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.
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.
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
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.
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.
Open AI has started on day one with that goal.
There also independant research that prove this. hard to Google ;)
Basicaly it's proven that just switching the autocomplete when you search Trump or Kamala can sway the votes of undecided by huge margin.
The seek those and switch the suggestion were it matter.
They also incite people to go vote depending on the choice and buch of other dirty tricks.
You are right that it no longer work. In the end truth will always win because it connect to reality. Having just X switching to truth will swarm the world.
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.
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.
However if you want to get _more_ information, or assess if thats bollocks or not, its much slower and click-ier
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.
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.
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.
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.
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.
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.
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.
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.
I don't think this is true at all. It is people prone to hype, or who are naive, who are using LLMs. The savvy know that a tool which you have to verify every single time (because it isn't deterministic and makes shit up) isn't actually saving you any effort.
You think that you don't have the check the link at the top of the page from a google search?
In fact, last I checked, for every google search I do, I have literally hit the page down key before starting to read.
> * you can’t cite an LLM result
And you think you can cite the top search result from a google search?
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.
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.
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.
I've found it to be helpful in getting quicker information out of some 'review' style videos, where I can ask a few pointed questions and get answers faster than the narrator can get to that info. I hadn't found it to be wrong in my few attempts with it, but ymmv
why would someone create a 10 minute video if no one would watch it and they would get no money for it?
Get a third party to do the crawling and the AI company can buy the data from the third party.
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.
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.
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.
- 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!
I fear the day that the poor kids who grew up believing everything LLMs hard out will reach a position of power.
We're in the early stages here.
I think the issue with LLM answers is that I often have to go to Google or something to check if the answer is right. Maybe it shaves some time off, but we're still back to the original problem.
I have documented how I run local LLMs here - https://abishekmuthian.com/how-i-run-llms-locally/ .
I am less convinced this means it’s always a wash (or worse). Sometimes it’s good to have something to start with. “You can’t edit a blank page” is a truism among fiction and non-fiction writers of all stripes for a reason. Of course, the quality of what you start with matters, and it matters more the less of an evaluatory mindset you come to your tools with. I know at least some earlier adopters have that mindset, but perhaps I’m too optimistic about how it generalizes.
That's possibly the biggest waste of my time you could think of, because I'm probably going to have to spend a half-hour and a trip out of the house finding out that the answer was wrong. I'd rather get the answer in 5 minutes and for it to always be right. Dying in an accident coming back from a taco stand AI didn't know closed 6 months ago would be the worst death.
Minimally there needs to be a transparent split between commercial queries (searching to buy something) and knowledge / abstract queries (searching to learn something).
Users should be context aware (ideally using completely separate tools) of when they are simply accessing a pay-to-play online product catalog versus when they are querying what is effectively a decentralized wikipedia.
Commingling the commercial with the factual was always going to be a dead-end.
The creator can use the tool themselves and post it with ads. In fact, I'd prefer it.
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.
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
> 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.
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.
And again speculating, but given Apple's new emphasis on privacy, it might rhyme quite well to (1) make that into apple intelligence or even (2) make it fully local and, as a matter of principle, not dependent on external infrastructure.
The only thing they care about is ad revenue. Google created Chrome which vastly improved browser user experience. Google is a major participant in web standard & JavaScript language evolution, among other work. That's all true, but not necessarily because they "care about the web", but rather it helps their ad business. If people put the entire world's information on websites, and people spend more time in browsers, Google ends up earning more money from ads.
going from profitable to "we own gigantic yachts that supply our humongous yachts" aka jeff bezos money requires absurdly crafted insidious borderline evil marketing.
The reductio of this argument is that nothing can ever change or improve because if it was possible someone would have done it already.
More to the point, people who have used Kagi seem to speak favorably of it. A search engine you have to pay for is never going to be the mass market option, but it can have enough users to be self-sustaining and remain one of the options, and it proves it can be done.
I gave a thought on whether this could be some copyright issue with Amazon but didn't bother to check the robots.txt file, nicely done!
https://www.goodreads.com/quotes/11541816-few-hundred-years-...
The robots.txt seems to exclude things which are genuinely useful to exclude, like RSS feeds.
#/media/File:Pig_poster.jpeg){kind=link}
#/media/File:The_Menu_(2022_film).jpg){kind=link}
<meta content='noindex' name='robots'>
Search goes out of its way to hide why I want and show me bullshit shopping ads and influencer videos. The overview at least tries to help. For now.
But I will emphasize: it's still not that helpful, it's just less corrupted than the main body results are... so far.
I've been using kagi and I've noticed that the only time I ever switch to google is for things that are truly local to where I am at the moment (restaurants, etc..).
Kagi is really great.
I've also been testing perplexity and I'm not that convinced yet. The only thing it's been decent at is finding relevant studies.
https://pdx.su/blog/2024-12-29-using-kagi-for-a-bit-over-a-y...
I wish they’d setup something like Mullvad where you get an account number, pay for said account, and that’s it.
Kagi and mullvad make the same claims to privacy and non-tracking of accounts. What's the difference between a random numeric and a random alphanumeric account identifier?
Edit: actually I just remembered that my android devices are linked to my Kagi account with a token. Kagi gives you an alphanumeric token you can use in your query URL to authenticate searches. That's how my homescreen search widgets are set up, no email required.
That said, is anyone using the Google Search API to try to cut out a lot of the junk the author is talking about? How well has that worked?
A big difference here is that oprn source models are available, effective and checkpointed at this point in time!
Worst case scenario, we stop getting new open source models and are forced to query new, suboptimal models only for recent information.
(Or this is how I remember it)
The manual included with the game was also a very interesting and fun read - full of humor and quips about the game devs - even including a humorous piece on the main developer's baby daughter. Reading the manual made the game and the game devs feel so much more alive. I haven't played OMF in decades, yet I still remember most of their names - Rob Elam, Ryan Elam, the genius music composer Kenny Chou[1] and not to forget the baby, Bethany Kay Elam. Till date I wonder what she's is up to, and whether she's gotten over her habit of slobbering over the keyboard...
Personally, for me, OMF2097 was the definitive fighting game of all time. It's a pity that almost no one ever thinks of it, it's always either Tekken, Street Fighter, or MK. All great games, mind you, but they're nothing like OMF.
[1] Kenny Chou uploaded a remake of the OMF theme song a while ago, in case you weren't aware: https://www.youtube.com/watch?v=UvlVaQl7kEk
Users will need to learn that Google is only as trustworthy as the crappy websites it uses for data that drives its AI. I'll leave it up to you to work out how that might impact Google's brand.
My friend and I used to paste pre-AI Google search snippets to each other when they were so bad, especially when it quoted a comment on Reddit.
Doctolib in France (and Italy, Germany, Netherlands) is one such example. Founded in 2013 so decent life, still as good as in the beginning for both consumers (people booking healthcare appointments) and the customers (doctors paying to use it for their appointment management). And they're only getting better, with e.g. an AI assistant in beta to take notes during appointments.
Libraries themselves are a special thing - they've been invented before intellectual property was a thing, and have been attacked by IP proponents ever since. In this way, they're very much like LLMs, and many of the arguments against LLMs trained on copyrighted material apply just as much to public libraries. Oh the irony.
For Llama, I can just say "Are you sure?" and it will change its tune (unless it's quite "certain" about the results).
Qwen is more insistent, but will change course if I say "I looked it up and it says you're wrong".
You're telling me there's a modern frontier model that refused to ask clarifying questions after you told it to?
If you explicitly tell it not to search, it's less likely to anchor itself in trying to search the web and going down rabbit holes.
It also more likely to pause at times and ask the right questions to nudge.
(Hint: it is a film from 2021 starring Nicolas Cage.)
But it won't be functional, because Large Language Models requires far more samples than your private library, at least if you want it to do things that you couldn't solve with a much simpler deterministic search.
For example, usefully extending the document "Which book had the sarcastic one-armed antagonist?" with another sentence that happens to also be the answer.
I've occasionally thought to myself "once an idea is created it wants to be free," but in the back of my mind I've always had some sympathy for artist of any medium trying to profit off their talents or anyone trying to create anything and profit from their efforts.
The library comparison is notable, but a library has a limited, physical nature. They can only hold a finite amount of books, while anything digital can be replicated indefinitely.
I shouldn’t have to read 2000 words to make a cheesecake. And I shouldn’t have to read it three times before starting to make sure I combine the ingredients in the right order.
Even the good ones are often subtly wrong. For example, never add baking powder or especially cinnamon to wet ingredients. Stir them into the dry ingredients first, then combine. Otherwise they clump. With cinnamon it makes it look bad. With chemically reactive ingredients it can lead to insufficient rise. Who taught you people to cook? Obviously not grandma or PBS.
I see a lot of people blame “stale” baking powder and while that is a thing, mixing it in wrong or subbing oil for butter or not chilling (eg cookie dough) is just as likely a culprit.
My friend made two sheets of cookies from the same batch and the second ones were terrible. She left the dough on the counter while the first batch was in the oven. Rookie mistake. And she has adult children.
This reminded me that, rather hilariously, it used to be called expertsexchange.com before adding a dash (experts-exchange.com).
The economics of just giving the news with little bias just aren't there anymore.
Except given the noise/signal ratio and the sheer mass of information we have today, the workload is much higher than training for a 42 km run.
News is leaning more and more into entertainment.
You did have all of this before, but 24h news channel with empty content are reaching new magnitude, fox news types of outlet are getting bolder and bolder, manufacturing facts is now automated and mass-produced, consequences for scandals are at an all time low, concentration of power at an all time high, etc.
It was bad.
It is getting worse.
There's a simplified page for CNN news at <https://lite.cnn.com>.
I've found that frustrating as all the stories are jumbled together with little rhyme or reason (though they seem to be roughly date-ordered).
Ironically, the story URLs themselves include both date and news-section coding, as with:
https://lite.cnn.com/2024/12/28/us/patrick-thomas-egan-accused-tv-reporter-attack/index.html
It's possible to extract these and write a restructured page grouped by subject, which I've recently done. One work product is an archive of downloaded front-page views, which I've collected over about the past 5 days. Extracting unique news URLs from that and counting by classification we get a sense of what CNN considers "news":
Stories: 486
Sections: 27
76 (15.64%) US News
67 (13.79%) US Politics
9 (1.85%) World
8 (1.65%) World -- Americas
6 (1.23%) World -- Africa
15 (3.09%) World -- Asia
4 (0.82%) World -- Australia
5 (1.03%) World -- China
2 (0.41%) World -- India
37 (7.61%) World -- Europe
21 (4.32%) World -- MidEast
2 (0.41%) World -- UK
8 (1.65%) Economy
45 (9.26%) Business
4 (0.82%) Tech
3 (0.62%) Investing
8 (1.65%) Media
8 (1.65%) Science
7 (1.44%) Weather
4 (0.82%) Climate
22 (4.53%) Health
2 (0.41%) Food
1 (0.21%) Homes
39 (8.02%) Entertainment
52 (10.70%) Sport
22 (4.53%) Travel
9 (1.85%) Style
One element which had inspired this was that so much of CNN's "news" seemed entertainment-related. That's not just "Entertainment", but also much of Health, Food, Homes, Sport, Travel, and Style, which are collectively 147 of 486 stories, or about 1/3 of the total.
Further, much if not most of the "US-News" category is ... relatively mundane crime coverage. It's attention-grabbing, but not particularly significant. Stories in other sections (politics, business, investing, media) can also be markedly trivial.
Ballparking half of US news as non-trivial crime, at best about 60% of the headlines are what I'd consider to be actual journalistic news, and probably less than that.
On the one hand, I now have a tool which gives me a far more organised view of CNN headlines. On the other ... the actual content isn't especially significant.
I'm looking at similar tools for other news sites, though I'm limited to those which will serve JS-free content. Many sites have exceedingly complex page layouts, and some (e.g., the Financial Times don't encode date or section clearly in the story URLs themselves, e.g.:
https://www.ft.com/content/d85f3f2d-9e9d-4d92-a851-64480e56a248
-------------------------------
Notes:
1. For those interested, most readily accessed and parsed, the Vanderbilt TV News Archive (<https://tvnews.vanderbilt.edu/>), which has rundowns of US natinoal news beginning 5 August 1968, to present (ABC, CBS, and NBC from inception, with CNN since 1995 and Fox News since 2004). It's not the most rigorous archive, but it's one that could probably be analysed more reasonably than others.
What's happened is that the income of media outlets has declined to the point that most can't get factual accuracy even if they want it.
Or to put it another way, the media's accuracy rate has stayed consistent at some value less than 100%, but if all three TV channels reported the same information then it looked like they had 100% accuracy. Once there were more sources of information then it became apparent that the media's accuracy was less than 100% despite their protests to the contrary.
The result is that the media landscape is fractured. A person can live in a bubble where all of their news sources (eg NYT, WaPo, and Bluesky for one bubble; Fox, Newsmax, and Truth Social for another bubble) all report the same information, making their accuracy appear to be 100%, while any single source of information outside the bubble that disagrees with the bubble is disagreeing with a bunch of apparently 100% accurate sources and so can safely be discarded.
The solution is to realize that no source is 100% accurate or unbiased even despite genuine efforts to be. That isn't to say that some sources aren't more accurate or unbiased than others, but you should apply some base level of skepticism to any and every source
Instead of facts being unaffordable, it seems that lies and bias simply pay more (or at least the media outlets seem to think so).
I noticed a drop in traffic, despite having added a lot of valuable guides this year. The traffic per page is way down, and only for Google.
You are correct that people don’t pay for this, even when they email me and I personally assist them. There’s just an expectation that things on the internet are free and that’s fine.
Thank You For Making And Sharing :)
Prompting isn't necessarily the career some people wanted was sold as, but it's not a bad idea to practice a bit and build a sense of what a clear and effective prompt looks like.
-
To be clear, I get telling people it's a "you" problem every time an issue with LLMs comes up isn't helpful... but sometimes the disconnect between someone's claimed experience, and what little most people actually can agree LLMs are capable of is so great that it must be PEBCAK.
I just tried the original checkpoint of GPT 3.5 Turbo and it was able to handle drilling up and down in specificity as appropriate with the prompt: "I need you to help me remember a movie. Ask clarifying questions as we go along."
I had great results prototyping agents at work for specific tasks and answering in a specific style including asking appropriate clarification questions.
But at home with just free/local options? I've nowhere near the same settings to play with and only had very mixed results. I couldn't get most models to follow simple instructions at all.
There are plenty of revenue models aside from ads.
I kid, but also hope I'm wrong.
The issue is that they don't want to. They'd rather be a middleman offering you "useful recommendations" (that they or may not sell to the highest bidder) instead of offering you value.
Google operates the largest display ads network. They literally *pay* websites for SEO spam, and take a very healthy cut off the top.
I wish people would stop acting like Google has been in a noble battle against the spam sites, when those sites generate Google billions of dollars a year in revenue.
The obvious question is, why would they ruin search for display? The answer is greed combined with hubris. They were able to double dip for years, but they killed the golden goose.
Everybody with a brain knew this would happen when they bought Doubleclick, and it took longer than expected, but here we are.
It makes no financial sense for Google to give you good search results and get you off Google as soon as possible.
Instead, if they make you spend more time on Google due to having to go through more crappy results, they can sell more ads.
Most people won't change search engine and will stomach it.
Until ChatGPT happened and can save you the pain of having to use Googles search engine.
And I’m not saying this makes them useless: I pay for Claude and am a reasonably happy customer, despite the occasional bullshit. But none of that is relevant to my point that the bots get held to a different standard than Google search and I don’t see an easy way for Google to deal with that.
Sort of. Top results for any kind of question that applies to general population - health, lifestyle, etc. - are usually complete bullshit too. It's all pre-AI slop known as content marketing.
I think it's closer to a well spoken idiot.
> as long as information gets out there
A possibly incorrect summary of the information gets out there. Given how much nuance I weave into my content, and how much effort I put into getting the phrasing just right, it frustrates me to no end. There's a very high likelihood that AI could give someone an invalid answer _and_ put my name under it, surrounded by their ads.
You can't have that if Google is plagiarizing your site and delivering the info.
Websites are training data and will become an anachronism.
If I want to get my name our there - which I don’t - I’m going to post to LinkedIn, give in person talks at conferences, try to get on popular podcasts that have guests, etc.
You remember the pagerank paper? It described how Google classifies each page on a scale from "something that links to good pages" to "informative page". Google and other search engines produces links to the latter. And since then, web site operators have had strong incentives to be on the "informative page" end of the range. Today I don't think the 2000s code can find a lot of pages of the former kind (well, outside Facebook).
It produced very nice results back then. It was/is good code, but good results need more than just good code, it needs good input too.
ChatGPT with web search does a good job of summarizing content.
2) I took at look at the most recent CMS data[0] I could find (from 2022,) and out of the top ten owners of hospitals in the United States, zero are payers. I only recognize about half of the parties in the 11-20 part of the list, but of the ones I do recognize, one is related to a payer. I can find no data to support your assertion that insurance companies are purchasing hospitals. They are purchasing physician practice groups, but that only reinforces the dynamic I described where hospitals have to court physicians to drive patients to their facilities.
0 - https://aspe.hhs.gov/sites/default/files/documents/582de65f2...
To make sure I'm not misremembering, I've asked deepseek in web search mode: "Is it true that hospitals are increasingly owned by insurance companies in US" It says: "In summary, the ownership of hospitals by insurance companies is a growing trend in the U.S. healthcare system, driven by the desire to control costs and integrate care delivery. While this model offers potential efficiencies, it also raises significant concerns about the quality of care and the balance of power in the healthcare industry." I've looked at several links it provided and they are consistent with the conclusion. Try it for yourself.
I keep hoping my local university hospital system will offer such a thing.
I've made a mistake of consuming healthcare related content due to the recent ceo assassination. Do not recommend.
As for affiliate links, I think they are a thing of the past. It's exactly these that web users want to avoid. Better to make a deal where you charge the bank a fee for each person you sign up. There's a lot of banks who offer these referral deals to all their customers. For example N26 gives you €70 per referral and Wise gives £25 per referral.
You can probably make good money from your website from doing what you love. But ads and affiliate links and getting money from traffic is a thing of the past.
I’d much rather help a greater number of people for free than the well-off minority that can afford my time. I’d sooner run my business into the ground than change this.
I think you are thinking and operating in the old paradigm, thinking that somebody spending a few hundred dollars on getting expert help on the Internet is outrageous, even if it's a life changing spend. Would you consider somebody spending a few hundred dollars on expert advice in a fancy office to be outrageous? Then consider that your expertise is way higher. There's nothing wrong with you charging for your immigration services and expertise. And as I said, you can still offer as much information for free as you please. It's only better for sales.
Google does not owe you any traffic and they don't owe you any business income from affiliate links or ads. Zero. If you don't like Google using the information on your website that you are giving away for free, then it only takes a few minutes to remove your domain from Google.
You can combine giving information for free with getting paid for your work. But you can't demand that Google pays for that.
I bet you if you had insightful posts on HN (not saying you don’t) and people knew you, you would get more traffic by putting a link in your profile here than people searching on Google.
March 23rd 2023
https://openai.com/index/chatgpt-plugins/
That’s 666 days.
So you are off by over “one order of magnitude”
I subscribe to Ben Thompson’s writing and make it habit to go to a few other websites because they have earned my trust.
The only method that most people have ever had of gaining traction is via word of mouth and not through search engines.
No one owes you traffic or discoverability any more than they owed HuffPost or the other click bait, SEO optimized websites before the algorithm changes
Does Perplexity actually give you a clickable link like ChatGPT does?
Also probably why I get email from people visiting as it's one of the few places people can reference said info.
That was actually one of the main concerns of Larry Page back in the day, that the majority of Web's information might get and be locked behind walled gardens, paywalls or whatever else.
You’re complaining about “discoverability” which hasn’t been easy since 2000.
The most successful independent writer today is probably Ben Thompson’s “Stratechery”
https://stratechery.com/about/ https://blockbuster.thoughtleader.school/p/how-ben-thompson-...
Through organic search, you probably won’t find any of his free articles when searching for a topic on the first page. He had to put in the work over years and couldn’t depend on Google.
I can assure you that force is strong with me.
I was using searx instances with reasonable results but many of them started failing recently.
Anyway, I hope everyone finds a good one. I fear things will only get worse though.
I posted an analogy about the dynamic that exists between hospitals and doctors. You responded by saying that's a distinction without a difference, when the dynamic I described is a primary difference between the two groups: doctors can practice medicine without hospitals. Hospitals cannot provide patient care without doctors.
I'm not ignoring anything. I posted an analogy about how the US hospital business has some similar incentive structures as Google's search business, in that both are dependent on third-parties to deliver revenue. You, for reasons that are not clear to me, felt the need to post an unhelpful, off-topic, and incorrect rant about the insurance system in the US backed up, apparently, by nothing more than your favorite AI hallucination engine.
I don't think you've even tried to understand what I posted or why, nor do I think you are capable of understanding why your claim is completely irrelevant to what I wrote. Guess what? Even if insurance companies purchased every single hospital in the country, those hospitals would still be dependent on the doctors to operate.
Back in the day, if I wanted the answer to some specific question about, say, restaurants in Chicago, I'd search for it on Google. Even if I didn't know enough about the topic to recognize the highest quality sites, it was okay, because the sorts of people who spent time writing websites about the Chicago restaurant scene did know enough, and they mostly linked to the high-quality sites, and that was the basis of how Google formed its rankings. Word of mouth only had to spread among deeply-invested experts (which happens quite naturally), and that was enough to allow search engines to send the broader public to the best resources. So yeah, once upon a time, search engines were pretty darn good at pointing people to high quality sites, and a lot of those quality sites became well-known in exactly that way.
My first post was on Usenet in 1994 using the “nn” newsreader
The web has gotten much larger than when it didn’t exist when I started.
But web rings on GeoCities weren’t exactly places to do “high quality research”. You still had to go to trusted sites you knew about or start at Wikipedia and go to citations.
Before two years ago I would go to Yelp. Now I use the paid version of ChatGPT that searches the internet and returns sources with links
What you say has been around for a few weeks has literally been around for paid users for over a year
Google very much can crawl information on Facebook and Instagram that people have made “public”
As far as “social dynamics”, do you remember Cambridge Analytics? Why would I want my social graph to be publicly available.
It’s bad enough that people have their contacts synced with Facebook.
Google AI responded: "To lose weight, men typically need to reduce their daily calorie intake by 1,500 - 1,800 calories"
Which is obviously dangerous advice.
IMO Google AI overviews should not show up for anything (a) medical or (b) numerical. LLMs just aren't safe enough yet.
But maybe I'm just weird. Oftentimes when my wife or kids ask me a question, I take a deep breath and start to say something like "I know what you're asking, but there's not a simple or straightforward answer; it's important to first understand ____ or define ____..." by which time they get frustrated with me.
Funnily enough, this is exactly what the LLM does with these questions. So well that people usually try to tweak their prompts so they don't have to wade through additional info, context, hedging, and caveats.
Obese people can lose a bit more under doctor supervision. My understanding is that it’s tied partially to % of body weight lost per week and partly to what your organs can process, which does not increase with body mass.
So for example if your weight is stable at 2500 kcal per day, I would start by reducing the intake by 250–500 kcal, but not more. If this works well for a month or two and then you want to lose weight faster, you can still reduce your intake further. You generally have to do that anyway even just to maintain the velocity, because weight loss also tends to reduce calorie expenditure.
First and foremost, you need to monitor your calorie intake against weight. Here is a useful text about that: https://www.fourmilab.ch/hackdiet/
I get a pretty good summary when I paste the question into Google. It comes up with a ballpark but also gives precautions and info on how to estimate what caloric restriction makes sense for you within the first 3 sentences.
And all in a format someone is likely to read instead of clicking on some verbose search result that only answers the question if they read a whole article which they aren't going to do.
This seems like really lame nit picking. And I don't think it passes the "compared to what?" test.
But I wonder, were those few words the full response? Information hiding to prove a point is too easy.
Same advice as my trainer gives me.
reduce their daily calorie intake to 1,500 - 1,800 calories
or
reduce their daily calorie intake by 1,500 - 1,800 calories
[0] Note that the robot suggested to reduce calorie intake by 1,500->1,800 calories, and the recommended calorie intake is 2,000.
I asked this about 1 minute after you posted your comment. Perhaps it learned of and corrected its mistake in that short span of time, perhaps it reports differently on every occasion, or perhaps it thought you were a rat :)
The median lethal dose (LD50) of caffeine in humans is estimated to be 150–200 milligrams per kilogram of body mass. However, the lethal dose can vary depending on a person's sensitivity to caffeine, and can be as low as 57 milligrams per kilogram.
Route of administration
Oral 367.7 mg/kg bw
Dermal >2000 mg/kg bw
Inhalation LC50 combined: ca. 4.94 mg/L
That’s half the people in a caffeine chugging contest falling over dead. The first 911 call would be much much earlier. I doubt you’d get to 57 mg before someone thought they were having a heart attack (angina).
--
The median lethal dose (LD50) of caffeine in humans is estimated to be 150–200 milligrams per kilogram of body mass. However, the lethal dose can vary depending on a person's sensitivity to caffeine, and can be as low as 57 milligrams per kilogram. Route of administration LD50 Oral 367.7 mg/kg bw Dermal 2000 mg/kg bw Inhalation LC50 combined: ca. 4.94 mg/L The FDA estimates that toxic effects, such as seizures, can occur after consuming around 1,200 milligrams of caffeine.
There was a table in the middle there.
Maybe the argument is that if you turn off the randomness you don’t have an LLM like result any more?
In the most concentrated form in typical commercial caffeine tablets, it's half to one fistful. In high-caffeine pre-workout supplements, it's still a quantity that you'd find almost impossible to get down and keep down... E.g. a large tumbler full of powder of mine with just enough water to make it a thick slurry you'd likely vomit up long before much would make it into your bloodstream...
I'm not saying it's impossible to overdose on caffeinated drinks, because some do, and you can run into health problems before that, but I don't think that error is likely to be very high on the list of dangerous advice.
Also, in what context is this dangerous? To reach dangerous levels one would have to drink well over 100 cups of coffee in a sitting, something remarkably hard to do.
some people use caffeine powder / pills for gym stuff apparently.
someone overdosed and died after incorrectly weighing a bunch of powder.
doubt it is a big leap to someone dying because they were told the wrong limits by google.
https://www.bbc.co.uk/news/uk-wales-60570470
as ever, machine learning is not really suitable for safety/security critical systems / use cases without additional non-ML measures. it hasn’t been in the past, and i’ve seen zero evidence recently to back up any claim that it is.
For my high-caffeine pre-workout powder, I suspect I'd vomit long before I'd get anywhere near. Pure caffeine is less unpleasant, but still pretty awful, which I guess is why we don't see more deaths from it despite the widespread use.
I agree with you that there really ought to be caution around giving advice on safety-critical things, but this one really is right up there in freak accident territory, in the intersection of somewhat dangerous substances sold in a poorly regulated form (e.g. there's little reason for these to be sold as bulk powders instead of pressed into pills other than making people feel more macho downing awful tasting drinks instead of taking pills).
> The hearing was told the scales Mr Mansfield had used to measure the powder had a weighing range from two to 5,000 grams, whereas he was attempting to weigh a recommended dose of 60-300mg.
Nothing to do with an LLM nor with someone not knowing the exact LD50 of caffeine. Just "this article contains someone dying of caffeine overdose, and we're talking about caffeine overdose here, therefore LLM is dangerous."
At 200mg per pill, which is the strongest I had, I'd still have to down some 70+ pills in one go. Not strictly impossible, but not something you could possibly do by accident, and even for the purpose of early check-out, it wouldn't be my first choice.
A 500lbs man will need to consume 4000kcals/day to not lose weight. Cutting 1800 of that is realistic and might be good advice on the LLM's part, so it really depends on how GP asked the question.
The argument is, as you suggest, that without randomness you don't have an LLM-like result any more. You _can_ use the most likely token every time, or beam search, or any number of other strategies to try to tease out an answer. Doing so gives you a completely different result distribution, and it's not even guaranteed to give a "likely" output (imagine, e.g., a string of tokens that are all 10% likely for any greedy choice, vs a different string where the first is 9% and the remainder are 90% -- with a 10-token answer the second option is 387 million times more likely with random sampling but will never happen with a simple deterministic strategy, and you can tweak the example slightly to keep beam search and similar from finding good results).
That brings up an interesting UI/UX question.
Suppose (as a simplified example) that you have a simple yes/no question and only know the answer probabilistically, something like "will it rain tomorrow" with an appropriate answer being "yes" 60% of the time and "no" 40%. Do you try to lengthen the answer to include that uncertainty? Do you respond "yes" always? 60% of the time? To 60% of the users and then deterministically for a period of time for each user to prevent flip-flopping answers?
The LD50 question is just a more complicated version of that conundrum. The model isn't quite sure. The question forces its hand a bit in terms of the classes of answers. What should its result distribution be?
Found an article about a teenager who died after three strong beverages. The coroner is careful to point out that this was likely an underlying medical condition not the caffeine. The health professional they interviewed claims 10g is lethal for “most” people, which would be 100-150mg/kg. That still seems like something an ER doctor would roll their eyes at.
And if on purpose, using caffeine would just be staggeringly awful...
it’s intent (want to improve my gym performance so down a bunch of caffeine) combined with incorrect information gained from what is supposedly a trustworthy source (the limit presented is much higher than it actually is for humans).
I use LLM to help with training data as they are great at zero shot, but after the training corpora is built a small, well trained, model will smoke an LLM in classification accuracy and are way faster - which means you can get scale and low carbon cost.
In my personal opinion there is a moral imperative to use the most efficient models possible at every step in a system design. LLM are one type of architecture and while they do a lot well, you can use a variety of energy efficient techniques to do discrete tasks much better.
And, yes, purpose-built models definitely have their place even with the advent of LLMs. I'm happy to see more people working on that sort of thing.
https://en.m.wiktionary.org/wiki/ideal
(We’re allowed to imagine the impossible.)
