I'll be the contrarian here and say I actually like Google's AI Overview? For the first time in a long time, I can search for an answer to a question and, instead of getting annoying ads and SEO-optimized uselessness, I actually get an answer.
Google is finally useful again. That said, once Google screws with this and starts making search challenging again, as it has been for years, I'll go elsewhere.
May I ask how old you are? I'm 38 and I've been trying hard to break my 10 year-old of the habit of just typing questions into search engines (or telling me to "Ask Google" whenever she asks me a question and I say, "Oh, I don't know").
I loath products like Facebook, Messenger, Google Photos, etc. are turning their traditional "search" page/feature into a one-stop AI slop shop.
All I want to do is find a specific photo album by name.
I just searched "what's the ld50 of caffeine" and it says:
> 367.7 mg/kg bw
This is the ld50 of rats from this paper: https://pubmed.ncbi.nlm.nih.gov/27461039/
This is higher than the ld50 estimated for humans: https://en.wikipedia.org/wiki/Caffeinism
> The LD50 of caffeine in humans is dependent on individual sensitivity, but is estimated to be 150–200 milligrams per kilogram of body mass (75–100 cups of coffee for a 70 kilogram adult).
Good stuff, Google.
Honest question: why?
I understand not wanting to use Google (the search engine) or not wanting to support Google (the company). But I don't see with the issue with just looking up questions.
I'm 10 years younger than you, and I've been reaching for search engines first since I was 7, I think. Basically since I learned how to turn the computer on and open a web browser.
Google exists, as both a successful enterprise and as a verb, precisely because to most people they are exactly the same thing.
No, this is wrong. People ask what they want to know. Sometimes the best answer is a link. Sometimes it's just an answer. The ability to intuit which is best is what makes products in this space worth making.
First conceptualization of the "search" were web directories then AltaVista and Google drove the complexity down for the users by providing the actual system which crawls, index and ranks web information. Now cycle will repeat again and we will get Answer Machines aka chat bots which drive the UX complexity for users even more down.
Why would I skim search results links and websites if the "AI" can do it for me. The only reason would be if you don't trust the "AI" and you want the actual links of websites so you can look for useful information by yourself but the majority of people want an instant answer/result to their search query hence Google's old school button "I'm feeling lucky".
Sometimes the answer we want is a specific page containing some term, but for most people, most of the time, I'd argue that getting a narrower piece of information is more likely to be valuable and helpful.
Once these monopolies have successfully established themselves, they will become indistinguishable from the ad-invested websites they replace. The only difference is that they will create no new information of their own, and they will destroy the indieweb that once provided it.
If a process gives false results half the time, and verifying any result takes half as long as deriving a correct solution yourself... Well, I don't know the limiting sum of the infinite series offhand, but it's a terrible tool.
What does that say about their traditional search results?
But when you are looking for new shoes to buy or food recipes then .gov sites can't help you and that's where things get ugly....SEO spam ugly.
For example, it says there's a sequel to a Disney film called Encanto, and there just isn't. https://bsky.app/profile/jasonschreier.bsky.social/post/3lee...
The AI summary now isn't perfect because it can still regurgitate wrong information from the Internet, or hallucinate information when there isn't any -- but it seems to actually understand what I want now, so it doesn't suffer from the incorrect matching problem.
Also, there are way more AI answers now than there ever were snippet answers.
You get the average of the seo optimized answers
One major advantage of Google's original pagerank was that originally it worked well and number of links to a page was a good proxy for trustworthiness and authority on a subject. It used to be that you'd find what you were looking for in the top few Google search results, which was a massive improvement to Alta Vista which was the existing competition where you'd have to wade though pages of keyword match sites listed in no particular order.
Anyway, source is critically important, and if I'm looking to find something authoritative then the output of an LLM, even if RAG based, is not what I'm looking for! Increasingly people may be looking to search to verify stuff suggested by an LLM, which makes a search engine that puts LLM output as it's top result rather unhelpful!
It doesn't help that with Google in particular their AI output is all heavily DEI biased, and who knows what else ... I just don't trust it as objective.
And when they're not helpful, it's no different from the first search result not being helpful and going to the second. Plus, they do a pretty good job of only showing them for the types of searches where they're appropriate.
Are the right 100% of the time? Of course not. But snippets weren't right 100% of the time, and not infrequently clicking on the top search result will contain information that's wrong as well. Because the Internet isn't 100% right.
The idea that a "wall of text from AI" is somehow bad doesn't make any sense to me. And it's not a "wall", it's basically paragraph-sized. Where the context is really helpful in determining whether the answer seems correct/reasonable.
They're just a summary, so any information is in the results or hallucinated.
If the AI could accurately point to the correct information, they would just order the results as such, but instead it's just a paragraph of spaghetti on a wall to look cutting edge.
I don't get why a Google Workspaces account can have Gemini forcibly disabled across the entire enterprise yet still have these AI features seep in with no way to manage it at the enterprise level.
Back when they only tried to help you find something, they were good at that. Really good. Then the ads and meta-slop came in and you couldn't find things anymore.
Then they decided they also wanted to answer questions, which is hard enough (they're often wrong). So they have to focus harder on answering questions.
And since they're trying to do both in one page/place, the question-answering has taken center stage, and finding things is now next to impossible.
So they're no longer a search engine. They're a crap version of OpenAI.
Google is barely more useful because of this.
I don’t mind playing with AI to help scratch together some code, but I do that using better models. Whatever model google is using for search results is too crappy for me to consider trusting.
But knowing when it is good is still hard, as I can’t trust it more than an LLM. But with an LLM I have a simple chat window, not a bag of rabid SVPs fighting to be on the SERP page.
I still have to check the sources and then add “reddit” to the end of my search query
so for me its actually an additional third step or remembering not to trust the ai overview
... unless you want anything like a perspective or an opinion on something, instead of a factual answer to a question, in which case it's totally useless.
Google search is awfully bad these days.
I was searching for a quote that I'd heard in an audiobook the other day. I just had the general paraphrase, and didn't feel like scanning through the chapters to go find it. This was a somewhat obscure source.
Google had just straight garbage for me. The quote was political in nature, and I felt like the results were fighting general tone-policing filters and were tuned for recent events.
o1 on the other hand, found the author of the quote, summarized the general idea of what i might be searching for and then cited potential sources.
It's just patently obvious to me that google has failed in delivering the core value prop of their product, they're begging to be replaced.
Described it to ChatGPT, and we had a back and forth where I explained why the games it suggested me weren’t right, it eventually found the correct game (Nocturne) and was able to explain to me that half of the things I remembered from the game were just plain wrong, and that’s why Google couldn’t find it
ChatGPT helping me with my hallucinations, go figure
Getting ahead of myself to be sure, Google absolutely deserves to be stomped, so for now I guess we just ride out this wave.
Edit: I see elsewhere that others are converging on this idea and expressing it more clearly, namely that we may be in a honeymoon period.
Bugged me on and off for the better part of a decade and I couldn't figure it out from describing it to google - the only thing I knew for sure were a few graphical UI screens seared into my brain, the rest was far too generic to really narrow things down.
In the end ChatGPT got it correct in the first try from a minimal description, confirmed by watching a youtube playthrough and the memories coming back immediately.
Masters of Orion if anyone was curious :)
> me: what's the relatively recent movie with a pig on the movie poster
> gpt: The movie you're referring to is likely "Pig," a 2021 American drama film. It stars Nicolas Cage as a truffle hunter who lives alone in the Oregon wilderness. He embarks on a quest to find his beloved foraging pig after she is kidnapped. The film was directed by Michael Sarnoski .
> me: no, that movie does not have a pig on the poster
https://en.wikipedia.org/wiki/Pig_(2021_film)#/media/File:Pi...
> gpt: My mistake, let's correct that. Given your description, another film that fits the criteria of having a pig on its movie poster and is relatively recent is "The Menu" (2022). This film features a darkly comedic and thrilling story set against the backdrop of an exclusive restaurant on a remote island, where a young couple experiences a very unusual dining experience. The pig on the poster is part of the film's intriguing promotional material, hinting at the film's critique of culinary culture and excess.
https://en.wikipedia.org/wiki/The_Menu_(2022_film)#/media/Fi...
> me: No, that move does not have a pig poster
> gpt: It seems I misunderstood your initial request. After a more detailed search, I couldn't find a recent movie specifically featuring a pig prominently on its movie poster beyond the titles we've discussed. Could there be any other details about the movie you're thinking of that might help narrow it down? For instance, any specific elements of the plot, actors involved, or even the genre might provide more clues to identify the correct film.
movie I was looking for was "The Hunt": https://en.wikipedia.org/wiki/The_Hunt_%282020_film%29#/medi...
I mean just de-ranking any article with an affiliate link alone would skyrocket the relevance of what content you surface on search.
The problem for Google is, they’re incentivized to make the results worse than the SERP ads. If the organic results are too good, nobody would ever click the ads. And they basically gutted the 3rd party Adsense ecosystem, so they no longer monetize off third party sites. That to me, was the dumbest decision in company history — basically leading to the dilemma they’re in now. They squeezed all the profit in the short term while killing the open web in the long term.
You can’t have a product that purports to help people search the open web…while simultaneously trying to sabotage people from organically clicking on the open web. It’s pure idiocy.
The answer is staring them right in the face with Youtube, who faces zero threat to their dominance. Turns out if you just surface the best stuff and rev-share the ad money with the content creators (like they used to do with blogs via Adsense) then 1) the creators keep producing good stuff 2) the product stays useful and 3) importantly the monopoly profits continue minting!
https://www.wheresyoured.at/the-men-who-killed-google/
Traditional search still works. Ask anyone who uses kagi. Google makes more money (for now) with garbage search, so they're optimizing for garbage. Thing is, garbage in, garage out, and it will eventually catch up with them (might already have given the disparity between Gemini and Claude/cgpt)
It was to do with a song used as a theme to a sitcom, and it changed the name of the song in the first answer, then it changed the name of the song and the sitcom on the second, and I forget what the third one did. Then I Googled it and got my answer straight away.
One thing I wish either was better at is finding things from fuzzy or minimal descriptions. My memory is pretty bad but I often want to find a movie I'd watched in the past.
I often remember little bits and pieces or themes from a movie or show and curious what it was from, and both Google and ChatGPT are absolutely terrible at this.
Compared to say, r/tipofmytongue, which is absolutely fantastic at such things. Sure, it's AI vs humans, but the difference in ability between the two on such queries is pretty staggering.
Asked Bing Copilot by describing the thing I wanted and got the exact part number and a link to a schematic on how it fits. Ordered it for just a few euros.
But recently it looks like Microsoft has been dialing back the AI answers on Bing. Maybe it got too expensive?
I use only local LLM's, So if anyone has Open AI's search tools give it a shot.
[1] "Few hundred years of Western society that we have lost the ability to memorise vast amounts of information."
― Lynne Kelly, Memory Craft: Improve your memory using the most powerful methods from around the world
https://chatgpt.com/share/6770c547-2f90-8004-ba41-21bfa4d3a7...
Curious about your local LLM usage -- do you have that documented, or can you recommend sources on how to get started in that domain? I self host most of my infrastructure, but not LLMs so far. Do you need special hardware? How do you interact with the LLMs? How to you keep them updated? Do you fine tune/do any training, or just of the shelf llama? Do you need to know a bunch about quantization? How fast are the responses? Can you use them in your IDE as a coding assistant? How is resource utilization?
- Bing: Goodreads is third result
- DDG: Paywalled NZ Herald article appears to be the only result.
Of course what you've really uncovered is that Google search is the only thing that respects robots.txt: https://www.goodreads.com/robots.txt
They have long since been riding the downhill slope of the enshittification curve, so the 'core value prop' is advertising now, which I submit they've been delivering.
Google isn't for you or me, it's for Google.
Google enshitified one product to require more money for the new one, while delivering zero added value overall.
I would say, well done.
A lot of HN readers conceptualize the forces attacking the integrity of the search results as just some isolated people taking occasional potshots, and then maybe slinking away if their trick gets blocked.
It is probably a lot more accurate to visualize the SEO industry as a Dark Google. Roughly as well resourced, with many smart people working on it full time, day in, day out, with information sharing and coordination. It isn't literally one company, but this conception is probably a lot closer then the one in the heads of most people reading this. Dark Google is motivated, resourced, and smart.
And then, once I started thinking of it that way for this post, I realized that increasingly.... Google is increasingly at beck and call of Dark Google. They're increasingly the real customers of Google and the real source of money. It's why Google just seems to be getting worse and worse for us... it's because we're not the real customers any more. Dark Google rules.
And if Dark Google has not yet figured out how to scam AI... it is only a matter of time. Dark Google is where Google gets its money now. When Dark Google turns its attention to AI fully, OpenAI will be no more able to resist its economic incentives than Google did.
Can't wait for the first screenshot of someone searching for the impact of the battle of Gettysburg on the civil war and seeing the AI do its subtle best to slide an add for Coca Cola into it in some semantically bizarre manner.
Expect the SEO collective to shift focus on AI if the search approach becomes profitable in a few years.
That said, given an "AI search" is estimated to be at least ten times [0] as expensive per query than traditional search, I hope you like ads.
For those hoping to see that cost to go down, training costs for improved models have instead been going up. [1]
[0] https://www.scientificamerican.com/article/what-do-googles-a...
[1] https://www.pymnts.com/artificial-intelligence-2/2024/openai...
At this point I'd be much more interested to hear which "unicorn" tech company did not have such a honeymoon period which it later turned away from. This should really be the default, expected behaviour at this point.
Must go look for a patent on it, there will be one. (lol)
Advertising industry.
I wish I knew what it would take for people to stop treating the unholy blend of marketing communications as respectable occupation, and consider it for what it is: a guild of liars ruining lives and societies.
Similar can be said about almost any other job, except the well-paid part.
Look at the world before advertising. Everything had to be local small scale only. So everything was very expensive, because no large-scale manufacturing effectivity and massive discounting on end product. Lot of technology isn't even possible on small scale.
Nothing worse than salty uneducated devs that think they understand how world works, just because they know how to code, but know nothing about history, economy, business and marketing.
I don't like intrusive advertising either. Nobody says that it has to be pushed to the most extreme level possible for it to maintain the benefits. Not even remotely. I also use agressive adblock, I don't react to ads in Google or YouTube, because they tend to be bad and completely non-relevant. I occasionaly react to Instagram ads though, for example. I bought products off Instagram ads and I am glad for it.
Some way to promote your product to consumers is extremely valuable and healthy to the modern world. Unless you want to separate yourself from it and become a self-sufficient small community oriented society, like Mormons.
The idea of virality and "build great product and they will come" has to be the stupidest crap devs tend to believe. It only works briefly in the early stage within the new market category. 99.9% of world'S products are in mature stage, and those beliefs will get you bankrupt. World needs advertising. New startup founders of great valuable products need advertising. You can notice that those that understand that, succeed vastly more often.
There is one thing the AI companies have going for them that Google doesn't: They don't have 90% market share.
That's a huge problem that only Google has, because if your black hat SEO stops working against Google, you dedicate all your efforts to fixing it until it does, and then Google has to win against the combined efforts of everyone in the world.
Now suppose there were a dozen search engines that all had around equal market share. You find something that works against the first one but that causes you to get dropped to page 10 by two of the other ones. You finally find something that works against three quarters of them... for a week... after which it still works against a third of them but doing that causes the other two thirds to drop you again. To have any chance with those now you have to stop doing that, but if you do you fall off the front page for the third it was still working against. Also, by the end of the month that third will be a quarter.
You could target only one specific search engine, but then you're doing the same amount of work for only 8% of the advantage, meanwhile that search engine can concentrate their efforts on thwarting the similarly smaller percentage of black hat SEOs who chose to target them instead of one of the competing search engines.
It's much harder to hit a dozen moving targets at once than just one.
Its kind of like the US hospital system, where doctors are considered by the hospital, if not de jure then certainly de facto, to be the real customers of the hospital. Doctors don't pay the hospital much of anything -- the patients do, usually via their insurance company -- but without the doctors, no procedures happen (i.e., no "traffic.") Hospitals can't bill for room and board, nursing services, therapy, etc., where the hospital makes its operating income without the doctors, and in markets where multiple hospitals exist, doctors drive the patients to the hospital(s) of the doctor's choice. Ergo, the doctor is the "real" customer of the hospital.
The hospitals can and have adapted to get a bigger share of the revenue pie by hiring their own doctors and buying up the clinics that drive a lot of customers to hospitals in the first place, just like Google has introduced products that are more vertically integrated, but the basic dynamic still exists where they are dependent on third parties to deliver customers.
In a way, it's the other way around, Google is paying the spammers for providing billboard space for their ad placement services.
The pervese incentive is that the harder it is to find what I'm looking for, the more ads I get served, hence all ad supported products trend towards becoming useless (see also: Amazon.com)
Were we ever? I didn’t pay for search. I don’t pay for email.
But I don't think Google is part of them, or their slave. I think Google is our last line of defense.
True, it's not very effective; more like the knight in Monty Python's Sacred Grail. Still, when we lose Google, we'll have nothing else.
Perhaps AI could drive a similar reset.
I think AI companies have a bit more time to avoid a similar situation.
Disconcerting take
I like the narrative aspect of it
Things will get even worse as scammy companies start flooding the web with LLM generated content pushing their products to bias LLMs to increase the probability of outputing their name for keywords related to their business.
Whenever I read or hear anything from the medias now, I'm now always asking myself "what are their political inclinations? who is owning them ? what do they want me to believe? how much of a blind spot do they got ? how lazy or ignorant they are in that context ? etc."
They killed the trust I had in them so many times I can't get any the benefit of the doubt anymore.
It's exhausting.
And journalism has been gutted, more gutted than is obvious. Especially, with mainstream journalists having few "feet on the ground" a lot can sneak by (what happened in East Palestine, for example, can be found on Youtube's Status Coup new but not the mainstream).
It's not a coincidence that the solution to this problem is exactly the organizations that are being systematically undermined and dismantled.
We just saw this with ABC News’s settlement with Trump because its owner Disney wanted to stay in his good graces.
We also saw this with Bezos owner Washington Post
It's not easy for a truly creative, new and unique content to get into your local library.
The real thing that ruined the open web and viability of search was, ironically, when Google killed display advertising by cutting Adsense payouts to near zero.
Now publishers monetize via the much more sinister “affiliate” marketing. You know, when you search for “Best [X]” and get assaulted with 1,000 listicles packed with affiliate links for junk the author has never even seen in person.
At least in the old system, you knew that an ad was an ad! Now the content itself is corrupted to the core.
Google is machine-gunning its foot since 2021, it’s really unclear to me whether they’re killing their baby just to make the job harder for competitors or something. For now… I open the Google Search results with a machete, and often don’t find any answer.
Talk about severing your own foot to avoid gangrene.
I disagree. Any prescription for what the ranking should be that isn't simply the most relevant result is a worse ranking.
I don't care if the top search result is the fastest, leanest, shortest, straightest, most adless, most equitable answer to my query if it's not the best answer to my query. I'll take the slowest loading, most verbose, popup ridden, mobile-unfriendly site if it's the one that has what I asked for.
Trying to add weights for things other than relevance is probably exactly where Google started going wrong. And then when it turned out badly, people propose yet more weights beyond relevance to fix the problem of irrelevance?
I just don't think Google cares enough about the web as a whole to make strategic decisions for content quality in aggregate.
Sure it cares about geeky nuances and standards (e.g. page structure / load times), but Pichai isn't considering the impact on web content quality when debating an algorithm change or feature.
If Google continues driving web quality off the cliff? Well, the business KPIs stayed green.
Even better for Google the worse the organic results are the more you need to rely on ads or some sort of ai snippet.
Everywhere where SEO people congregate, they talk only about this: how to produce content that will eventually end up in training data for LLMs, so that when you ask about anything remotely connected to a given brand, its products will show up in the response.
Ads are bad enough today, but it's possible the future will be worse: product placement in everything, everywhere, all of the time.
> Hardin threw himself back in the chair. “You know, that's the most interesting part of the whole business. I admit that I thought his Lordship a most consummate donkey when I first met him – but it turned out that he is an accomplished diplomat and a most clever man. I took the liberty of recording all his statements.”
>... When Houk, after two days of steady work, succeeded in eliminating meaningless statements, vague gibberish, useless qualifications—in short all the goo and dribble—he found he had nothing left. Everything canceled out. Lord Dorwin, gentlemen, in five days of discussion didn't say one damned thing, and said it so that you never noticed.
I'm pretty sure that we're now at the level of AI where it's possibly to fully automate such an analysis, such that even if the original content is entirely corrupted by product placement, the AI could cut it out to leave only the valuable information, if any remains. The only question is whether the AI will be on the user's side or the advertiser's side.
Let's go with truly open models! you say. That way we can be sure there are no shoddy behind-the-scenes deal going on between the model provider and some company or government.
But the ads are in the training data, they are part of the fabric of the world. You can't get rid of them except if you do the training yourself, which is a huge amount of work, and maybe impossible (because model providers escape copyright laws, and you can't).
Right, and it could be that a measurable criteria to optimize for will be the path finding from prompts to naturalistic conversations that mention products or even that reinforce consumerist thought patterns and consumerist self perception.
Unfortunately, it doesn't, and so I can't verify them. Not sure if it's an actual limitation of current LLM or rather they're intentionally filtering out the sources.
This will only be a problem for a few more years. Soon every article, paper, and website will be generated by a LLM. Verifying the output of ChatGPT by referencing other LLM generated source material will be a pointless exercise.
Try asking for sources, whenever I have asked, it gives them.
As a side note: I am using Safari and I noticed that Apple's search is also replacing my Google searches. In the past if I knew name of a company or organization but not their website I'd Google it. Now I put it in the address bar and Safari very often finds the website for me.
* you have to check an LLM result, especially if it cites something (because it may or may not exist)
* you can’t cite an LLM result
It’s a useful tool, but it lacks certain utility features that a useful web + effective search has. Or had.
And this: "OpenAI's search is becoming Google in the 2000s, if it can remain trustworthy."
The problem I see: People use OpenAI/Perplexity for knowledge. Not to seek website. I think sooner or later, most website will block AI crawlers. What does a website gets out of it?
I think it's pretty damning that it's not a built in YouTube feature by now.
Get a third party to do the crawling and the AI company can buy the data from the third party.
I get it though. I sort of am the news guy of my family and they constantly ask me where I go for news. It's an impossible answer. I grew up with the internet in it's early days, using it for policy debate research. It's a non-precise method of consuming various sources, judging their answers on plausibility and commonalities, and a healthy dose of constant skepticism.
But people don't want that. They want the answer spoodfed to them.
I fear the day that the poor kids who grew up believing everything LLMs hard out will reach a position of power.
The web battle will then happen on this moving quickly, like the news.
This will give immensely more power to the medias, and I fear that a lot given they have demonstrated time and again they can't be trusted with it.
Who decides those are facts?
What if someone comes up with alternative facts?
Youtube/Instagram Reels/Tiktok is the (sad) future. "Classical" media is a zombie.
Google is deader than dead on the search front. But I think they'll go the IBM route, albeit more successful
Even putting entire chunks of text in quotes isn’t enough anymore. I can never get Google to search for what I want without trying to engineer a prompt, when it could at some point.
In trying to become more helpful, it’s become worse.
So far I have not heard anyone say I GPT’d it, but Google is running very dangerously close to the edge here. For one thing the founders have checked out, never a good sign.
Something that also bugs people is GOOG wants to follow you everywhere, when you sign in to many websites that little blurb asking for your google account comes from a google server (<script src="https://accounts.google.com/gsi/client" async defer>).
I was responsible for servers that ran 100m page views a day at Yahoo! One day I was approached by this smarmy little guy who asked if he could pull logs from the machines. Alarm bells. Who the heck was this and what was he doing with the logs. I knew of course he worked for Filo and so I had to give over the data. This was the start of the spying on the customers. Google is a master of this, and it really irks a lot of their customers. Another red flag.
Alternates like duck duck go and brave have made some inroads. Their percentages are quite low still.
There have been layoffs in the name of cost cutting. Googlers have had some very public employee dissatisfaction meetings (my name for them). Employee compensation problems, problems with businesses the company is etc.
One last thing, Mark Cuban sold Broadcast.com to Yahoo for $5.7 billion April 1, 1999 (seriously!). “ Apollo Global Management acquired a 90% stake in Verizon Media, which included Yahoo and AOL, for $5 billion. Verizon retained a 10% stake in the new company, which was rebranded as Yahoo upon the deal's completion.” The deal was finalized Sept 1, 2021 according to chatGPT.
Probably just my limited perspective, but I am also noticing, it's vastly men who use ChatGPT daily on anything from random questions, to health queries or personal growth. Not sure why, but somehow, I don't know a single female who would use it much, beyond super basic queries. Meanwhile guys of all kinds of backgrounds, nerds or not, technical or not, young or old, doesn't matter ... if there is a heavy user, it's a guy. But as I say, just limited perspective, I don't know big enough number of people for substantial sample size. Just recently I see the stark contrasts more and more, even very smart, nerdy and highly curious women I know, are not interested in ChatGPT.
Because it will happen. I’m afraid that ChatGPT is my friend for 20€ today, but prices will increase and response quality will go the way of Siri.
They are probably thinking about it.
ChatGpt will become one of the most valuable company if they can pull it off and still keep the users happy.
I started with chat and asked why I couldn’t change the passcode on a kid's device.
I tried 3 answers. None worked.
So I google. First hit is an Apple forum with the exact problem. Solved.
Really wish such bold claims had better evidence.
I'm open to the suggestion that OpenAI can disrupt Google, but this was a weird case to highlight.
Open AI has started on day one with that goal.
Sure they charge some users for premium access, but they aren't currently enough to cover costs.
openAI needs a step change in performance, and that meta doesn't release an open-source version of it and a step change in compute efficiency.
Also, most of the content was either stolen(divx, mp3 etc) or created without of expectation of immediate reward(mostly passion projects).
Oh and btw, Google didn't got infested after LLMs proliferation. Google results were useless way before that. With LLMs there's even improvement as the spam is at least mediocre content.
The only solution I can dream of is to remove the incentive, aka remove advertising. I'm afraid I'll be dead long before that.
Google started going bad in the 2000s (albeit not as bad as now).
> if it can remain trustworthy.
At no point was it trustworthy - even if it were an abstract LLM, trust would be an issue; but this is the opaque product of a corporation heavily invested in by untrustworthy entities and people.
That does not mean it isn't often useful, but "trust" and "usefulness" are two very different things.
Google only had to provide superior value with a clean UI. OpenAI has to contend with normalizing the mechanisms that are upsetting the lives of the customer base that pays them; the customers they'll replace with ad servers as soon as it becomes prudent to start indicating their end-game.
- Local search results for businesses, phone #s, directions isnt available
- Im paying GPT subscriber and it constantly logs me out on my different devices
- Sora I can not upload photos of whoever & make them do whatever like https://hailuoai.video/ which is free and at times fairly convincing (fun for the 12 yr old in you lol).
I know GPT Search is new and Im excited for GPT to become a phone AI OS or Open AI & MIcrosoft developed their own phone with a new personal device paradigm... i.e. create a H.E.R. phone.. it's your personal AI Assistant that does all for you via text, voice, hand gestures, facial expressions, etc. Once you pick up your phone you see your assistant waiting to assist. You can skin your AI assistant to look like anyone living or dead (loved one could live on & help your throughout ur day). Probably some crazy ideas but a H.E.R. phone / personal device as described (some parts) would be something new/different and possibly give Apple and Android a run for their money!
A friend suggested to use his LLM wrangling skills to get the SDK adapted. The results were interesting, but we wasted a day or two on trying to make it actually work and failed.
Then it turned out I can call C code from within my runtime, which the LLM did not point out. I figured out the specifics with a bit of googling and successfully managed to call C functions. Yet there were still issues in parsing the data, now in C SDK itself; the friend used different LLMs to refactor and comment C code, but they did a bad job with missing implementations and a lot of general obvious comments (an empty deinitialization function with “clean up as needed” comment and so on).
Then it turned out there was an SDK for my runtime. I just did not search enough. Of course, the LLM would not say that. The LLM would just obediently try to do what it’s asked to do and never question why.
Even at that time, Google hardly ever showed me ads that I wanted to see (even though in former days, Google's ads were less intrusive than they are today): as I sometimes mention on Hacker News, most advertising networks have difficulties to "pigeon-hole" me into interest groups - many interests of me are somewhat niche.
For example many Google searches that I do are about scientific topics from my areas of expertise - this is a rather hard topic for advertisisers (though it is plausible that it might be a lucrative topic for anybody who is capable to monetize on people like me).
On the other hand, if (rather accidentally ;-) ) Google's advertising/interesting sorting algorithm actually "finds" some interest of me which can be "monetized" via ads that try to sell me something, it's the common case that I have already bought such a product recently - in such a situation I clearly don't need another piece of the product. The reason for this is simple: after I bought the product, I have to understand some of the product's "complicated convoluted details", so a lot of Google search queries are of the type "[product name] [potential problem that I have with the product]". Thus, I do a lot more Google search queries for the product after I bought it.
It should be obvious that for the ad to pay off for the advertisier, it should be shown before I buy the product - thus Google has to be capable of interpreting the quite weak signals that might show that in the future I might want to buy such a product, and not the strong signals that Google sees in the weeks after my purchase.
Is is ironic that LLMs are the source of much of the garbage in search results. Good business model to produce unbearable noise and the filter that recovers some signal, I guess.
Today majority of the internet users ie 10-32 years old or 60%+ of the internet users grew up with using Google and how to get best answers our of it. Chat gpt might bring in some churn but as long google is close enough it won't get replaced easily.
If Google's competitive advantage was only that they had a clean and simple web page, I don't think they'd have nearly the sticking power they ended up having. You can design a front-end that looks like Google's original UI in a matter of hours.
It seems implausible tale that in the 25 years since their ascendance, nobody has tried to compete with them with a simple-looking search box.
Google became dominant because Google was much better than the alternatives.
It hit me that in a few years, this may not be available as Docker and other tool suppliers start paying for advertising. We’ll see.
Their search results have been less than useless to me for some years now. And then LLM's came along and have been my go-to for all queries.
“Before getting a response, a word from our sponsors:” type thing?
Nailed it. Google should show the transcript.
The old Internet still exists, but Google's ranking behaviour hides it.
If you're going to work the metaphor, work the metaphor!
> Yahoo was dominant back then, and it tried to put everyone and everything in front of you. Then we learned about the paralysis of choice. Too many choices, the mental fatigue weighed in, and the product became difficult to use.
This nonsense again? I was around then, and I switched from Yahoo and AltaVista to Google despite its dumb name and stupid, childish logo because Google's results were hands-down better. Instead of a solely full-text search paradigm based only on keyword density, Google also ranked pages based on how many other pages linked to them, the so-called "PageRank" algorithm.
This worked much, much better, and was much harder (for a while) to game. Before Google, it was common when searching to find pages that gamed the search engines by stuffing their <meta> keyword tags with SEO crap or putting it in giant footer sections in a tiny font the same color as the background (to render it invisible). Google's PageRank wasn't fooled by this.
Also most of the major search engines adopted similarly minimalist UIs, and it did zero to stop the bleeding. They all lost to google. (AltaVista, the pre-Google Google, was still useful for a while for some specialty searching, like for anonymous FTP servers, and I wonder if DEC had never gone under or if Compaq had spun off AltaVista, maybe history would be different.)
EDIT: I just realized the article doesn't even mention AltaVista. Unbelievable.
Great job to both organizations!
It's index is created by people surfing with the Brave browser, so only websites used by real people are included.
For me, it's the web in general that isn't the same. Google Search is probably just as good, but I have an idea that the content to be indexed isn't what it was.
Has the world changed, or have I changed?
Probably both.
The WWW of content isn't the same, and i don't search for the same things anymore.
My use of search has become integrated in my patterns in the physical world. I need to know what products are in stock, where things are, when a restaurant is open and so on.
For those searches, Google is generally excellent I find.
Also, I actually find Google's AI Answers to be pretty decent.
Even if I do ethically disagree with denying the original content authors those page views.
the rest of the process described herein has been best described by cory doctorow as "enshitification."
I mean, Gemini is much better than the "traditional" google search as well.
Anything is better than 2024 google search actually.
#/media/File:Pig_poster.jpeg){kind=link}
#/media/File:The_Menu_(2022_film).jpg){kind=link}
