Readit News logoReadit News
potsandpans · 8 months ago
Just sharing an anecdote:

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.

Lewton · 8 months ago
A week ago, I was looking for the name of a semi obscure late 90ies computer game. Google could not help me given the description i gave

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

glenstein · 8 months ago
I've had a conversation almost exactly like this too, about an obscure dos based 3d fighting game. And some pessimistic instinct tells me I should worry, like this capability will be optimized away in future versions. It's like that precise pang of satisfaction is tied to a jaded feeling that I can't trust it to last if it ultimately depends on infrastructure and incentives that will lead openai toward eating the world like Google did.

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.

phil21 · 8 months ago
This is great, never thought to use ChatGPT for this use. I have been trying to remember a game from extremely early memories where I was able to play it for a single weekend at an uncle's house in my youth when my parents were out of town.

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 :)

nox101 · 8 months ago
I have tried the same, and had ChatGPT utterly fail.

> 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...

KetoManx64 · 8 months ago
I've done the same thing with movies quite a few times now. I'd mention a scene or two from the movie and approximately what decade it came out in and some of the themes of the movie and after a couple of back and forths it was able to return the name that I had forgotten.
VirgilShelton · 8 months ago
Wow! A million thanks goes to you! I never thought of using ChatGPT to find an old book I had 30 years ago! I just found it! Epic! I use ChatGPT but never tried this before! Thank you, thank you thank you!
pembrook · 8 months ago
There’s so much low effort, low hanging fruit that Google could do to improve results, that I just assume they've realized those things are unprofitable for them.

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!

paradox460 · 8 months ago
It's intentional.

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)

droidist2 · 8 months ago
I cringe whenever I hear the "it's SEO that ruined the search results" excuse for Google's incompetence/negligence.
ToucanLoucan · 8 months ago
It's more IMO the logical conclusion when you have a company that was built by engineers to solve problems than then changed out all their leadership over time to business executives who don't do anything besides line-go-up.
robertlagrant · 8 months ago
We did some Christmas quiz and as asked ChatGPT one of the answers, as the magazine had missed printing some of the answers by accident.

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.

bhhaskin · 8 months ago
That's the biggest issue with LLM searching. I cannot trust the answers. Search engines aren't much better, but at least I can check different sources. And to be fair search engines where never meant to be answer machines.
geertj · 8 months ago
Piling on, but I wanted to find a song I had once heard when I was a kid. I did not know the exact lyrics, just that it was woman talking about her husband leaving for space. I had tried to find the song using regular search engines multiple times over the years. Eerily (a little over a year ago, using GPT3.5), I was able to find the song within about 15 minutes of prompting with various pieces of information including tone, topic, and rough year I heard the song. (The song was "Clouds across the moon" from the Rah band.)
morkalork · 8 months ago
That's where I'm at too, I wanted to find the origin a quote and couldn't remember the exact words. Google was just pulling up random shit related to the words in the query and nothing related to the quote itself. ChatGPT figured it out in a minute. Same goes for looking stuff up in books, just ask what chapter something happens in.
silisili · 8 months ago
Interesting that worked. My experience with what I consider a similar type thing has been dismal. Perhaps not similar enough?

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.

t0mas88 · 8 months ago
Same experience for me for a small plastic car part. Tried to find it via Google using multiple queries but nothing worked, ended up at generic SEO car part sites trying to sell me anything but the part I needed.

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?

Abishek_Muthian · 8 months ago
I didn't paraphrase, I put the exact quote[1] I had copied earlier from goodreads in google and got garbage.

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

igor47 · 8 months ago
Open AI fails here:

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?

fivestones · 8 months ago
I tried with OpenAI’s o1 model and it came up with the right answer on the second try: https://chatgpt.com/share/6774a930-1e44-8013-8591-424c3b58d8...
BeefWellington · 8 months ago
Interestingly:

- 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

powtain-gen1 · 8 months ago
Please refer to the thoughts of Google's former CEO: AI can create deadly viruses!

https://powtain.com/pow/Ox2zJL

1980phipsi · 8 months ago
I couldn’t remember the phrase “oral history” and Google was terrible at figuring out what I wanted to search for, but ChatGpt got it for me after a few back and forths.
imperialdrive · 8 months ago
I had a similar experience last week. Searched and searched for a blurb from Middlemarch, without luck. o1 returned exactly what I was hoping for in one fell swoop.
smallmancontrov · 8 months ago
Google can't even find exact matches most of the time and its heuristic matches are just not as good as the transformers.
michaelcampbell · 8 months ago
> google has failed in delivering the core value prop of their product

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.

illiac786 · 8 months ago
Doesn’t Gemini perform just as well?

Google enshitified one product to require more money for the new one, while delivering zero added value overall.

I would say, well done.

m_ke · 8 months ago
SEO ruined the web, guided by Google's ranking algorithm.

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.

wwweston · 8 months ago
Libraries and librarians are starting to seem very relevant again. As are journalistic institutions.
BiteCode_dev · 8 months ago
Journalistic institutions have been requiring so much fact-checking, cross referencing and research lately it's a full time job to get informed.

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.

joe_the_user · 8 months ago
Libraries are booming but as gathering spots and place for people to get wifi to ... consume the web. Books remain but the selection is quite sparse.

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).

giraffe_lady · 8 months ago
What a relief then that those are all healthy, well-supported organizations with bright futures.

It's not a coincidence that the solution to this problem is exactly the organizations that are being systematically undermined and dismantled.

Ekaros · 8 months ago
I wouldn't even be sure about libraries... Books or whatever you are storing have to come from somewhere. And you have to regularly enough get new items in. And if these are polluted by AI generated content in various ways... Being able to pick real things from fake is nearly impossible outside very specialised areas where you have gone to primary sources. And even then just look at science. Already buckling with various issues.
scarface_74 · 8 months ago
Unfortunately, many of the “journalistic” institutions are owned by large corporations who aren’t going to “speak truth to power” in fear of retribution.

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

debesyla · 8 months ago
A library is similar to search engine - it can't have (display) all possible items (results), so there is also a bias for selection.

It's not easy for a truly creative, new and unique content to get into your local library.

techdmn · 8 months ago
I would argue that advertising ruined the web. SEO for sites selling real products only goes so far. People are often searching for information, and monetizing that activity through advertising is what caused the disaster of low quality content flooding the web today. I'm not saying things would be perfect without advertising, just much better than they are now.
pembrook · 8 months ago
Advertising ruined the UX of Google’s search page, but I would argue the exact opposite when it comes to the web itself.

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.

eastbound · 8 months ago
This. If Google kept at “Pages must be short and provide straight answers”, then we’d have much better search results today.

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.

mrkramer · 8 months ago
It's fascinating to me that Google didn't yet crack the actual discovery of websites and information. Google is constrained to 10 search results by design because majority of people won't ever go to the second search results page. So basically they have to figure out how to put as much useful information and links on the first page of search results. Btw I think we need web directories now more than ever.
hombre_fatal · 8 months ago
> If Google kept at “Pages must be short and provide straight answers”, then we’d have much better search results today.

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?

ethbr1 · 8 months ago
Why ascribe to malice, what can be explained by ineptitude?

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.

gscott · 8 months ago
Maybe, but Google in trying to stamp out seo spam just gravitates now to a few big company websites and shows them first because it no longer matters. Google is actively now trying to not even show you the organic results.

Even better for Google the worse the organic results are the more you need to rely on ads or some sort of ai snippet.

jerf · 8 months ago
Don't bet on AI staying clean.

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.

NBJack · 8 months ago
I very much agree this is effectivity a 'honeymoon' period.

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...

JKCalhoun · 8 months ago
The kids running local LLM's then have the right idea. They can stop with the last, good dataset before Sellama (and AdGPT) poisoned the well.
captainbland · 8 months ago
> I very much agree this is effectivity a 'honeymoon' period.

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.

trollied · 8 months ago
Expect ads to be interspersed with ChatGPT replies in the near future. It's another place to advertise.

Must go look for a patent on it, there will be one. (lol)

TeMPOraL · 8 months ago
Dark Google isn't a new thing. Isn't even an Internet thing. It's the very same cancerous growth on society that's been ruining every single communication medium we invented, the disease that's the answer to "why X sucks?" for any X.

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.

johny115 · 8 months ago
Devs always complain about advertising, but it's why devs tend to do much better comparatively to other jobs in same region. Without distribution mechanisms, there are no sales, without sales, there are no well paid jobs, and eventually no jobs at all.

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.

AnthonyMouse · 8 months ago
> And if Dark Google has not yet figured out how to scam AI... it is only a matter of time.

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.

squiggleblaz · 8 months ago
If beating SEO was something a company with a different algorithm could do, then it would have happened by now. Google remains the default search engine because the alternatives are perhaps even more susceptible to SEO than Google, so there just isn't the motivation to use them. Why do I have to go to the second or third page to find an answer with a naive search on DDG?
_false · 8 months ago
I like the Dark Google metaphor, but SEO agencies being Google's real customers makes no sense to me.
marcus0x62 · 8 months ago
Not OP, but here's how I read it: the SEO operators are driving traffic to google's ad network, where google make's its money. They aren't necessarily paying google much: the ad buyers are doing that, but they deliver the eyeballs to google's ads.

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.

jazzyjackson · 8 months ago
Maybe one step removed, if I understand it right, the spam sites make money by offering ad space and traffic, and Google makes money by selling ad placement on those sites, so actually Google and Dark Google are on the same side of the marketplace.

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)

flpm · 8 months ago
I think it's more a symbiotic relationship, they feed on each other and both benefit at the expense of the users
edgyquant · 8 months ago
SEO agencies often onboard people to AdWords
jonplackett · 8 months ago
Yeah I also didn’t get this. Can you explain what you meant?
ccppurcell · 8 months ago
"dark Google" seems like the title of a blog post I would find on HN! This is intended as a compliment, in case not clear... Add some important facts and figures (what is the revenue of dark Google, who and how many are they employing) and write it up!
lostlogin · 8 months ago
> we're not the real customers any more.

Were we ever? I didn’t pay for search. I don’t pay for email.

Doctor_Fegg · 8 months ago
I pay for both now (Kagi, Runbox). It’s just so much better.
MichaelZuo · 8 months ago
Yeah it’s hard to see how most HN user were the ‘real customers’ of Google at any point in time. It makes no sense to claim that.
m463 · 8 months ago
Google isn't a search company, it is an identification company. that is its moat.
bambax · 8 months ago
"Dark Google" is dark as in bad, but not as in obfuscated. They can be seen and observed in places like LinkedIn where they discuss their plans in the open.

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.

sethev · 8 months ago
I think you're right, but also this doesn't contradict the article. Google reset to a cleaner state (leaving behind the advertising choked portals of the late 90s). Over time both internal and external forces have chipped aways at Google's original model.

Perhaps AI could drive a similar reset.

discordance · 8 months ago
It's taken 20 years of a public company having to show quarter on quarter, year on year revenue increases, which has resulted in (Dark) Google squeezing dollars over quality.

I think AI companies have a bit more time to avoid a similar situation.

Ekaros · 8 months ago
Or not. If the rates stay where there are or do not drop drastically there is lot sooner pressure to actually show profits. 2010s were very special economic environment.
mettamage · 8 months ago
Fun take

Disconcerting take

I like the narrative aspect of it

Dead Comment

bambax · 8 months ago
> Does ChatGPT Search have trust? Open AI isn't monetizing its search just yet, but AI has its own issues with hallucinations.

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.

falcor84 · 8 months ago
This reminds me of that awesome analysis of all the speech of a diplomat's visit in Asimov's original Foundation book:

> 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.

bambax · 8 months ago
What will happen is that when you ask the AI to summarize a book to remove the fluff, it will inject random mentions of how the main character decided to drink a Coke.

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).

glenstein · 8 months ago
>Ads are bad enough today, but it's possible the future will be worse: product placement in everything, everywhere, all of the time.

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.

Mistletoe · 8 months ago
Suddenly your "friend" starts recommending Coke or talking about it. But your friend is the AI now because everyone is lonely and living in their Death Stranding cells.
shinycode · 8 months ago
I agree we need something radically different because it’s an open gate to partial product placement with ads generated on the fly to people taste. Awful future ahead
tensor · 8 months ago
This is why there will be a market for personal LLMs that act as your agent, or maybe shared for a family or the like.
dagmx · 8 months ago
A lot of folks are focusing on the AI answers that Google gives, but for me the real downgrade has been the change in their algorithm a few years ago where it tries to search for what it thinks I mean instead of what I search for.

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.

cma · 8 months ago
Especially for programming identifiers. You put in some really tech sounding camel case identifier and it tries to split it out and match straight to celebrity trash scraped from Taboola.
RF_Savage · 8 months ago
The Yahooification of Googles search becomes more amusing when one considers that it is now led buy the dude who ran Yahoo search to the ground.
lelandfe · 8 months ago
Prabhakar Raghavan was recently "promoted" out of that: https://www.wheresyoured.at/requiem-for-raghavan/
Der_Einzige · 8 months ago
Given how Vivek and Elon kicked the hornets nest about this, I wonder if there will be blow-back at Yahoo. A lot of people don't realize that Yahoo basically only survives today off the back of H1b labor.
smt88 · 8 months ago
Every large tech company only survives because of H1b labor.
BadHumans · 8 months ago
Not anymore. Prabhakar was promoted from Head of Search to Chief Technologist whatever that means.
binkHN · 8 months ago
> Enter 2024 with AI. The top 20% of search results are a wall of text from AI...

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.

warner25 · 8 months ago
But "search" and "getting an answer to a question" are two different things, aren't they? I realize that the trend has been going this way for a long time - probably since Ask Jeeves started blurring the line - and this is indeed how a lot of people try / want to use search engines, but still... I wish that Google (and competitors) would have separate pages for something like "Ask Google" vs. traditional search (where I want to find a particular document or quality content on a certain topic instead of just getting a specific answer).

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").

darknavi · 8 months ago
Yes, they very much are two different things.

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.

echelon · 8 months ago
I get very wrong and dangerous answers from AI frequently.

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.

croes · 8 months ago
It want stay long. You are now in the pre ad phase. As soon as the ads are integrated the answers will become worse.
gr4vityWall · 8 months ago
> I've been trying hard to break my 10 year-old of the habit of just typing questions into search engines

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.

webspinner · 8 months ago
Right, A lot of times I'm searching for a filing. Or a site link. I do not ask questions when I'm doing so, that's ridiculous. I don't ask questions if I'm searching for a recipe, or something in my local area either. Actually, I very rarely do this.
ajross · 8 months ago
> But "search" and "getting an answer to a question" are two different things, aren't they?

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.

sagarm · 8 months ago
Like you, I thought typing questions into Google was wrong for a long time. The times have changed; this is how most people interact with Google, and it really does convey intent to the system better now that we have sufficiently powerful NLP.
mrkramer · 8 months ago
>But "search" and "getting an answer to a question" are two different things, aren't they?

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".

masa331 · 8 months ago
Kagi has better search and you can tweak it however you like. So the product you are wishing for exists.
vidarh · 8 months ago
Getting an answer to a question is a superset - the answer can be a page.

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.

nicbou · 8 months ago
The answers come from the same websites. They just get stripped of their traffic. As someone who puts a ton of work into writing accurate, helpful guides, it's devastating to have my work plundered like that.

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.

carlosjobim · 8 months ago
What value does the traffic have for you? Is it lost revenue from ads? Or are you selling something? If you're selling something, then the AIs could very well be giving you more sales than they take away.
scarface_74 · 8 months ago
How are you monetizing your website? Is it with ads?
zblevins · 8 months ago
Where are you publishing your guides? Would love to add another bookmark to my collection.

Dead Comment

m_ke · 8 months ago
It would be great if it wasn't completely wrong 50% of the time.
GiorgioG · 8 months ago
Describes my general experience with AI across the board. Copilot, ChatGPT, Claude, etc. It’s like I’m talking to a genius toddler. With ChatGPT losing 5 billion dollars on 3.7B in revenue this is unsustainable. It feels like the dotcom bubble all over again.
traverseda · 8 months ago
That's a very pessimistic take. It's right about 50% of the time!
jsheard · 8 months ago
The mark of a great product/feature is always when they feel the need to force it on users, because they know that a significant portion of users would switch it off if they could.
Terr_ · 8 months ago
The difficulty of verifying the answer isn't-wrong is another important factor. Bad search results are often obvious, but LLM nonsense can have tricky falsehoods.

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.

binkHN · 8 months ago
I find it mostly right 70% of the time.
Ancalagon · 8 months ago
Yeah the AI summaries are garbage still
TiredOfLife · 8 months ago
Compared to 0% of relevant results in first 10 pages it's an enormous improvement.
Schnitz · 8 months ago
The AI answers are nowhere near good enough to always be at the top, without any clear indication that they are just a rough guess. Especially for critical things like visa requirements or medical information. When you search Google for these sort of things, you want the link to the authoritative source, not a best guess. It’s very different for queries like say “movies like blade runner”.
pishpash · 8 months ago
It seems damning enough that Google itself doesn't know what is a more authoritative source or they would have weighted their AI output appropriately.

What does that say about their traditional search results?

mrkramer · 8 months ago
Not all queries are the same but I agree with you that the authority of source is crucial. That's why for example .gov sites rank high and should rank high because government is usually the most trusted source.

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.

BadCookie · 8 months ago
An example: I was looking up what a good diet is to follow after a child has been vomiting. The AI said to avoid giving fruit juice … yet the authoritative sources said the opposite. I already knew not to trust the AI, but this was nail in the coffin for me.
whimsicalism · 8 months ago
agreed and frankly I am a big fan of LLMs in general… it just doesn’t seem like the one behind google search is all that smart
onion2k · 8 months ago
Google's AI summary of search results hallucinates. You might like it, but you may also end up seeing, and believing in, something that just doesn't exist.

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...

selimthegrim · 8 months ago
It also misidentified an article by Bernard Vonnegut about ice crystals as written by Kurt Vonnegut
KTibow · 8 months ago
Most if not all of the times it "hallucinated" it was paraphrasing the web.
toddmorey · 8 months ago
For quick simple steps like how to get a Bluetooth keyboard into pairing mode, it seems to work really well. I hated the prior world where everyone attempted to hide the real answer 3/4ths of the way through a useless blog post or YouTube video.
lubujackson · 8 months ago
Which, we should note, didn't happen 10 years ago before the accountants took over search at Google. Those good, lean, helpful pages still exist. Google incentives websites to have pages of slop on everything now because they track how long you spend on a site as a "metric of a good match". Forrest for the trees...
asdff · 8 months ago
Were you not googling before? They had a bullet point summary that was actually more accurate because it scraped direct quotes from the website. Now I am getting wrong info from the ai summary. Its a huge step back from just what was there previously but its sold as some advancement.
crazygringo · 8 months ago
It definitely didn't seem more accurate to me. If quite frequently either scraped quotes that weren't actually an answer to my search (the webpage was correct, but the link between my search and the webpage was not), or it was an answer but the answer was wrong (because the webpage was wrong).

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.

Deleted Comment

whimsicalism · 8 months ago
…i’m no fan of the google AI feature but it is way more accurate than the scraped bullet point predecessor which would often scrape things while missing something key like a “here is the opposite of what we are talking about:” in the webpage
QuadmasterXLII · 8 months ago
They are also wrong just slightly too often. After the fifth time I was twenty minutes in to trying to use command line options that just don’t exist before realizing that I was being led down the winding path by an ai hallucination that I mistook for a stack overflow quote, I broke and paid for Kagi. Which then immediately added an AI drek feature, fml.
lm28469 · 8 months ago
> I can search for an answer to a question and, instead of getting annoying ads and SEO-optimized uselessness, I actually get an answer.

You get the average of the seo optimized answers

HarHarVeryFunny · 8 months ago
An answer is only as good as the expertise behind it. When searching I always pay attention to the source, and will skip ones that look less trustworthy.

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.

crazygringo · 8 months ago
I totally agree, I really appreciate them. Half the time they give me the answer straight away.

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.

jayd16 · 8 months ago
They're strictly worse.

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.

kotaKat · 8 months ago
I just want to be able to turn the stupid overview off. That's all. One simple toggle.

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.

masa331 · 8 months ago
Why don't you use Kagi? It has better search and you can customize a lot of things, even turning off their LLM
0xbadcafebee · 8 months ago
Is Google supposed to give you an answer, or help you find something you're looking for?

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.

pishpash · 8 months ago
It's wrong enough and unsourced enough that it's more cognitive load to vet the result than not having it.

Google is barely more useful because of this.

Deleted Comment

flakes · 8 months ago
Its hit or miss for me. This week I was googling how to use libarchive and the AI generated responses at the top of each query were either incorrect or hallucinations of methods that don’t exist.

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.

xboxnolifes · 8 months ago
I sometimes like it, but I've gotten very skeptical of it. One day a friend and I searched the exact same question in Google and got opposing answers for the identical search string. Thus wasn't in the "AI" widget, but one of their usual widgets that give answers to questions. I assume both use some form of AI anyway.
griomnib · 8 months ago
I think when it’s good it’s pretty good.

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.

yieldcrv · 8 months ago
I dont find it useful for the things I search

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

verdverm · 8 months ago
I use google.com for search and Gemini for Q&A. Two sites for two modes. I also use uBlock to remove the ai response from my search results to keep them clean and separate
christophilus · 8 months ago
Same with Brave search. The AI answer is often good enough for me to not need to go further. I’m with you, except I don’t use Google.
scarface_74 · 8 months ago
Search for anything with Google that has high ad monetization potential. You will find that Google turns off the AI overview.
antihero · 8 months ago
Arc Search is what Gemini dreams of being. I’ve found it to be incredibly useful tool to cut through a lot of the crap.
ClimaxGravely · 8 months ago
The few times I gave it a try it was dead wrong. The dream is nice but the execution is lacking.

Deleted Comment

ajkjk · 8 months ago
Google search had gotten so bad the AI overview is passable in comparison. They don't deserve credit for that! Search was better at getting useful information fifteen years ago than it does now. (And yes, the internet is way more full of garbage now--but they did that, they are responsible for that too!)

... 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.

jayd16 · 8 months ago
Why do we think the AI is any better? Isn't it based on the same dataset as search? How can it be anything but strictly worse for any given query?
whimsicalism · 8 months ago
if google’s AI overview were as smart as 4o, i would like it a lot more.
cyanydeez · 8 months ago
"Be Socially destructively evil via diffusion of content"

Deleted Comment

moralestapia · 8 months ago
You're definitely a contrarian.

Google search is awfully bad these days.

bfrog · 8 months ago
Google in 2000s was excellent. Modern Google makes me feel like I’m a product being sold a lemon at a barb wire fenced used car lot. It’s horrible, the things being shown are horrible, and there’s questionable ethics and value to be had by even going there.