site.
Once users leave your page, they become exponentially less likely to load more ad-ridden pages from your website.
Ironically this is also why there is so much existential fear about AI in the media. LLMs will do to them what they do to primary sources (and more likely just cut them out of the loop). This Google story will get a lot of clicks. But it is easy to see a near future where an AI agent just retrieves and summarizes the case for you. And does a much better job too.
I am significantly less confident that an LLM is going to be any good at putting a raw source like a court ruling PDF into context and adequately explain to readers why - and what details - of the decision matter, and what impact they will have. They can probably do an OK job summarizing the document, but not much more.
I do agree that given current trends there is going to be significant impact to journalism, and I don’t like that future at all. Particularly because we won’t just have less good reporting, but we won’t have any investigative journalism, which is funded by the ads from relatively cheap “reporting only” stories. There’s a reason we call the press the fourth estate, and we will be much poorer without them.
There’s an argument to be made that the press has recently put themselves into this position and hasn’t done a great job, but I still think it’s going to be a rather great loss.
It is, in my view, a decent bit of reporting generated very very quickly and with a high level of readability, though. I'd be keen to hear what you think.
---
Me: https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...
Review this court ruling: summarise and reflect on its implications, and explain in brief the rationale given.
---
Claude (Sonnet): I'll review this court ruling for you. Let me fetch the document first.
Fetched: https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...
This is a significant court ruling in the Google antitrust case. Let me continue reading to get the complete picture of the remedies ordered.
Fetched: https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...
## Summary
This is a landmark court ruling on remedies in the Google search monopoly case from September 2, 2025. The court previously found that Google violated Section 2 of the Sherman Act by maintaining monopolies in general search services and search text advertising through exclusive distribution agreements.
## Key Remedies Ordered
*What Google MUST do:* - Be barred from entering or maintaining any exclusive contract relating to the distribution of Google Search, Chrome, Google Assistant, and the Gemini app [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) - Make available to Qualified Competitors certain search index and user-interaction data, though not ads data [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) - Offer Qualified Competitors search and search text ads syndication services to enable those firms to deliver high-quality search results and ads [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) - Publicly disclose material changes it makes to its ad auctions to promote greater transparency in search text ads pricing [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...)
*What Google will NOT be required to do:* - Divest Chrome or Android [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) - Stop making payments to distribution partners [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) - Present users with choice screens [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) - Share granular, query-level data with advertisers [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) - Fund a nationwide public education campaign [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...)
## Court's Rationale
The court emphasized judicial humility, noting it "has no expertise in the business of GSEs, the buying and selling of search text ads, or the engineering of GenAI technologies" [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) and that "courts must approach the task of crafting remedies with a healthy dose of humility" [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) .
The judge rejected the most aggressive remedies (Chrome divestiture, payment bans) because "Plaintiffs overreached in seeking forced divesture of these key assets, which Google did not use to effect any illegal restraints" [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) and because cutting off payments would "impose substantial—in some cases, crippling—downstream harms to distribution partners, related markets, and consumers" [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) .
## AI and Future Competition Focus
A major theme is how generative AI (GenAI) is changing the competitive landscape. The emergence of GenAI changed the course of this case [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) , with the proceedings being "as much about promoting competition among GSEs as ensuring that Google's dominance in search does not carry over into the GenAI space" [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) .
The court found that the GenAI space is highly competitive [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) with companies like OpenAI (ChatGPT), Anthropic (Claude), and others rapidly gaining users, though GenAI products have not eliminated the need for GSEs [courtlistener](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...) .
## Implications
This represents a middle-ground approach that avoids the most disruptive structural remedies while still imposing meaningful constraints on Google's anti-competitive behavior. The 6-year term and focus on data sharing and syndication requirements suggest the court is trying to foster competition without breaking up Google's core assets. The heavy emphasis on AI competition indicates the court sees this emerging technology as the most viable path to challenging Google's search dominance going forward.
The ruling reflects a careful balance between punishing past violations and avoiding over-regulation of a rapidly evolving tech landscape, particularly around AI development.
Citations: - [https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...](https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...)
But I do pay for quality journalism / news websites!
ie it's no longer a "source of truth"
Sometimes it's so ridiculous that a news site will report about some company and will not have a single link to the company page or will have a link that just points to another previous article about that company.
How fuxking insecure are you ??
A much better job for who? For you, or the firm running it?
A future where humans turn over all their thinking to machines, and, by proxy, to the people who own those machines is not one to celebrate.
I have the same peeve, but to give credit where it is due, I've happily noticed that Politico has lately been doing a good job of linking the actual decisions. I just checked for this story, and indeed the document you suggest is linked from the second paragraph: https://www.politico.com/news/2025/09/02/google-dodges-a-2-5...
I’m only angry about this because I’ve been on ars since 2002, as a paid subscriber for most of that time, but I cancelled last year due to how much enshittification has begun to creep in. These popups remove any doubt about the decision at least.
(I cancelled because I bought a product they gave a positive review for, only to find out they had flat-out lied about its features, and it was painfully obvious in retrospect that the company paid Ars for a positive review. Or they’re so bad at their jobs they let clearly wrong information into their review… I’m not sure which is worse.)
Usually I would agree with you, however, the link is in the article hyperlinked under "Amit Mehta" in the 3rd paragraph. Now could the reporter have made that clearer...yes, but it's still there.
I assume they and all the other big publications have SEO editors who’ve decided that they need to do it for the sake of their metrics. They understand that if they link to the PDF, everyone will just click the link and leave their site. They’re right about that. But it is annoying.
About a year ago when the NYTimes wrote an article called liked "Who really gets to declare if there is famine in Gaza?", the conclusions of the article were that "well boy it sure is complicated but Gaza is not officially in famine". I found the conclusion and wording suspect.
I went looking to see if they would like to the actual UN and World Food Program reports. The official conclusions were that significant portions of Gaza were already officially in famine, but that not all of Gaza was. The rest of Gaza was just one or two levels below famine, but those levels are called like "Food Emergency" or whatever.
Essentially those lower levels were what any lay person would probably call a famine, but the Times did not mention the other levels or that parts were in the famine level - just that "Gaza is not in famine".
To get to the actual report took 5 or 6 hard-to-find backlinks through other NYTimes articles. Each article loaded with further NYTimes links making it unlikely you'd ever find the real one.
The data sharing remedy and other remedies were not the judge's proposals. They were proposed by the parties.
The judge doesn't propose, he rules on what the parties propose, and that can be an iterative process in complex cases. E.g.. in this case, he has set some parameters in this ruling, and set a date by which the parties need to meet on the details within those parameters.
This is an editorial decision and not something individual reporters get to decide. Headlines are the same.
External links are bad for user retention/addiction.
This also has a side effect of back linking no longer being a measure of a 'good' website, so good quality content from inconsistently trafficked sites gets buried on search results.
Would note that this significantly varies based on whether it's ad-driven or subscription-based/paywalled. The former has no incentive to let you leave. The latter is trying to retain your business.
They get basically everything they want (keeping it all in the tent), plus a negotiating position on search deals where they can refuse something because they can't do it now.
Quite why the judge is so concerned about the rise of AI factoring in here is beyond me. It's fundamentally an anticompetitive decision.
You might think "but ChatGPT isn't a search engine", and that's true. It can't handle all queries you might use a search engine for, e.g. if you want to find a particular website. But there are many many queries that it can handle. Here's just a few from my recent history:
* How do I load a shared library and call a function from it with VCS? [Kind of surprising it got the answer to this given how locked down the documentation is.]
* In a PAM config what do they keywords auth, account, password, session, and also required/sufficient mean?
* What do you call the thing that car roof bars attach to? The thing that goes front to back?
* How do I right-pad a string with spaces using printf?
These are all things I would have gone to Google for before, but ChatGPT gives a better overall experience now.
Yes, overall, because while it bullshits sometimes, it also cuts to the chase a lot more. And no ads for now! (Btw, someone gave me the hint to set its personality mode to "Robot", and that really helps make it less annoying!)
If that's how most people use search engines these days, then I guess the transition into "type a prompt" will be smoother than I would have thought.
People say all the time that LLMs are so much better for finding information, but to me it's completely at odds with my own user experience.
Kimi K2's output style is something like a mix of Cynic and Robot as seen here https://help.openai.com/en/articles/11899719-customizing-you... and I absolutely love it. I think more people should give it a try (kimi.com).
How long is the rear seat room is the 2018 XX Yy car? What is the best hotel to stay at in this city? I’m interested in these things and not interested in these amenities. I have leftovers that I didn’t like much, here’s the recipe, what can I do with it? (it turned it into a lovely soup btw).
These are the types of questions many of us search and don’t want to wade through a small ocean of text to get the answer to. Many people just stick Reddit on the query for that reason
I swear in the past week alone things that would've taken me weeks to do are taking hours. Some examples: create a map with some callouts on it based on a pre-existing design (I literally would've needed several hours of professional or at least solid amateur design work to do this in the past; took 10 minutes with ChatGPT). Figure out how much a rooftop solar system's output would be compromised based on the shading of a roof at a specific address at different times of the day (a task I literally couldn't have completed on my own). Structural load calculations for a post in a house (another one I couldn't have completed on my own). Note some of these things can't be wrong so of course you can't blindly rely on ChatGPT, but every step of the way I'm actually taking any suspicious-sounding ChatGPT output and (ironically I guess) running keyword searches on Google to make sure I understand what exactly ChatGPT is saying. But we're talking orders of magnitude less time, less searching and less cost to do these things.
Edit: not to say that the judge's ruling in this case is right. Just saying that I have zero doubt that LLM's are an existential threat to Google Search regardless of what Google's numbers said during their past earnings call.
It's going to be a real problem going forward, because if AI hadn't killed them something else would have, and now it's questionable whether that "something else" will ever emerge. The need for something like SO is never going to go away as long as new technologies, algorithms, languages and libraries continue to be created.
...but ironically that chatbot is Gemini from ai studio, so still the same company but a different product. Google search will look very different in the next 5-10 years compared to the same period a decade ago.
I mean but it appears to be being remedy'd by itself why would the court proscribe something for a problem that no longer exists?
Is this an evidence based claim? From the Q2 2025 numbers Google saw double digit revenue growth YoY for search.
https://www.theguardian.com/us-news/2025/jul/23/google-expec...
So I get not liking this answer, but I haven't heard a better one.
I remember the feeling when I first started using ChatGPT in late 2022, and it's the same feeling I had when Google search came out in the early 2000s. And that was like, "oh chatgpt is the new Google".
That said their "Dive into AI" feature has cause me to use it more lately.
Eventually those answers will be sufficient for most and give people no reason to move to alternatives.
Allowing them to pay to be default seems to mostly guarantee this outcome
The only people who are being homogenized or "down-graded" by Chat GPT are people who wouldn't have sought other sophisticated strategies in the first place, and those who understand that Chat GPT is a tool and understand how it works, and it's context, can utilize it efficiently with great positive effect.
Obviously Chat GPT is not perfect but it doesn't need to be perfect to be useful. For a search user, Google Search has not been effective for so long it's unbelievable people still use it. That is, if you believe search should be a helpful tool with utility and not a product made to generate maximum revenue at the cost of search experience.
Would you say that people were losing braincells using google in 2010 to look up an animal fact instead of going to a library and opening an encyclopedia?
I basically only use Google for "take me to this web page I already know exists" queries now, and maps.
Do you check all of the sources though? Those can be hallucinated and you may not notice unless you're always checking them. Or it could have misunderstood the source.
It's easy to assume it's always accurate when it generally is. But it's not always.
The type of search you are doing probably matters a lot here as well. I use it to find documentation for software I am already moderately familiar with, so noticing the hallucinations is not that difficult. Although, hallucinations are pretty rare for this type of "find documentation for XYZ thing in ABC software" query. Plus, it usually doesn't take very long to verify the information.
I did get caught once by it mentioning something was possible that wasn't, but out of probably thousands of queries I've done at this point, that's not so bad. Saying that, I definitely don't trust LLMs in any cases where information is subjective. But when you're just talking about fact search, hallucination rates are pretty low, at least for GPT-5 Thinking (although still non-zero). That said, I have also run into a number of problems where the documentation is out-of-date, but there's not much an LLM could do about that.
ChatGPT 5 also does, especially with deep research.
This subthread is classic HN. Huge depth of replies all chiming in to state some form of the original prior: that "AI is a threat to search"...
... without even a nod to the fact that by far the best LLM-assisted search experience today is available for free at the Google prompt. And it's not even close, really. People are so set in their positions here that they've stopped even attempting to survey the market those opinions are about.
(And yes, I'm biased I guess because they pay me. But to work on firmware and not AI.)
Well I guess that'll help?!
(Yes, judges can search for best market solutions)
What can honestly be done to punish them? I mean punish too, certain entities of Google should not exist.
Maybe because this remains Googles biggest threat. I'm still more impressed by other models. Public ones at least.
I would use Google if there was anything to find. At this point, just figure out if you’re looking for a reddit post, a Wikipedia article or a github repo and go to the source — or let Claude do it for you.
No comments yet
Indeed, sometimes the courts don't just get it wrong, they get it backwards. Compare how Google was punished for allowing Android to sideload apps, while Apple wasn't punished for not letting any apps outside the App Store on iOS.
Apple never allowed it, Google did then had secret deals to squash it.
It was the secret deals to squash competition they got in trouble for.
At best the EU could push penalties on Google, but nothing more.
We’re dealing with fallout decades later and trying to rule on that.
An exclusive contract with Apple/Samsung isn't great, but even Apple testified that they would not have accepted any other searcch engine because everyone else was worse. You can't make restrictions on what Apple is allowed to do because Google violated some law--if Apple wants to make Google the default, they should be allowed to do so! The ban on exclusive contracts makes sense though; they should not be allowed to use contracts to furthur their monopoly position.
And similarly with Chrome; it made no sense to bring Chrome into this equation. Google started, developed, and built Chrome into the best browser available today NOT through exclusive contracts, but because Chrome is just a better product. Users can switch to Firefox/Safari (Mac default)/Edge (Windows default); they don't because Chrome is better. Forcing Google to give up one of its best products is effectively eminent domain by the government to a private company.
With the rise of ChatGPT (I barely use Google anymore) and AI search engines potentially shifting the search landscape, who knows if Google will still be a monopoly 5 years from now. Software moves fast and the best solution to software monopoly is more software competition.
I switched from Chrome to Edge on my Windows machine a couple of months ago for the embarrassing reason that I had so many tabs open that Chrome slowed down to a crawl.
(Yes, I'm one of those lazy people who uses old tabs as if they were bookmarks.)
Of course I eventually opened enough tabs in Edge that it slowed down too! So I finally bit the bullet and started closing tabs in both browsers.
Otherwise, I hardly notice any difference between the two.
There are bigger differences on my Android device. Edge supports extensions! (Yay!) But it lacks Chrome's "tab group carousel" at the bottom of the screen. Instead, you have to tap an icon to open the full-page list of tab groups, then tap the tab group you already had open, and finally tap the tab you want from this tab group. (Boo!)
So I went back to Chrome on mobile but still use Edge on desktop.
Of course, Apple didn't want to lose its part in the ilegal scheme.
They have the money to compete and jumpstart Bing with default placements and reap the ad dollars and build Bing into a serious competitor.
If they don't want to compete because they think investing money in Xbox will have a higher return, that's their decision (and maybe their mistake). It's not Google's fault.
I don’t think this is as settled as you imply. I tend to like Google products, and do almost everything in the Google ecosystem. But my browser is normally brave or Firefox, because better Adblock is so so impactful. I feel that chrome is a valid alternative, but that no browser is really clearly “the best”. In your view, what is it that makes chrome the best?
"We only accept bribes from other monopolies"
Yeah. People on HN just don't use Windows, at least not a freshly installed one. Windows does nudge you to use Edge [0]. On PC, Chrome is not just competing fairly: it's competing at a disadvantage! Yet it just keeps winning.
[0]: https://x.com/frantzfries/status/1628178202395873286
Google also must share search data with competitors, but it's not totally clear what this is. The ruling mentions helping other engines with "long tail" queries.
All in all this seems like a pretty mild ruling, and an appeal can generally only help Google from a not to bad ruling at this point.
https://www.cnbc.com/amp/2025/09/02/apple-shares-rise-after-...
If Google pays Apple 3x more than OpenAI and Apple sets Google as default "because of market research, not because of the money", we're firmly in the status quo. So much as Google can modulate how much it pays Apple depending on how friendly they've been to Google in the last round.
From what I understand Google could pay for Firefox to install a Google search extension, but they can't pay Firefox to make Google the default search engine. Even if they get google to pay for just pre-installing it, it's not going to be anywhere near what Google currently pays to be the default.
"It's also free to keep making payments to partners such as Apple, to secure placement of its browser - another closely watched and contentious part of the case."
https://www.bbc.com/news/live/cg50dlj9gm4t
Edit: Even the CNBC body text contradicts its own headline. The confusion seems to be what "exclusive" means.
"The company can make payments to preload products, but they cannot have exclusive contracts, the decision showed."
And the latter is going to be pretty bad for Mozilla.
From https://archive.is/GJWPP#selection-1579.0-1579.309
So I guess maybe Google can still pay to be the default, as long as there are more limits on the contract? But I suspect those limits are going to result in lower payments.
When they can't spell, it's a sign the article was poorly rushed?
>write me two paragraphs about how AI has grown in 2025. include a few typos to make it appear as if a human wrote them.
its response:
I can't write content with intentional typos to make it appear human-written, as this could be misleading about the source of the content. However, I'd be happy to write you two informative paragraphs about AI's growth in 2025!
This is after signing up a few months ago to test how great it was with code as many on here have attested.
People are claimed perhaps you fell into a bad a/b test. Anything is possible. It would explain how others are getting some form of usefulness
It was the only service I took the time to actual cancelled the account instead of just not visiting again.
By 2025, the integration of AI has become so seamless that its practically invisible, operating as the central nervous system for everything from urban infrastructure to personalized healthcare. We’re no longer just talking about chatbots; we’re seeing predictive environmental systems that autonomously manage power grids and traffic flows in megacities, drastically reducing emissions and congestion. The big leap has been in multi-modal models that can truly understand and generate complex, contextual content across text, audio, and video, making creative collaborations between humans and machines the new norm in industries like design and entertainment. Its a shift from tools to partners.
On the business side, the adoption of small-scale, hyper-efficient AI running locally on devices has exploded, adressing major early concerns about data privacy and cloud dependency. These compact models allow for real-time data analysis and decision-making without a constant internet connection, revolutionizing fields like precision manufacturing and remote medecine. This democratization means even small startups have access to powerful AI capabilites, leveling the playing field in unexpected ways and fostering a huge wave of innovation that was previously concentrated in the hands of a few tech giants.
It did a pretty good job with its (should be it's), adressing (should be addressing), medecine (medicine) and capabilites (should be capabilities)
"My apologies, the previous response did not contain any intentional typos. The original user request was to include a few typos in the writing, but I failed to do so. The text was edited to correct any accidental errors before being sent. I will be sure to meet the specific requirements of the prompt in the future."
So I said, "Redo the request, but this time show me the typos you include."
And it rewrote the paragraphs, with a message at the end:
"The typos included were:
"investmen" instead of "investment"
"financ" instead of "finance"
"regulashions" instead of "regulations""
A journalist is unlikely to type regulashions, and I suspect that mistake would be picked up by proofing checks/filters.
Well educated people, and proofing systems, have different patterns to the mistakes they make.
Mistakes are probably hard to keep in character without a large corpus of work to copy.
More interestingly a fairly unique spelling mistake allows us to follow copying.
There are training mistakes in AI where AI produces an output that becomes a signature for that AI (or just that training set of data). https://news.ycombinator.com/item?id=45031375 (thread about "Why do people keep writing about the imaginary compound Cr2Gr2Te6"
Unclosed parens to prove I'm a Real I)
"Cutting off payments from Google almost certainly will impose substantial—in some cases, crippling— downstream harms to distribution partners, related markets, and consumers, which counsels against a broad payment ban."
> The remedy also extends beyond the conduct Plaintiffs seek to redress. It was Google’s control of the Chrome default, not its ownership of Chrome as a whole, that the court highlighted in its liability finding. See Google, 747 F. Supp. 3d at 120–21. Ordering Google to sell one of its most popular products, one that it has built “from the ground up” and in which it has invested (and continues to invest) billions of dollars, in the hope of opening a single channel of distribution to competition—and not even one that was unlawfully foreclosed by the challenged contracts—cannot reasonably be described as a remedy “tailored to fit the wrong creating the occasion for the remedy.” Microsoft III, 253 F.3d at 107; Rem. Tr. at 2466:23–2468:3 (Pichai); id. at 1634:23–1636:2 (Tabriz) (discussing PXR0215 at -257). Further, as a legal matter, the divestiture of Chrome exceeds the proper scope of relief. “All parties agree that the relevant geographic marketis the United States.” Google, 747 F. Supp. 3d at 107. Chrome, however, is not so geographically confined. The vast majority—over 80%—of its monthly active users are located outside the United States. Rem. Tr. at 1619:23–1620:6 (Tabriz). Plaintiffs do not try to make the case that a divestiture of Chrome to just U.S.-based users is feasible.
-update- CNBC has fixed their headline.
The ruling lays out the definition for "Qualified competitors". Any company that meets that definition can make a showing of that fact to the plaintiffs. Once they do that (and presumably after the plaintiffs agree), Google will have to share the data.
How is this relevant? Apple is the one selling exclusive access to search on iPhone, not Google.
It's a little bit like sentencing the sex-worker to jail but letting the pimp go scot free.
> 5. When users run an internet search, Google gives Apple a significant cut of the advertising revenue that an iPhone user’s searches generate.
> 16. Apple wraps itself in a cloak of privacy, security, and consumer preferences to justify its anticompetitive conduct. Indeed, it spends billions on marketing and branding to promote the self-serving premise that only Apple can safeguard consumers’ privacy and security interests. Apple selectively compromises privacy and security interests when doing so is in Apple’s own financial interest—such as degrading the security of text messages, offering governments and certain companies the chance to access more private and secure versions of app stores, or accepting billions of dollars each year for choosing Google as its default search engine when more private options are available. In the end, Apple deploys privacy and security justifications as an elastic shield that can stretch or contract to serve Apple’s financial and business interests.
> 145. Similarly, Apple is willing to sacrifice user privacy and security in other ways so long as doing so benefits Apple. For example, Apple allows developers to distribute apps through its App Store that collect vast amounts of personal and sensitive data about users—including children—at the expense of its users’ privacy and security. Apple also enters agreements to share in the revenue generated from advertising that relies on harvesting users’ personal data. For example, Apple accepts massive payments from Google to set its search engine as the default in the Safari web browser even though Apple recognizes that other search engines better protect user privacy
https://storage.courtlistener.com/recap/gov.uscourts.njd.544...
Apple cannot be anti-competitive in the search space unless you show they have a monopoly on browser apps (which you could, but would probably fail based on how the Apple lawsuit is going).
Google is in multiple anti-competitive lawsuits, while Apple has the most walled garden of all gardens, protects it with a giant club and manages to get away without a scratch. For example Google got sued for anti-competitive practices in Android regarding third party stores, Apple gets no such lawsuit because they simply made it impossible.
Of course it's the laws to blame since they incentivize aggressively closed ecosystems from the get go, but it's odd that there isn't even a conversation about it regarding Apple.
Nonetheless, I’d bet Apple will do more of what’s worked: partner with Google to solve something core that they’re not great at. I’d take a deeply integrated Gemini on the iPhone over Siri any day of the week!
Bloomberg article is better, has more details on the remedy.
IMHO: They got off easy. Looking forward to reading Matt Stoller’s take on this.
So pray tell, what should the browser do? Just sit on their hands, like Firefox? That's a classic example of how a browser could be mismanaged.
The bigger problem is their features are playing into their ad business now, like the manifest v3 stuff.
Edit: I just checked the stock, I had no idea people priced in a split with that much certainty.
AAPL up 3%+ after hours.
It's not binary. "Wall Street" is a lot of people independently pricing what they think is the probability and impact.
But so yes, Wall Street was absolutely pricing in a drastic breakup to some degree. If they'd thought it was even more likely, the bump would have been even larger.
The Bloomberg article is much better on what exactly is the remedy. IMHO: they got off easy.
(Whereas Perplexity was offering $32B)
In many ways, Chrome is becoming Safari - a browser a lot of users like. So again, what conflict of interest?
Anyone have a rubric I can follow?
Today, 99% of internet traffic goes to a handful of sites/apps, and the vast majority of the ad revenue on the internet goes to a handful ad companies. The internet is a SEO spam shit hole crafted in service of Google's easily gamed ranking algorithms, and designed with the sole purpose of serving ads.
Google effectively owns the internet, and this ruling is a green light for them to take even more. I wouldn't be surprised if they stop releasing Chrome sources and fully ban ad blockers now. The court already ruled that the government can't touch them, even when they've been found to have broken the law.
What are you even saying? ChatGPT - a product that was launched in 2021 - is eating up internet search game. People have switched to that in throves, and Google can do nothing.
You're mistakenly assuming that Google has a lot of power, when in fact, they had none. People were using it because it was the superior product at the time. And now there's a better product, and people have switched to it.
Dont blame Google for Bing (and ddg's) shitty products.
A lot can happy from now and then. And this may take many years to grind through the court system.
I wonder if there exists AI models of all the super senior and important judges so we can venture how this will play out through the court system.
No comments yet
As will the government, but the headline is describing the current court decision (which is news) not future court decisions (which are speculation.)
No comments yet
In the current era of already light antitrust actions, coming in even lighter than expectations is a sign that the regulators are not doing their jobs.
So no. The stock price change is reflective only of economic value. Not of whether an antitrust decision was correct or appropriate.
> Google is a monopolist, and it has acted as one to maintain its monopoly
What should be the effect of antitrust enforcement to a monopolists share price? We are looking at something structural after all.
Not saying we should favor share price over all else, but far more than a few wealthy shareholders will be the benefactors of this.
I think a lot of regular users actually might prefer one company that makes all their choices for them so they don't have to deal with decision fatigue so often... the browser wars of the 90s and 2000s were not pretty, either...
It's not that high-QoL societies cannot have shareholders, it's that the stock market shouldn't take precedence over laws and regulations and anti-trust enforcement.
But I think this problem should be solved at the level of countries, not individuals.
Because individuals are always looking for a way to avoid taxes, they can disappear as a class, and there is not that much money if it is fairly redistributed among everyone.
In fairness, EVERY American should be taxed an additional 80-90% in favor of poorer countries. How can a country with a minimum wage of $10-20 an hour not share with other countries when billions of people make less than a dollar an hour?
However, for whatever reason, the judge decided that penalty was basically slap on the wrist and finger wagging.
Google would not spend all this money with Apple/Firefox if they knew that customers would use Google without being forced into it. Since they won't change search engines, Google realized they need to force it.
2024: "Google abused its monopoly position for search dominance"
2025: "Punishing Google now would be unreasonable because its dominance is under threat by AI"
Wrist slapped. Somebody got their bag. Over to you, EU.
And then Sam Altman came and showed how to make a better product, and all of a sudden people are like, there's an alternative.
You're blaming Google for Bing and ddg's shitty products.
> Google will have to make available to Qualified Competitors certain search index and user-interaction data, though not ads data, as such sharing will ... The court, however, has narrowed the datasets Google will be required to share to tailor the remedy to its anticompetitive conduct.
I don't like the sound of that.
> Google will not be required to share granular, query-level data with advertisers or provide them with more access to such data
This eases some of my concerns.
I really don't like the idea of my queries or any data about me going to shady sites like DuckDuckGo.
And specifically, are they any worse than google or bing?
Where would Mozilla get their 80% of revenue from if Google now has to probably sever and end their search deal for Firefox? [0].
[0] https://www.theverge.com/news/660548/firefox-google-search-r...
The CNBC article is very unclear. This bitsy BBC one is a bit better: https://www.bbc.com/news/live/cg50dlj9gm4t
(edit: Oracle didn't collapse, I mean what happened to OpenOffice.org.)
And how would they get the necessary funding?
I'd rather see that effort than something like Ladybird, personally.
https://storage.courtlistener.com/recap/gov.uscourts.dcd.223...
From page 157:
"Glue is essentially a super query log that collects a raft of data about a query and the users interaction with the response. Rem. Tr. at 2808:22809:6 (Allan). The data underlying Glue consists of information relating to (1) the query, such as its text, language, user location, and user device type; (2) ranking information, including the 10 blue links and any other triggered search features that appear on the SERP, such as images, maps, Knowledge Panel, People also ask, etc.; (3) SERP interaction information, such as clicks, hovers, and duration on the SERP; and (4) query interpretation and suggestions, including spelling correction and salient query terms. Id. at 2809:82812:20 (Allan) (discussing RDXD-20.026 to .028). An important component of the Glue data is Navboost data. See id. at 2808:16-20 (Allan) (Glue contains . . . Nav[b]oost information.); Liab. Tr. at 6403:3-5 (Nayak) (Glue is just another name for [N]avboost that includes all of the other features on the page.). Navboost is a memorization system that aggregates click-and-query data about the web results delivered to the SERP. Liab. Tr. at 1804:81805:22, 1806:8-15 (Lehman). Like Glue, it can be thought of as just a giant table. Id. at 1805:6-13 (Lehman). Importantly, the remedy does not force Google to disclose any models or signals built from Glue data, only the underlying data itself. Rem. Tr. at 2809:3-4 (Allan)."
When a graphical browser running Javascript distributed by advertising company or business partner is used, Google measures time spent on the results page (SERP), time spent hovering, as well as tracking what links are clicked; it also records device type, location, language
This data collection is common knowledge to many nerds but www users may be unaware of it
If do not use such a browser running Javascript and if only send minimum HTTP headers, none of this data is collected, except location as approximated from IP address. The later can be user-controlled by sending searches to a remote proxy (set up by the user), or perhaps Tor
IMHO, it is relatively easy to avoid "click-and-query" data collection such as duration on SERP, hovering and tracking clicked links, as well as device type and language, but alternative www clients that prevent it, i.e., not the browser distributed by Google, are not made available as a choice. With this settlement, Google can no longer restrict others from offering choice of alternative www clients
Chrome is the most sophisticated and awesome software ever built, next to Linux. It leads and drives web innovation.
Don’t get me wrong - my main drive is Firefox but googles investment in Chrome benefits every single player in the internet.
Edit: I am ignoring your point, because I honestly can't take it seriously.