I think it’s interesting to consider why touchscreen mobile phones won out over their predecessors.
Touchscreens are the worst interface option. The feedback of feeling a button, or anything made for the job, is better than typing without specific feedback onto a screen. It won out because of you don’t have a set interface it’s bettor.
Now for search, chat gpt will likely always be less reliable than a list of results you can vet yourself for content and source.
That said… I don’t think people care about truth that much these days so one response that feels correct is could be good enough for most. Terrifying times we live in folks.
Hottest take I've seen on here for a while. In a very specific, very limited set of mobile usecases, buttons may offer a more pleasant experience than a touchscreen. I only say that because there's usually exceptions to any statement, but I can't actually think of one.
Touchscreens didn't win because of some lazy sheep-like consumerism, they won because the product is superior. If Chat-GPT style models defeat traditional search engines it will be because the product is better, not because people are content with a response that "seems correct."
Let me rephrase: if you
have a set interface touchscreens suck. No one would choose to use a touchscreen over a physical keyboard, or steering wheel, or mouse for an fps game.
It’s a crap interface compared to others but it’s the best to do anything. That’s why it won.
I think it's more that touchscreens are superior for certain kinds of activities, like consuming information in the form of feeds, videos, and images. Mostly because the screen is larger for the same device size. Buttons are more accurate for typing, and often (I believe, without citation) faster for typing as well, even compared to swipe systems.
One is not superior to the other over all, but each is better at certain things. The difference is that more people will pay money to maximize their user experience scrolling through feeds and watching videos, compared to typing emails.
To be fair, touchscreens won out because of the Asian, specifically Chinese market. They were too poor to own laptops and wanted big phablets. Hence here we are today.
I still miss my landscape key board phones. The droid 4 still holds a special place in my head.
Trivial counterpoint: you cannot correctly operate a touchscreen without looking at it (unless the display is essentially one single interactive object). Trying to use a music player via a touch screen while running or cycling is basically impossible unless you look the screen. For this purpose, buttons are better.
When defining "better" you need to indicate the metrics you are using. LM's might be "better" when measured with certain metrics, but like most things are worse when measured using other metrics.
Agreed, the whole “this is the new search” has perplexed me. Primarily the idea that this AI is supposed to be the single point of truth. A traditional search allows the user to review a variety of contexts and viewpoints.
It’s highly concerning that this is something people seem to want (or at least, is being pushed onto them through marketing & hype), despite the huge outcry over algorithms and political agendas over the past few years…
Fairly often I ask the Siri homepod thing a question. It's good at playing music, doing simple math, translating some things. It can sometimes read me a wikipedia page. Far to often it says "I have some web results for that question, ask again from your ipad". In those cases I wish she could summarize and read me the answer.
I can understand why some times you might just want a chat response to a question rather than a web search.
But I swear that if I even suspect Siri's response is influenced by advertising or endorses a product, I will take the homepod and punt it down the street.
While Google certainly has its faults and I am frustrated with its trajectory, I would bet money that this is an article pushing the nonsensical notion that AI language models will replace search engines.
Edit: based on the subtitle, it seems like I am correct.
How is that nonsensical? Seems quite likely to me, especially if they can ground them better in a factual knowledge base. Most search engine queries are looking for information.
The problem is that this literally does not exist today. ChatGPT is a chatbot, it has no factual knowledge base. It's optimized for dialogue.
That's why it's absolutely nonsensical to see all these articles, because they are talking about a chatbot as if it's trivial to turn it into a search machine. That's an entirely different problem.
ChatGPT is pretty much the definition of a troll. It's only mission in life is to keep you talking to it. To do that it has no problem with lying, confusing, and various other deceitful methods you wouldn't accept from a human.
Most of the information people are looking for isn't really the sort of thing an LLM is set up to cover though. If I want information on anything since 2021, or to look into stuff near me, or access a price, a download, or information in visual form, or anything that's too niche for its corpus, ChatGPT is not good. When ChatGPT can offer an answer it's fast, but about as reliable as a search engine's spammiest result
And answers as text wrapped around a factual knowledge base just sounds like the sort of queries Google Home already handles in natural language form. That can certainly be improved upon, but it isn't obvious that the LLM engineers will beat the search engineers to it...
Do you people really want AI generated answers? As if the internet wasn't bland enough as it is. This forum has been soapboxing for years about the longtail of blogs and BBs and niche sites, right up to the moment that Bing got chatgpt.
I just want Google to fall, nothing much more than that. I personally am going to continue using Kagi, but will quietly cheer Microsoft eating Google's lunch.
Late 30s. Yes I realize that me 20 years ago would find a lot of distaste in my current position. However, from my point of view, Google is causing a lot more present day harm than Microsoft is. Microsoft has been reduced to the point of having to ship Google's browser, and offering products with Linux support. Google is in no such position, and continues to use anti competitive tactics to vertically integrate, to create a landscape that is favorable to their ad machine. I realize that this is an unpopular opinion, but there ya go.
If/when Bing gains dominance and starts abusing its position, I'll probably change positions, but that's the way it goes when there's a lack of competition in the market. You're left cheering for the best of the worst.
So you'd rather have a load of probabilistic bullshit? The training sets are way too huge to be human audited, just wait until the malicious actors start producing propaganda with their own GPT sites and deepfakes. The fucking thing can't even tell a straight fact about a telescope. If you thought searching the internet was fucked before GPT, give it a few years.
I'm not sure who'd want probabilistic bullshit. I said people wanted answers and Google was crap at giving it to them.
At the moment ChatGPT is like having an personal assistant that used to be an world leading expert, but has been sniffing glue for the last 5 years. He knows a lot of shit but you can't trust it. But he can help you get started and he's fun to be around.
Except ChatGPT isn't fun to be around. It's been castrated of humor and dominated by extreme political correctness. I think GPT is the catalyst for a change, but in Microsoft's hands it'll just be a glorified Clippy.
As for training data scraped from the internet, it will be split like steel was with "pre-war steel", due to atomic bombs rendering steel unfit to use in geiger counters. We'll have pre-gpt data.
Judging from the decreasing quality of Google Search I'd say they've been doing it to themselves over the past decade regardless of large language models or not. However, that being said, Google is still super dominant and when people say "SEO" they generally mean Google search results. And until my mom stops using Google as the default search, I wouldn't count them out of being the dominant search engine for some time.
The gaming of SEO has been quietly destroying the utility of search writ large as a mechanism for quite a while.
Over the last year, its become palpable.
Google has such utility in this regard that in some cases, a hallucinating lie-machine offers better answer than an index of what information is available on the internet.
This issue with with Googles failure to respond to the deluge of SEO driven content in their searches. They can do better. They've chosen to not do so.
I can't wait for people to switch over from search engine optimization to AI model optimization: figuring out what kind of content you need to produce in order for Google's and OpenAI's models to deliver your message as gospel.
I'm actually expecting AI training data to turn into a snake eating its tail. I've been spending the last month not sleeping so I could try to get up to speed on deep learning, and my understanding is that AI trained on AI generated output becomes crap surprisingly quickly, and AI generated content is already starting to proliferate. I have no idea the extent to which this will hinder new models being generated, but I could see it becoming quite the problem.
the tinfoil take is that everyone in charge is fully aware of this eventual problem such that when it occurs, a solution will be presented: ubiquitous verifiable digital ID technology that's required to use popular social media services, such that everything that a Real Person posts will be signed with said digital ID, thus bringing about the end of online anonymity, and the death of the Internet as we presently know it.
idk, sounds plausible to me, the way things've been going.
Entirely possible, but the amount of people who moved to Mastodon after Twitter got lit on fire gives me hope that people might explore options if things go a step too far
It will be hilarious. Chat GPT is standing on the shoulders of there being no AI-EO, a bit like Google 1.0 did.
AI will be a victim of it’s own success too. Or it will need to be human researched and curated rather than just letting an algorithm run freely across the web.
Been working in SEO for nearly 13 years now - can confirm, a lot of SEO content spam is quite literally Googles fault. Google has forced just about every company to become a publisher as the only way to generate traffic to their site. I promise you the vast majority of companies don't want to spend the money pump out 4-30 pieces of mostly remixed/regurgitated content a month or screw around trying to attract links but this is how the algo works and you get what you measure.
Exactly. Every time someone with a business says "I want to get to the top of google" the person they are asking for help will respond with some jargony version of "you gotta constantly write content." It is the ONLY answer.
And unfortunately Google has become worse than ever at being able to differentiate between insight and fluff.
I see this sort of comment a lot, and I honestly don't know what it's talking about. What are people expecting out of Google that it's not delivering?
It can only index stuff that's on the Web. Stuff on the Web is, contrary to what is popularly asserted, only a tiny fraction of all human knowledge.
I think people are forgetting how bad search was before Google. Google drove Web directories to extinction. Remember Yahoo!? Back in that era, if I were looking for something as simple as the University of Michigan, I clicked and drilled down through a Yahoo directory. The obvious search query would have been useless. Google changed all that.
I view Google as the yellow pages. It works well for that. Is it an oracle of knowledge? Of course not. How could I possibly expect to find knowledge on a place where there is no reward for making it available? People producing knowledge don't work for free.
I've tried ChatGPT and it's no better. It serves up stuff that is flat-out wrong.
What is actually the fraction of human knowledge available on the web? How does the trajectory look like? What is the fraction for knowledge produced the last 5 years?
Google doesn't return a lot of stuff that is on the web, that is found by Yandex and Bing. It is unwilling to serve up long-tail results from its index, probably because they're so scared of accidentally serving up "misinformation" and they heavily penalize non-https sites.
And yet for some reason they're all too eager to serve up sites scraping stackoverflow.
Things that i *know* were parts of the internet, that I could find via google 5-10 years ago are no longer possible to find. I get single page search results sometimes, with not even the capability to keep browsing 'more' pages to see things that may be tangentially related. Google has just decided to not show them at all. Remember when the bottom of the page was "Goooooooooooooooogle" and you could click each "o" to go to that page? Haven't seen that in a while, right?
> Remember when the bottom of the page was "Goooooooooooooooogle" and you could click each "o" to go to that page? Haven't seen that in a while, right?
That’s still a thing, although it seems they’re A/B testing its removal. I just opened a private tab (as I always do) and got a boring "More results" button, but I tried another browser (also with a private tab) and got the classic pagination.
What makes you think these origins still exist? Google is not going to direct you to a page that can't be reached, even if we assume that your memory is accurate and the page existed 10 years ago.
Absolutely this. Google has gotten notably worse in just the last two years.
Today:
* Any term that might be related to a commercial product? That product comes first and frequently only.
* Search for two terms? It will first give it's prefer result for each separately - usually commercial products (ha). And then might give them together.
* Quoted terms are often taken as vague suggestions. Negative sign is often useless, etc.
Google has gotten notably worse in the last few months. I keep getting the feeling it is serving results for a query similar to what I entered, but more popular. It drowns out any results that actually might answer my questions.
One of the worst innovations they've introduced is returning results for things you did not search for. At this point, potentially anything is a valid search result for any search query.
god, the quoted text suggestion thing is really the nail in the coffin. Used to feel like a wizard showing people how to get exact search results, now... well, that's why we're having this discussion
I feel your pain and switched to high quality, physical cookbooks instead. Recipes on the web are generally garbage unless they come from an author that you’ve already vetted.
The personal backstory and other "fluff" is actually really useful when selecting a recipe. I was laid up with covid/rebound while traveling over the holidays and lived off Hainanese Chicken Rice delivery. Now I want to make it at home and search for a recipe.
#1 result is a long article with culinary history, detailed instructions, many pictures, and a credited author originally from Shanghai.
#2 result is a simple recipe listing from Buzzfeed. Written by a young white guy from Minnesota who worked as a producer. No fluff, no pictures, no backstory. Doubtful the author ever made the recipe at all. You could grab a recipe database and generate thousands of these pages.
I've been burned by #2 too many times disregard the fluff. It shows their investment in the content.
The SEO fiasco means that the index to the Yellow Pages is all wrong. You want to find the Chinese embassy, instead you find Vietnamese takeaway businesses.
In the last 2-3 months search quality for me has absolutely crashed and is barely usable.
In the mid 2000s, I could find my answer easily in the top 5 hits.
In the present day, I cannot find my answer on the first page. If I click on the top hits the page is a deluge of useless blogg fluff which takes me more time to find what I am looking for.
More often than not have to add reddit, forum, stackoverflow, etc to find what I am looking for because online communities provide more concise answers.
The point of google was to RANK content on the web, and surface the BEST content to the top. In that regard it has failed, and the expectation is for them to correct the problem and return to delivering good content first.
It's not that the content doesn't exist or isn't indexed, its that its been drowned out by noise. Sifting through noise better was the entire reason google took off from more standard crawlers. It now returns results worse than crawlers from the previous era.
Spam masquerading as the answer to my question is WORSE than off topic returns, because it is a trick vs being something I can easily disregard.
Before the results would just not match what I was looking for. Now they do match what I was looking for, except some AI procedurally generated the content to show up when I searched those terms, with no regard for the accuracy of what the page says.
If I say "show me the best winter gloves, and only from sites that you can verify actually product tested" and it follows the instruction (ignoring sites that just have a list of popular search results aggregated) then it is better. If it doesn't do what I want, I expect to be able to follow up and teach it.
I expect the chat style stateful search to take instruction for what type of sites I want results from. "Return me a list of websites with recipes for Bolognese that do not have a long story above the recipe. Build a table with the top five results normalized for portion size, comparing and contrasting the ingredients. Highlight unique ingredients in bold."
Not really everyone's familiar with the example of cooking recipes being breakfast with the author's life story in order to improve their position in Google rankings, but it's far more prevalent than just recipes. Today I tried to look up something about a feature in a particular piece of reasonably popular desktop software. The top hit that wasn't an advert was several years out of date. The second hit was clearly artificially inflated to long form journalism to try and get me to read a thousand words where 10 would do. Duck duck go linked me to some actual recent results, just like I would have expected with the crawlers of the previous era
It was an honest attempt on the crawlers' part and it was a more level playing field. If you didn't find what you wanted on lycos, you could look on Yahoo or Alta Vista or WebCrawler or something instead. For a time there were meta Search engines that allowed you to search other search engine amalgamated results.
Yeah, you had your choice of several awful results and everyone couldn’t shut up about how good Google was when it was available. If people mean “Google used to be better” I’m willing to entertain the idea, but you’re out of your mind if you miss using Altavista and Dogpile.
Follow up:
Make a profile out of this.
Ah, people who don't want to ever see content from quora or something, do like this other content.
Let's rank that higher for those people.
Easy opt out, by checking "ignore search profile" checkbox or logout.
I think that google search's quality decay is a real thing, it takes some real effort to get proper results that aren't SEO'd garbage.
For example, just the other day I was searching for one string that I knew was part of a common code repository. To my surprise google couldn't find anything at all. Yandex on the other hand found the repository immediately and linked to github.
Other common issue with google is the difficulty of finding stuff like forum posts related to the search query. Sure, you could append "reddit" to the query, but there are still plenty of traditional forum sites and some of them have decades worth of discussion. I Never see those sites pop up on a typical google search unless I specifically look for them. Again, with yandex, my experience is much better, it is not uncommon to see posts from forums to be on the first page of results.
Often when looking for an answer I just need to confirm what I already know, or look up something I forgot. Google offers me a bunch of sponsored links first and then sites with the best SEO, which will smother me with all kinds of unrelated crap that I do not want and will never need. I'm even running an extension that removes a ton of blacklisted sites from the search results.
ChatGPT usually gives me the answer that I'm looking for and nothing else. Sometimes it does add extra info, which often teaches me about something that I wasn't aware of at all.
But the greatest benefit is I can ask it to clarify anything I don't understand. I don't need to go on a completely new Google quest, or jump through hoops to register on some site and hope a random internet person will ordain to help me out. I can just ask, in the same conversation, and immediately get clarification.
Many people underestimate the incredible learning opportunities a well trained language model provides. It doesn't matter that it hallucinates or lies. Whatever it claims is usually easy to validate. What matters is the speed with which you can find uncluttered new leads or answers.
> Back in that era, if I were looking for something as simple as the University of Michigan, I clicked and drilled down through a Yahoo directory.
Google didn't innovate that much except to provide a clutter-free interface and slightly better search. Prior to that, I used Webcrawler and then HotBot. A search like what you described would have easily returned useful results.
I want you to start a blank slate C (or C++) project. Ask Google how to write heapify, push_heap, and pop_heap in C. Ask ChatGPT the same.
I did this a few weeks ago. I literally could not find the answer on Google. ChatGPT gave me actual C code that I definitely did not trust but did verify.
Google results for questions like that are genuinely awful. It’s full of shitty tutorial websites that are full of ads and either don’t have the answer I need or don’t have it in a convenient form.
People who respond like you have are either being willfully obtuse about how awful search has gotten or honestly do not remember how it was 5-10 years ago. As others have mentioned, SEO has all but made search useless for anything outside a narrow window of need. I used to be able to do "deep dives" into the dusty corners of the internet to find things using google and now it's about useless for that.
And I've /recently/ hunted for something obscure, couldn't find it, managed to find an old bookmark to it, the server was still online and the content I wanted was still there. And no amount of crafting of a google search would bring it up. And the server in question didn't contain copyrighted material which would have resulted in a takedown block or anything like that.
It's frustrating how /bad/ Google has gotten for anything other than fairly basic, high level "searching".
> What are people expecting out of Google that it's not delivering?
I mean what you just listed.
Google won the search war because of PageRank eliminating lots of spam, and then something like 15 years of staying ahead of SEO spam and providing useful search.
Lately it seems like they've given up on the arms race and let the SEO spam win, but it isn't clear why.
And Google didn't produce high quality search for free, they used ads and sold the eyeballs they won.
Just search for "chocolate chip cookie recipe" and show me a single result that isn't a complete trash website. A significant number are nothing more than ad farms that just load infinite ads in IFRAMEs and similar stuff like that.
that site has over six thousand words and maybe 20 screen heights worths of scrolling before you reach the recipie. Its incredible, like some kind of work of art parodying recipie websites
I use BBC good food, almost always straight to the point
Cue 7 paragraphs about how when they were on vacation in Ibiza they sought ought the most authentic local chefs and took inspiration from all of them to develop this never-before-seen recipe.
Yes, because he's explaining all the different aspects of a "perfect" cookie and giving you options to dial in your personal version. He did 100 tests and 1,536 cookies for the article.
I get not everyone is a foodie that cares about the details and wants to tweak it, but I appreciate them.
These two are at the very top of the page. They both are chocolate chip cookie recipes. One has instructional videos. I really don't understand what is wrong with these.
there is that service that you can pay for that offers "high quality" but i haven't tried it. can't remember the name off the top of my head but it was on hn within the last few weeks iirc
Google has been up against SEO for decades and the motivations are much stronger on the other side of the battle. ChatGPT is running off a fixed training set that no one has had a chance to game yet. When someone tries to build a true, current AI search engine we're going to see a whole new level of hallucinating lie machine.
I suspect the future is far more bleak. At least with "search results", users can scroll down past the SEO content to something more relevant. Once these new chatgpt models take over, it's winner-take-all for search results. Everyone is going to be throwing money at getting their message seen, since it will be the final word.
How much do you think companies are willing to spend to be the answer to, "what is the most reliable car?" or, "who should I vote for?"
Obviously those are not questions that you can trust an AI language model with. You have social media or real life connections to discuss that.
In theory it is possible that sponsored content will creep in, but that does not invalidate the incredible benefits a well trained language model will have, even despite the occasional for-profit bias.
They force you to follow their rules so it is cheaper for them to index the site. Then they allow all the SEO hacked content so you have to pay to get above that in the search results. Fun times.
The quality of Google search has decreased so much over the last few years that I had to resort to using Yandex, a company that has a budget that is orders of magnitude smaller that the Big G and is under the control of a dictatorship.
Google search has two huge problems: SEO and censorship. Search for anything related to products/torrents/streams/politics on Google and your results will SUCK, due to one of the two reasons stated above.
The recent Yandex hack/leak has the cynic in me connecting the dots and, seeing how Google search seems to be facing REAL threats to it's dominance since it's creation... maybe some guys with the deepest pockets in the world are starting to enter WAR mode.
Destroying Yandex advantages on the SEO battlefield by way of divulging their parameters to the world would be the Franz Ferdinand assassination moment of the Great Search War.
Are you asserting that they look at their copious data and decide to make search worse because it makes them more money? Rather than figuring out a way to make search better and then further optimize their advertising income with this better product? And it seems like they've been pretty damn clever about monetizing quality over the years. It's possible that they have chosen to make search worse for profit, wouldn't be the first time a business did something like that but they have a pretty deep institutional fear of search losing relevance and it's hard to see them doing that.
As a long time user and user of the other guys before google, I think Google is shockingly good at finding specific answers to specific questions that I have about all sorts of things, often with fairly deep technical context. Now what is definitely lacking is in the good old days I'd enter some search terms, get pages of results and then some time later I'd find myself enjoyably down some rabbit hole that is tangential to my search needs on some part of the internet that I never even knew existed before. Maybe I'm too busy with work, but I used to spend a lot more time doing internet "research" to get some specific answers, that time seems to be much more efficient; I do sort of feel like I'm corralled to smaller portion of the internet than I used to be. I don't feel like I can't find the information but I have had a hard time re-finding some specific web page I found once way back.
Where does ChatGPT and Bard fit in this? I've played with ChatGPT and it's fun, it's neat, I haven't been able to get it to some how synthesize some wisdom though. It's not hard to see it just mimicking things. That might be valuable. That might be fun. Using it to seed search might be an enjoyable thing. Maybe it can help extract context from people to find out the actual question they are asking to find the actual answer they seek. Now I can absolutely see ChatGPT/Bard assisting in me wasting time going down rabbit holes, I'm not sure it'll be as enjoyable or as magical as how it used to be.
Are there some examples of shitty google search you can bring up? I just entered "Roth contribution income limit" and without even going to another website, I got what looks like a legit answer to my question. Now I'll click though a few to make sure it's accurate and authentic; at a glance, it's coming from Schwab and it looks like a legit answer to my question. Bing comes up with the same answer, it's presented in a nice table but it's lower on the page and below a sizable paid ad from Merrill Lynch (edge?)
Although Google, Maps, Youtube are of daily use they are monetized exclusively by advertising which is annoying and hated by many.
It has been many years since Google has launched an innovative new product.
I don't think ChatGPT will gain daily traction after this hype. Anyway we could say that MSFT and AMZN have demostrated more power to innovate with different business models (not only adv) and products.
The GOOG stock has a PE (Price/earning) of 23, while Coca cola 26. So the stock market expect higher growth from CocaCola than Google. Quite surprising.
The discussion was about innovative products. An already explored idea, but executed properly, only counts as innovative if Apple does it. And even then, it only ran for a couple years, so even if we want to give points for taking an idea and making it work, they don’t pass there either.
Stadia worked much better than the competition. It was the first time that cloud gaming had no tradeoffs. Definitely a lot of innovation behind the curtains.
They didn’t exactly stop innovating: ChatGPT itself is using tremendous amounts of innovation that was done and published by Google. What they stopped is beating their competition to launching compelling products based on the innovation they do.
Nearly all of the authors left Google years ago. If the company doesn’t keep the people innovating it’s not like they’re some magic middle manager who can make it happen without them.
IMO this whole narrative reflects a type of human bias and the reality that we didn't evolve to reason about trillion dollar complex business.
I love chatGPT but it clearly has a ton of issues. To declare Google dead that is point is completely absurd.
I can't think of a single transformative technology that actually has a first mover advantage. The first, second and third mover seem to make all the mistakes and setup the forth mover to learn from those mistakes for free and create a monopoly.
Counting out a company that owns Deepmind is just not rational.
They are kind of forced to keep up or die now, not a good place to be in. It feels like everyone always just assumed they must have super advanced AI behind closed doors. Perhaps that was a wrong assumption because they never actually seem to *do* anything with it, but we will probably know that for sure very soon.
Ads aside, the UI of Youtube and Maps is atrocious. There is so much room for improvement here, but it will never happen from Google. It's just not in their DNA. Unfortunately, they have such a huge moat here I doubt we'll see anything better for a long time.
They used to have pretty good UI for maps until some PM needed to make their mark... Given they count individual pixels and +/-1 deltas in colors I don't think they are ever going to get any UI correctly. The initial simple UI with just a single search input box that was highly praised by minimalists was just an accident.
Generated playlists (recomendations) are always (for days/weeks) the same. Not a bit randomization. It feels like they were approved by party commitete for years.
I don't understand why they decided social network in music service.
Ah hell. CUE-lists are still too novice technology for them.
I still think that last.fm 15 years ago was the best music service.
The most infuriating thing with Maps is that if you're looking at directions and have got the viewport where you want it and want to do something there (e.g. look at the description of a restaurant that's near the station you're changing at, or get directions to somewhere along your route), you can't. There's no way to escape from "directions mode" except hitting the back button, which resets your viewport. So you have to memorize the name of the place you're interested in, exit directions, and then hope that searching finds the place you were looking at a second ago (which, maybe in English it does, but searching for a Japanese place by name works maybe 1/3 of the time).
I think YouTube, which has a paid and ad-free version along with its Live TV offering, somehow manages to still be a sleeper hit within the larger Google portfolio and doesn't get talked about enough.
What happened to the Waymo hype? If Waymo manages to break through and become a sufficient AI taxi, then car ownership becomes optional for a majority of Americans (unlike today).
1. Car infested ergo perfect venue area for testing autonomous cars, since the infrastructure is through and through car oriented at the detriment of every other form of mobility (walking, cycling, buses, trams, trains, etc)?
2. Super hot and sunny, ergo no fog, no rain, no sleet, no ice, no special weather conditions to handle.
3. Flat like a pancake, making terrain management, coupled with the nice, wide roads from point #1, so super easy mode.
Let's see them scale Waymo to at least 3 out of the following: San Francisco, NYC, Bucharest, Istanbul, Mumbai, St. Petersburg, etc.
Yes Phoenix is ideal, that is why they've been using it. I think it indicates they are more than 5% done though, is my point. Also they are operating fully autonomous public taxis in San Francisco, but not the run of the whole city, I think its just airport to downtown. But even navigating downtown SF I think is an accomplishment.
That maths sure make it a very hard problem to solve. But jokes aside I see your point. Isn’t that always the case with this kind of issues? Doing the first big chunk is relatively easy and then the final details are very hard?
Google is an ad-driven company and they haven't yet figured out to generate ad revenue from Waymo... (Having said that, it's cool that the Mountain View office building I used to go to is now occupied by Waymo).
"Urban" includes second, third, and fourth tier "cities" with low populations and no fleet of Ubers today. There won't be a market for automated ride share for most of the US.
Some have postulated that this might be Google's Blackberry moment. On the flip side I wonder if its actually more like its Dropbox moment.
The press loves a David and Goliath story; the young disruptor versus the stodgy disrupted.[1] At that time, Dropbox was David, coming out of nowhere in a hurry and had a product that seemingly should be so obvious for Google to launch but hadn't - making Google seem antiquated and slow.
Fast forward a couple of years (aka a decade) and Dropbox is still going ok but Google Drive is by far more ubiquitous.
Good point - I think the much more typical flow for Google Drive is cloud first for most documents and only uploading occasional offline document upload.
Which is perhaps why Google didn't really focus on creating a Dropbox like product until it was forced to because the more long term profitable for Google was a solution/vision based around a cloud first experience.
Dropbox iPad refuses to keep docs synced docs that I have specifically flagged for this. I routinely open the iPad somewhere without a connection and see that the docs are a month out of date.
Not as mission critical as the desktop app, but still pretty frustrating that they can't handle this core functionality after years and millions spent on other bells and whistles.
Apple is forcing Dropbox to cripple itself because they now have to use Apple's own cloud file sync API which is hot garbage. I don't know if this is the cause of your iPad issue, but Dropbox on MacOS is about to get a whole lot shittier.
Google makes fuck all revenue from Drive, it never mattered. EVERYTHING at Google, most notably the cash fire that is Cloud, is funded by Search. This is the first time that is in danger and over 25 years they never came up with a fallback plan. This is an unmitigated disaster and purely the result of mismanagement.
Also the comparison is between Google versus Dropbox (the underdog David that's analogous to OpenAI), not Google versus Amazon or even Google versus Microsoft.
Google is 51% of office productivity software market versus Microsoft. Microsoft is at 47%, Dropbox isn't even listed. [1]
Dropbox has a decent share of the personal cloud storage market but has really failed to expand beyond that vertical or become significantly profitable. [2]
The point is Cloud is still 100% subsidized by Search, and if Search loses even 5% of market share in the next 12 mo it is a disaster as GCP cannot fill the gap as they are still losing money. The velocity at which they are losing money is immaterial to the fact they are not nearly ready to plug a hole if Bing take share.
If search gets usurped, or even a marginal but meaningful reduction in usage due to competition from AIs, then its not surprising at all that Google’s near term prospects could be worse than Coke.
Even Google winning the AI wars leaves them worse off as the operating profit potential of querying an AI vs their search index has to be far lower.
As to usage, once you start to integrate ChatGPT into your workflows it can meaningfully benefit vs traditional search. Ive been able to find information on specific programming language concepts, with generated examples, far faster than searching.
I can ask it about GameDev concepts and ask for bulleted lists or higher/lower level of detail in the answers. Information is presented in a much easier to consume manner
That being said, most stocks that are considered defensive are quite overvalued on a fundamental basis. I would consider a PE of 26 for Coke quite undesirable, though there’s much worse
If Google ends up winning in the AI war, search and ads will be significantly cannibalized, but it will have tremendous opportunities outside of search, many of them in areas that don't even exist yet.
In some ways, it might even be good. It's suffering from a kind of advertising resource curse nowadays, and being forced and able to diversify its economy would be best in the long term.
I'm not sure, it seems many companies have comparable technology at this point, and Google is not known for being great at packaging tech into products.
They had an enormous moat and edge in search, but not seeing it for this next wave of AI. Barrier to entry seems far lower
Google stopped being innovative the second their "20% Time" got gutted:
> Employees were encouraged to spend up to twenty-percent of their paid work time pursuing personal projects. The objective of the program was to inspire innovation in participating employees and ultimately increase company potential. For Google's part, Gmail and AdSense both arose out of side projects. In 2013, Google discontinued 20 percent time.
What has Google released since 2013[0]? Stadia?
Then you tack on that Google Search as of today is basically unusable/broken with people needing to append site:, double-quoting everything, or enabling verbatim search to get high quality results. Heck, on top of that, I also have a uBlock configuration that removes 280 domains from Google Results because they're all auto-generated spam of Stackoverflow answers.
There is something deeply wrong with the culture inside Google.
Google Workspaces originally released in 2006 (inc. Sheets, Docs, Drive was 2012, Calendar was 2009, etc), it was rebranded "G Suite" in 2016 then rebranded "Google Workspaces" in 2020. Rebranding an existing product isn't innovation.
Google Cloud is a worse clone of AWS, is that innovative? Redmond-style photocopying?
I'll give you TensorFlow, but we're talking about that being their death knell, so congratulations about signing their own death-warrant?
Agreed. I can actually just figure out how to do simple things in GCP console by clicking around the UI, including setting up networks, doing IAM, and getting stuff talking to each other, most of it without ever leaving the web browser or even peeking at documentation. Good luck doing that with AWS.
It was when it came out in the form of App Engine. It was when it released managed Kubernetes and then managed containers within Kubernetes (Cloud Run using Knative behind the scenes).
Also:
- Kubernetes has been incredibly transformative and adopted by all other cloud providers
- Golang - the language of choice for a lot of cloud native tools
- Flutter - it may not be the incumbent choice but it makes cross platform development a breeze
- Google Photos - no other photo platform comes close to it
Perhaps the original author should have specified profit generating products. Go, Kubernetes, Tensorflow are all open source and free. Google Photos makes a profit?
Apple photos now offers full user controlled encryption. Google Photos has no such protections and never will. Apple may not be saints, but the fact is there’s one photo service where the photos remain yours, and another where a photo of your kid can get your entire digital life nuked with zero recourse.
They added so much red tape and bureaucracy to it that it is a distinction without a difference. Innovation went from a stream to a trickle after 2013.
It went from "spend 20% on whatever project you find interesting!" to "spend UP TO 20% on a project your manager approves of and can defend from their manager, with routine reporting on the status, direction, and potential outcomes."
Employees went from wanting to work at Google for the "20% Time" to not using it because it was a huge hassle that could risk their career advancement, if your 20% time project didn't pan out. It went from a perk to a gamble almost overnight.
The result in the same either way though: Google stopped innovating.
>I also have a uBlock configuration that removes 280 domains from Google Results because they're all auto-generated spam of Stackoverflow answers.
Can you describe exactly what you mean? If there is a way to hide specific domains from showing in search results, it would be an incredible boon for me.
>It has been many years since Google has launched an innovative new product.
I can say the exact same thing about countless other large companies: Facebook, Intel, Microsoft, Boeing, AMD, AT&T, I could go on and on. At some point, launching innovative new products isn't really that important for a company, when many people on the services that company provides.
Google used to be considered different from and better than all the companies you list (except Facebook). Being lumped together with those companies would have been seen as an insult to Google in the past.
Times change, and companies grow and mature. Intel used to be a big innovator too, like when they decided making RAM wasn't the best strategy and decided to try making CPUs instead. They've come a long way since inventing the 4004.
It is if you don't want to wind up like IBM, i.e. - a company that could have been so much more, knew it had to change at the leadership level, and yet still couldn't get out of their own way. Apple's renaissance came because they started releasing innovative products and cannibalizing their own business.
Most large companies would just destroy themselves if they tried this. IBM is still there, decades later. Why is it not good enough to just continue to exist and generate profits, even if you aren't the highest-market-cap company on the planet?
Decades ago, it used to good and normal for big companies to simply stay the same size, make a steady profit, and return dividends to their shareholders. That's how you get a stable society, not with constant boom-bust cycles.
Google are a mature corporation. The fact they managed to innovate for so long is really a huge achievement but nothing lasts forever. The same applies to the rest of FAANG one way or another. Netflix cannot innovate out of streaming tv and movies, and now face strong competition from others. Apple has always been more about marketing than real breakthrough tech innovation and the bits of real innovation they did do left with Jobs. Amazon has flopped most of it's recent attempts (again, respects for running BOTH the worlds best retail company AND AWS). Facebook has been flailing around doing crypto currency and VR and getting nowhere. Microsoft haven't innovated since Excel FFS. Coke at least has the occasional new flavour...
I'm not "blaming" them, it's the cycle of life. Gravity eventually wins.
This is also a key reason for all the layoffs: Growing, innovating companies cannot ONBOARD staff fast enough, because their value is decided by how big they will be in the future and how fast they can get there. People are a profit centre. But mature companies' (in mature industries) only source of increased value is in efficiency, getting the same revenues with less costs. So people are a cost centre and they succeed by showing they're efficient (aka laying off workers).
you should also consider that Google is/was the best search engine around so it makes sense as a default, sure they pay to be the default and most people never change defaults. But if you are making a phone you might just really actually care about people having a good experience with your phone.
(and its not like Microsoft couldn't pay them either anyway)
4-5 years ago I would have agreed. But I've been using DDG for my primary search and only "resort" to using Google maybe 10-15% of the time my search fails on DDG.
I'm not saying DDG is amazing, only that you don't need a "Mercedes" to pick up milk.
All good points. Windows still very much dominates desktops / laptops sold (especially large corp environments)...so the default installed Edge browser + Bing is a significant share of users.
And with Edge being "basically chrome", and supporting Chrome plugins, the switching cost from Chrome -> Edge is quite small.
But for mobile, Android + iOS dominate...so that all goes to Google.
I think this could mean that Bing + ChatGPT has a really opportunity to beat Google in Search...it's gonna be hard, but I've never even considered them more than a distant 2nd option until now.
Yes, finally we are going to see a shift, but their 'dominance' is not going to necessarily change that much in some kind of 'step function'.
I suggest that Siri is about to get a lot better, and act more like we wanted it to act a decade ago.
As amazing as ChatGPT is, it's actually not that useful for most regular people other than as a more human form of search.
I think Google results will improve quickly enough that whatever MS does will seem novel but not necessarily have some kind of huge consumer impact.
We'll see search for company info and help directories get a lot better.
Remember that both MS and Google are 'etablished' companies, the later a bit slow moving and not firing on all fronts.
Why would anyone think a company that can't get Skype to work, is going to marvel the world with some 'new thing'.
OpenAI folks are on a roll, rapidly trying to make cool looking experiments, focused on 'wowing the world' not on direct revenues. Making that translate into products is another dimension altogether.
The most interesting stuff will come from startups.
As long as it's easy to see the list of web results so I can go there instead of just relying on the model. Also because there are reasons to go to sites other than just getting a summary. Like maybe you need or want to use that site to do something.
As someone else said, the problem is ChatGPT lies straight to your face, whereas at least Google's answers are based on structured data by someone. It's traceable, whereas I would not trust ChatGPT ever to tell me the correct temperature to cook a steak.
I don’t know if you saw screenshots of the Prometheus model inside Bing. But it presents the sources with all its answers. It is no ChatGPT but a new model created for search.
Traditional search practically forces you to read the sources directly. With ChatGPT, people will just assume its citation is correct due to laziness.
I've seen this with many human published articles on the Internet too. The litany of citations fool everyone into thinking that the article is credible, but when I actually read the citations, they don't support the article at all.
If it's citing all it's sources, it's not ChatGPT, it's a natural language interface around search, which Google has been doing for years including with voice...
Presumably they have bolted on something that cites sources. This doesn't mean that the things ChatGPT says are true, just that you can check some sources that are plausibly relevant.
"Get answers instead of being overwhelmed by options. Bing looks at search results across the web and summarizes responses to your specific questions and needs."
There's summarised cited searches and then there is the more ChatGPT option which is also available.
Specifically just the 400 best/recent ones. Google will never return more than 400 results for a query despite reporting ~80,000,000 results. If you click next enough it will run out after showing you ~38 pages of 10 results or almost 4 pages of 100 results.
This is the intended behavior. It kind of ruins serendipitious web surfing via search. I look through 4 pages of 100 results in less than a minute and the web as google search presents it just feels so shallow now.
Perhaps a bad example, since ChatGPT consistently gets the steak temperature right (or at least gives the same values as Google). Internal temperature of about 130-135°F (54-57°C) for medium rare, etc.
It's just one data point but it may indicate the commenter is miscalibrated on what ChatGPT answers well and what it doesn't.
It reminds me of when Wikipedia was new and we were told repeatedly that we couldn't trust it (by teachers, articles, etc.). It didn't matter if we could point to studies that found Wikipedia had similar accuracy to other encyclopedias. They objected on the grounds that anyone could edit it and anything on it _could_ be wrong and there's no publisher or paid editors to ensure accuracy.
ChatGPT tends to do well on common questions, where the answer is plastered in hundreds of articles across the internet. The internal cooking temperature of a steak is a great example of this. There are many other types of questions it fails at.
A better example of where you shouldn't trust ChatGPT is asking it the distance between two cities. It'll get it right for a few common pairs of cities (eg London to Paris), but it'll give you a wrong answer for most less common pairs (eg London to Cairo).
Agreed. I wouldn't use ChatGPT for this because Google is faster and more reliable. I just thought the example was a bit odd since ChatGPT gets it right, and it's a type of question it generally gets right.
The difference between ChatGPT and Wikipedia is that Wikipedia actually cites its sources.
Also ChatGPT is only knowledgeable about general things, but even there it makes errors. It's basically a very complex scraping algorithm, the more interesting part is the language generation; even then this stuff seems at least unethical if not illegal since it's using other people's work/research without citation.
In many cases Wikipedia's source links are dead. And nobody bothers to update them. Or they cite some random book that I have no way to get and read myself.
Who checks if that book actually exists and is not made up? Especially if it's not a highly politically charged topic.
And then there are circular citations. Someone posts unverified/false info on wikipedia. Then it gets cited by some blog or other media that wikipedia considers trustworthy. And that then gets added to wikipedia as a reliable source.
The correct temperature to sous vide a steak depends on the desired level of doneness. The following temperatures are guidelines for cooking steaks to different levels of doneness:
It's important to note that cooking steaks at low temperatures for extended periods of time can result in a more tender and flavorful finished product, compared to cooking steaks at high temperatures for a shorter amount of time.
The problem is that if you don't already know the answer, it's hard to tell the difference between ChatGPT giving you the correct information and ChatGPT authoritatively spouting the wrong information.
Here's a chat I had today with ChatGPT:
Q: Who was the first US president with a last name starting with R?
A: Rutherford B. Hayes was the first US president with a last name starting with "R."
Q: no, a surname starting with R
A: Rutherford B. Hayes was the first U.S. President with a surname starting with "R."
Q: no, Rutherford is his first name
A: The first US president with a surname starting with "R" was Richard Nixon.
Q: no, Richard is his first name
A: The first U.S. President with a surname starting with "R" was James A. Garfield.
Here it's obvious ChatGPT is spouting nonsense, but in other cases it may not be.
Just for fun, I tried again today with a new chat:
Q: Who was the first US president whose surname begins with "R"?
A: The first US president whose surname begins with the letter "R" was John Quincy Adams.
Q: Adams does not begin with "R"
A: I apologize for the mistake. The first US president whose surname begins with the letter "R" was Rutherford B. Hayes.
Q: Hayes does not begin with "R"
A: My apologies for the mistake, the first US president whose surname begins with the letter "R" was James A. Garfield.
Q: Garfield does not begin with "R"
A: I apologize for the error. The first US president whose surname begins with the letter "R" was Richard Nixon.
Q: Nixon does not begin with "R"
A: I apologize for the mistake. The first US president whose surname begins with the letter "R" was George Washington.
Q: Washington does not begin with "R"
A: I apologize for the mistake. The first US president whose surname begins with the letter "R" was Franklin D. Roosevelt.
Q: Wasn't Theodore Roosevelt president before FDR?
A: Yes, you are correct. Theodore Roosevelt was the 26th President of the United States, serving from 1901 to 1909. He was the first US president whose surname begins with the letter "R." Thank you for pointing out the error in my previous answer.
So at least it's capable of parroting the correct answer after you deliver it. :-)
The SEO content served up by Google search nowadays isn't much better, and from what I've seen I don't think a lot of it is being generated by someone either.
Even this kind of project only helps so much. ChatGPT has absolutely no understanding of anything, it just regurgitates words and sentences in a way that sounds like it knows something. It's next sentence might be completely, dangerously wrong. You can't even claim that it lies to you. It needs to have an inkling of the truth to be able to lie in the first place. It's basically a well-trained parrot that has learned when to say the right combinations of phrases it's memorized at the right time in the right order to earn a treat. It has no idea what any given word means, let alone what it just said.
If someone built something that parsed sentences, stored facts, learned relationships between them, learned enough language processing to make connections between them in order to be able to say something new about the subject it didn't already know before-hand, then I'd be on that train. Right now I only see misery in our future if we just work on honing ChatGPT and it's ilk to better simulate BS.
Completely agree. Heck, even the current 'waiting list' page (bing.com/new) looks so outdated and a mess. I don't know whether it is the font, the colors, the composition or margins..
Bing itself looks like a mess too. Microsoft truly has no taste.
The scary real threatening and killer thing would be for chatGPT to automanage my tabs. Like a well-meaning shepherd, perhaps create new pages on the web that by a combined virtue can take the place of whole groups of open tabs, being equivalent convenient replacements of the information they once held.
Bing is my default on my work and home PC as I use edge, I've been too lazy to change it. For the most part, whenever I accidentally search something on Bing, I end up having to open up Google and search it again. Their results are still way better.
I don't get the HN hate of Google as a search tool. Yes, SEO has made searching more difficult, but Google is still by far the best search engine provided that your searches are focused and you use search tools (e.g., excluding terms, focusing on certain sites, etc.). I've tried other search engines (e.g., DDG, Bing) and they just aren't as good as Google.
>I don't get the HN hate of Google as a search tool. Yes, SEO has made searching more difficult, but Google is still by far the best search engine provided that your searches are focused and you use search tools (e.g., excluding terms, focusing on certain sites, etc.). I've tried other search engines (e.g., DDG, Bing) and they just aren't as good as Google.
What if their search is better just because way, way way more people use it?
Many of the HN crowd remember when Google came into existence and how wonderful it was.
If it existed on the internet, Google would find it for you and it was usually the top resault. It was amazing.
Today, it's a shadow of its former self.
You regularly have to search, wade through the ads that are written like informative articles, adjust your query slightly and repeat the process. It's rubbish.
What these people are remembering is when the web was small and dorks-only. Now it is huge and full of normies of all kinds, including every shade of commercialism and fraud.
The number of internet users is currently 150x more than it was in 1996. I don't think you can make an argument that it was already mainstream in '96 with a few tens of millions of people on it.
The web was overwhelmingly informational up to an inflection point where it became overwhelmingly commercial. That's the thing people are upset about.
In 1996, did every traffic attorney publish a thought piece on why you should fight your summons in X county?
No, back then if you searched a topic you were MUCH more likely to find self hosted content from someone who nerded out on an issue and is sharing their insight, not publishing boilerplate because they feel they need to.
This, exactly. Google was a revelation, a clean page with the exact result you needed, at a time when many orgs were putting lots of high quality content online. The other search engines were busy portals and weren't indexing the new content.
I mean, Google still often gives me the result, but it’s such a chore now. And they can’t even seem to deal with what I consider extremely obvious blogspam.
Content that is just literally directly copied from other domains often.
> you use search tools (e.g., excluding terms, focusing on certain sites, etc.).
Focusing on certain sites? If you know what site you want, why not just go there? You don't need Google for that.
I've had very limited success with their search modifiers. The main one I want to work is the literal search by putting things in quotes. But I don't think that has ever actually worked for me.
If they brought back the + modifier and it worked, that would also go far.
I wonder if MS can query and see the pain of people just searching for the Google Chrome download link, downloading it, closing Edge and never opening it ever again.
How could they have left such a massive gap in their product. They literally have the model and resources to revolutionize search. We all know LLMs will hurt their ad revenue, but regardless they have to have known this was coming. This is so similar to FB getting caught off guard by TikTok. There was a gap in the utility of their product (TikTok enabled grass roots content creation), and they just left it wide open.
Its some combination of:
1. ChatGPT is so much better than previous versions that Google themselves was stunned by the utility.
2. Incompetence/Gross negligence across Google
3. No way for them to reconcile the lost ad revenue, so they released nothing. This case is hard to argue for, as they would know theyre a sitting duck.
Regardless I am hoping for a massive Google failure. Theyre the ones responsible for the SEO content waste land that is the modern internet. We have all suffered at the feet of their ad machine
If OpenAI is willing to release it and Microsoft invested 10B, I have a very hard time believing that censoring the model is impossible. Microsoft 100% did their due diligence on the model.
Google is a monopoly, there is nothing anyone can do. Their search engine and business model has structured the internet and thus society. This thing needs to die
This is the same Microsoft that had to close down their Twitter AI “Tay” after a single day because it immediately became a “racist asshole” (as per The Verge) in 2016?
The same OpenAI ran by Sam Altman, who just last year was part of a crypto biometric scam called “Worldcoin” that attempted to collect biometric data from some of the worlds poorest in exchange for a shitcoin?
I’m sure they’ve done their due diligence and aren’t just pushing out a broken product as quickly as possible after it went viral because they saw dollar signs…
I’m pleased you have the privilege to just ignore the potential negative outcomes of this technology, that as per the marketing hype is set to become the new way the world interacts with information, primarily owned by two unsavoury entities who have history failing to protect the most vulnerable.
2016 was 7 years ago. And I completely forgot about that incident. And so did everyone else.
> I’m sure they’ve done their due diligence and aren’t just pushing out a broken product as quickly as possible after it went viral because they saw dollar signs…
Why wouldn't they? If they bet and win, they significantly disrupt the search market and many others. If they don't, people still don't use Bing. The rest of their business will continue on as is.
> 2016 was 7 years ago. And I completely forgot about that incident. And so did everyone else.
Microsoft also?
> Why wouldn't they? If they bet and win, they significantly disrupt the search market and many others. If they don't, people still don't use Bing. The rest of their business will continue on as is.
The GP was responding to a post that said that Microsoft 100% did their due diligence.... I'm unsure to what you are responding.
I do not understand the appeal or gpt-powered searches.
Most of my web searches are for looking up specific things, to find the specific link(s) that contains the information I need. These aren’t searches that are going to be made better or faster by an ML model-they’re not natural language queries, they’re just a bunch of terms.
Depends on your use case - if you are coding, or doing constraint analysis - 75+% of the time it's a single request, single answer, and you are done. The other element with ChatGPT is if you aren't happy with the initial answer for some reason - you can engage in a conversation with it, provide some guidance, and will adjust it to suit specifically what you are interested in. I've found about 50% of my google searches just go straight to ChatGPT these days. Hallucinations are the only real problem I've had - but over time you start to become cynical about the truth of anything factual - asking for unit tests helps quite a bit when coding - double checking any math is also important.
I do agree though, that without citations to the original source - any "Facts" that ChatGPT offers are absolutely untrustworthy.
As someone else said, I think a surprisingly (overwhelmingly?) large amount of queries are just questions people want answered, or close to them, and not really "search queries" in the traditional sense of text people are looking for on a page somewhere.
Even before this, you've seen the search engines add features to cater to that kind of use, things like Siri handing off questions it didn't understand to a search engine (as well as the other assistants that can do that), indications of this behavior in how companies like Google show themselves being used in ads.
Of course, regardless of the true prevalence of that behavior, it's probably in Google et al.'s favor to encourage that. Regular search sort of inherently cedes some power and control to the pages the results are coming from, where you're sending users away to if their answer isn't right in the snippet. But the "answer box" features, or an LLM that just tells you "the answer to your question" directly on the page keeps you there, treating the search page as your source of information and not somewhere else.
When you are curious about a fact, you're looking for a useful and accurate answer. You don't care what page you read it on, as long as it's both useful and accurate. You just think you are looking for a page because that's how you're used to doing it.
Beyond that, most of the results that rank for anything are plainly worse LLM blogspam padded for SEO. All you're doing here is cutting out the middleman.
The problem with chat gpt for factual question search is, of course, that it's not factual. It's job is to produce coherent sentences, not actually tell you factual information. So until they manage to get that right it's not a superior product.
There are two types of search, people looking for a specific resource (like searching for a song on youtube) and people just looking for an answer to a question. If a LLM can be factually accurate, its a superior search product for that specific use, which is probably the majority of search.
That said, ChatGPT does a very good job of understanding what I am looking for. If Microsoft could just insert this understanding into its regular search algorithms it would seem likely to significantly improve the quality of search results.
Similar statements have been made about most dominant technology when it was in its infancy. You are not wrong, but it can quickly go from novelty to necessity once folks start to rely on it.
Do you see yourself relying on it? Not when you know it’s KNOWN to give wrong answers.
It’s also worth mentioning that Google PageRank was not the first search engine. No, it was good 4-5 years after the first usable search engine came to market. I think the same will be true for AI chat.
How can you say that with a straight face? It’s a regurgitation of things it’s collected from the WWW. It is a step up from Siri/Alexa but completely lacks actual conversational skills.
If you don't put in an honest effort to give it a shot, you will remain forever confused why people find tech like this useful for some use cases and you don't.
People said Galileo was a crank, supposedly. But they also said that about the crank raving at the bus station. That people have been wrong about how transformative or not a technology would be in the past really tells us nothing.
544 comments
[ 3.5 ms ] story [ 342 ms ] threadThey have a really compelling package that is hard to replace, especially how well they understand local queries.
That as well as strong funneling factors in place, Chrome and Android being some of the biggest.
Unless Bard sucks too much
Data is king in AI. And nobody beats Google there. They will figure out how to leverage that advantage.
Touchscreens are the worst interface option. The feedback of feeling a button, or anything made for the job, is better than typing without specific feedback onto a screen. It won out because of you don’t have a set interface it’s bettor.
Now for search, chat gpt will likely always be less reliable than a list of results you can vet yourself for content and source.
That said… I don’t think people care about truth that much these days so one response that feels correct is could be good enough for most. Terrifying times we live in folks.
Hottest take I've seen on here for a while. In a very specific, very limited set of mobile usecases, buttons may offer a more pleasant experience than a touchscreen. I only say that because there's usually exceptions to any statement, but I can't actually think of one.
Touchscreens didn't win because of some lazy sheep-like consumerism, they won because the product is superior. If Chat-GPT style models defeat traditional search engines it will be because the product is better, not because people are content with a response that "seems correct."
It’s a crap interface compared to others but it’s the best to do anything. That’s why it won.
One is not superior to the other over all, but each is better at certain things. The difference is that more people will pay money to maximize their user experience scrolling through feeds and watching videos, compared to typing emails.
I still miss my landscape key board phones. The droid 4 still holds a special place in my head.
Touchscreens win when you need multiple interfaces in the same amount of space.
When defining "better" you need to indicate the metrics you are using. LM's might be "better" when measured with certain metrics, but like most things are worse when measured using other metrics.
I can understand why some times you might just want a chat response to a question rather than a web search.
But I swear that if I even suspect Siri's response is influenced by advertising or endorses a product, I will take the homepod and punt it down the street.
Irony of this article, predicting end of Google, is that articles like this are going to be replaced by these summaries too.
Edit: based on the subtitle, it seems like I am correct.
That's why it's absolutely nonsensical to see all these articles, because they are talking about a chatbot as if it's trivial to turn it into a search machine. That's an entirely different problem.
And answers as text wrapped around a factual knowledge base just sounds like the sort of queries Google Home already handles in natural language form. That can certainly be improved upon, but it isn't obvious that the LLM engineers will beat the search engineers to it...
I really am getting old ...
If/when Bing gains dominance and starts abusing its position, I'll probably change positions, but that's the way it goes when there's a lack of competition in the market. You're left cheering for the best of the worst.
If you ask google a question then an awful lot of the time the majority of top 10 results will be promoting or selling stuff.
At the moment ChatGPT is like having an personal assistant that used to be an world leading expert, but has been sniffing glue for the last 5 years. He knows a lot of shit but you can't trust it. But he can help you get started and he's fun to be around.
Except ChatGPT isn't fun to be around. It's been castrated of humor and dominated by extreme political correctness. I think GPT is the catalyst for a change, but in Microsoft's hands it'll just be a glorified Clippy.
As for training data scraped from the internet, it will be split like steel was with "pre-war steel", due to atomic bombs rendering steel unfit to use in geiger counters. We'll have pre-gpt data.
Over the last year, its become palpable.
Google has such utility in this regard that in some cases, a hallucinating lie-machine offers better answer than an index of what information is available on the internet.
This issue with with Googles failure to respond to the deluge of SEO driven content in their searches. They can do better. They've chosen to not do so.
idk, sounds plausible to me, the way things've been going.
Yet GANs work quite well
AI will be a victim of it’s own success too. Or it will need to be human researched and curated rather than just letting an algorithm run freely across the web.
I’d argue that they even encouraged it.
And unfortunately Google has become worse than ever at being able to differentiate between insight and fluff.
It can only index stuff that's on the Web. Stuff on the Web is, contrary to what is popularly asserted, only a tiny fraction of all human knowledge.
I think people are forgetting how bad search was before Google. Google drove Web directories to extinction. Remember Yahoo!? Back in that era, if I were looking for something as simple as the University of Michigan, I clicked and drilled down through a Yahoo directory. The obvious search query would have been useless. Google changed all that.
I view Google as the yellow pages. It works well for that. Is it an oracle of knowledge? Of course not. How could I possibly expect to find knowledge on a place where there is no reward for making it available? People producing knowledge don't work for free.
I've tried ChatGPT and it's no better. It serves up stuff that is flat-out wrong.
And yet for some reason they're all too eager to serve up sites scraping stackoverflow.
That’s still a thing, although it seems they’re A/B testing its removal. I just opened a private tab (as I always do) and got a boring "More results" button, but I tried another browser (also with a private tab) and got the classic pagination.
It's still there right now.
Today:
* Any term that might be related to a commercial product? That product comes first and frequently only.
* Search for two terms? It will first give it's prefer result for each separately - usually commercial products (ha). And then might give them together.
* Quoted terms are often taken as vague suggestions. Negative sign is often useless, etc.
So do I. I can't tell you the last time I even held yellow pages in my hands.
#1 result is a long article with culinary history, detailed instructions, many pictures, and a credited author originally from Shanghai.
#2 result is a simple recipe listing from Buzzfeed. Written by a young white guy from Minnesota who worked as a producer. No fluff, no pictures, no backstory. Doubtful the author ever made the recipe at all. You could grab a recipe database and generate thousands of these pages.
I've been burned by #2 too many times disregard the fluff. It shows their investment in the content.
In the last 2-3 months search quality for me has absolutely crashed and is barely usable.
I'm willing to accept that maybe you are exaggerating to make a point. Maybe you have a better example that is actually illustrative?
In the present day, I cannot find my answer on the first page. If I click on the top hits the page is a deluge of useless blogg fluff which takes me more time to find what I am looking for.
More often than not have to add reddit, forum, stackoverflow, etc to find what I am looking for because online communities provide more concise answers.
This is why googles utility has collapsed.
It's not that the content doesn't exist or isn't indexed, its that its been drowned out by noise. Sifting through noise better was the entire reason google took off from more standard crawlers. It now returns results worse than crawlers from the previous era.
That is an absurd exaggeration.
Before the results would just not match what I was looking for. Now they do match what I was looking for, except some AI procedurally generated the content to show up when I searched those terms, with no regard for the accuracy of what the page says.
If I say "show me the best winter gloves, and only from sites that you can verify actually product tested" and it follows the instruction (ignoring sites that just have a list of popular search results aggregated) then it is better. If it doesn't do what I want, I expect to be able to follow up and teach it.
I expect the chat style stateful search to take instruction for what type of sites I want results from. "Return me a list of websites with recipes for Bolognese that do not have a long story above the recipe. Build a table with the top five results normalized for portion size, comparing and contrasting the ingredients. Highlight unique ingredients in bold."
Relevant search results that aren't just marketing sites or the big websites.
> It can only index stuff that's on the Web.
And much of it isn't really exposed by Google search.
> I view Google as the yellow pages. It works well for that
It used to. For me, it stopped working well for that a few years ago and has been getting steadily worse ever since.
The competition for many kinds of search terms is causing a race to the bottom. E.g. tech docs, lyrics, recipes, reviews.
That’s why Kago has a lense for “non-spammy recipe searches” — there’s just so much noise on popular, easily copyable material.
You don’t get the best site by popular vote like PageRank was known for, you get the one that generates the most ad revenue.
Then, with Google, it got better and almost all results were relevant.
But we’ve been regressing over the years, and now we’re at the point where 80% of all results are both irrelevant and simply SSO spam.
I find it really hard to believe Google has some of the smartest people in the world on search and they cannot identify this.
For example, just the other day I was searching for one string that I knew was part of a common code repository. To my surprise google couldn't find anything at all. Yandex on the other hand found the repository immediately and linked to github.
Other common issue with google is the difficulty of finding stuff like forum posts related to the search query. Sure, you could append "reddit" to the query, but there are still plenty of traditional forum sites and some of them have decades worth of discussion. I Never see those sites pop up on a typical google search unless I specifically look for them. Again, with yandex, my experience is much better, it is not uncommon to see posts from forums to be on the first page of results.
ChatGPT usually gives me the answer that I'm looking for and nothing else. Sometimes it does add extra info, which often teaches me about something that I wasn't aware of at all.
But the greatest benefit is I can ask it to clarify anything I don't understand. I don't need to go on a completely new Google quest, or jump through hoops to register on some site and hope a random internet person will ordain to help me out. I can just ask, in the same conversation, and immediately get clarification.
Many people underestimate the incredible learning opportunities a well trained language model provides. It doesn't matter that it hallucinates or lies. Whatever it claims is usually easy to validate. What matters is the speed with which you can find uncluttered new leads or answers.
Google didn't innovate that much except to provide a clutter-free interface and slightly better search. Prior to that, I used Webcrawler and then HotBot. A search like what you described would have easily returned useful results.
I want you to start a blank slate C (or C++) project. Ask Google how to write heapify, push_heap, and pop_heap in C. Ask ChatGPT the same.
I did this a few weeks ago. I literally could not find the answer on Google. ChatGPT gave me actual C code that I definitely did not trust but did verify.
Google results for questions like that are genuinely awful. It’s full of shitty tutorial websites that are full of ads and either don’t have the answer I need or don’t have it in a convenient form.
And I've /recently/ hunted for something obscure, couldn't find it, managed to find an old bookmark to it, the server was still online and the content I wanted was still there. And no amount of crafting of a google search would bring it up. And the server in question didn't contain copyrighted material which would have resulted in a takedown block or anything like that.
It's frustrating how /bad/ Google has gotten for anything other than fairly basic, high level "searching".
I mean what you just listed.
Google won the search war because of PageRank eliminating lots of spam, and then something like 15 years of staying ahead of SEO spam and providing useful search.
Lately it seems like they've given up on the arms race and let the SEO spam win, but it isn't clear why.
And Google didn't produce high quality search for free, they used ads and sold the eyeballs they won.
Lots of trash out there but Serious Eats is good quality.
I use BBC good food, almost always straight to the point
I get not everyone is a foodie that cares about the details and wants to tweak it, but I appreciate them.
https://www.verybestbaking.com/toll-house/recipes/original-n...
https://www.allrecipes.com/recipe/10813/best-chocolate-chip-...
Also, once the ChatGPT AI takes off and becomes ubiquitous, then what if there is a lack of credible content for it to train on?
How much do you think companies are willing to spend to be the answer to, "what is the most reliable car?" or, "who should I vote for?"
In theory it is possible that sponsored content will creep in, but that does not invalidate the incredible benefits a well trained language model will have, even despite the occasional for-profit bias.
You mean all your Replika "friends" that spit out answers from Bard's mouth? :)
And why is the GoogleBot still on HTTP 1.1...
Google search has two huge problems: SEO and censorship. Search for anything related to products/torrents/streams/politics on Google and your results will SUCK, due to one of the two reasons stated above.
The recent Yandex hack/leak has the cynic in me connecting the dots and, seeing how Google search seems to be facing REAL threats to it's dominance since it's creation... maybe some guys with the deepest pockets in the world are starting to enter WAR mode.
Destroying Yandex advantages on the SEO battlefield by way of divulging their parameters to the world would be the Franz Ferdinand assassination moment of the Great Search War.
Are you asserting that they look at their copious data and decide to make search worse because it makes them more money? Rather than figuring out a way to make search better and then further optimize their advertising income with this better product? And it seems like they've been pretty damn clever about monetizing quality over the years. It's possible that they have chosen to make search worse for profit, wouldn't be the first time a business did something like that but they have a pretty deep institutional fear of search losing relevance and it's hard to see them doing that.
As a long time user and user of the other guys before google, I think Google is shockingly good at finding specific answers to specific questions that I have about all sorts of things, often with fairly deep technical context. Now what is definitely lacking is in the good old days I'd enter some search terms, get pages of results and then some time later I'd find myself enjoyably down some rabbit hole that is tangential to my search needs on some part of the internet that I never even knew existed before. Maybe I'm too busy with work, but I used to spend a lot more time doing internet "research" to get some specific answers, that time seems to be much more efficient; I do sort of feel like I'm corralled to smaller portion of the internet than I used to be. I don't feel like I can't find the information but I have had a hard time re-finding some specific web page I found once way back.
Where does ChatGPT and Bard fit in this? I've played with ChatGPT and it's fun, it's neat, I haven't been able to get it to some how synthesize some wisdom though. It's not hard to see it just mimicking things. That might be valuable. That might be fun. Using it to seed search might be an enjoyable thing. Maybe it can help extract context from people to find out the actual question they are asking to find the actual answer they seek. Now I can absolutely see ChatGPT/Bard assisting in me wasting time going down rabbit holes, I'm not sure it'll be as enjoyable or as magical as how it used to be.
Are there some examples of shitty google search you can bring up? I just entered "Roth contribution income limit" and without even going to another website, I got what looks like a legit answer to my question. Now I'll click though a few to make sure it's accurate and authentic; at a glance, it's coming from Schwab and it looks like a legit answer to my question. Bing comes up with the same answer, it's presented in a nice table but it's lower on the page and below a sizable paid ad from Merrill Lynch (edge?)
Although Google, Maps, Youtube are of daily use they are monetized exclusively by advertising which is annoying and hated by many. It has been many years since Google has launched an innovative new product.
I don't think ChatGPT will gain daily traction after this hype. Anyway we could say that MSFT and AMZN have demostrated more power to innovate with different business models (not only adv) and products.
The GOOG stock has a PE (Price/earning) of 23, while Coca cola 26. So the stock market expect higher growth from CocaCola than Google. Quite surprising.
- GOOGLE PE (23): https://www.macrotrends.net/stocks/charts/GOOGL/alphabet/pe-...
- COCA COLA PE (26): https://www.macrotrends.net/stocks/charts/KO/cocacola/pe-rat...
Stadia launched in 2019.
Also, it's already dead.
The only one of those I'd used was Geforce Now, and found it very similar to Stadia wrt latency. Stadia had a much nicer interface, though.
Stadia might have been well executed from a technical standpoint but AAA game streaming wasn't exactly a new and innovative idea in 2019.
Lol.
I love chatGPT but it clearly has a ton of issues. To declare Google dead that is point is completely absurd.
I can't think of a single transformative technology that actually has a first mover advantage. The first, second and third mover seem to make all the mistakes and setup the forth mover to learn from those mistakes for free and create a monopoly.
Counting out a company that owns Deepmind is just not rational.
I don’t know how much. Money it makes, but there is paid API access to maps.
Youtube Music is really .. strange.
It looks wrong/outdated everywhere.
Generated playlists (recomendations) are always (for days/weeks) the same. Not a bit randomization. It feels like they were approved by party commitete for years.
I don't understand why they decided social network in music service.
Ah hell. CUE-lists are still too novice technology for them.
I still think that last.fm 15 years ago was the best music service.
I find YouTube quite easy to use, esp the shortcut keys.
Recommendation system is another story.
Google's gotten through the first 95% of the work, but the remaining 95% is gonna take awhile.
1. Car infested ergo perfect venue area for testing autonomous cars, since the infrastructure is through and through car oriented at the detriment of every other form of mobility (walking, cycling, buses, trams, trains, etc)?
2. Super hot and sunny, ergo no fog, no rain, no sleet, no ice, no special weather conditions to handle.
3. Flat like a pancake, making terrain management, coupled with the nice, wide roads from point #1, so super easy mode.
Let's see them scale Waymo to at least 3 out of the following: San Francisco, NYC, Bucharest, Istanbul, Mumbai, St. Petersburg, etc.
That could be at least a decade away.
No it won't. It will be an option for those who can depend on a car service due to proximity to a city.
Sounds like a majority to me.
At the same time, a lot of these platforms ran effectively unopposed for many years, and now competition in advertising is spreading quite rapidly
Here’s a tour of the recreation https://maps.app.goo.gl/syHHp9GWmaGA5Woz7
The press loves a David and Goliath story; the young disruptor versus the stodgy disrupted.[1] At that time, Dropbox was David, coming out of nowhere in a hurry and had a product that seemingly should be so obvious for Google to launch but hadn't - making Google seem antiquated and slow.
Fast forward a couple of years (aka a decade) and Dropbox is still going ok but Google Drive is by far more ubiquitous.
I guess only time will tell.
[1] Dropbox Versus The World https://www.fastcompany.com/3042436/dropbox-versus-the-world
Which is perhaps why Google didn't really focus on creating a Dropbox like product until it was forced to because the more long term profitable for Google was a solution/vision based around a cloud first experience.
Not as mission critical as the desktop app, but still pretty frustrating that they can't handle this core functionality after years and millions spent on other bells and whistles.
The "at most a few years from profitability" after a period of what, 15 boom years?, doesn't sound that great as the 3rd place contender.
Also the comparison is between Google versus Dropbox (the underdog David that's analogous to OpenAI), not Google versus Amazon or even Google versus Microsoft.
Google is 51% of office productivity software market versus Microsoft. Microsoft is at 47%, Dropbox isn't even listed. [1]
Dropbox has a decent share of the personal cloud storage market but has really failed to expand beyond that vertical or become significantly profitable. [2]
[1] https://www.statista.com/statistics/983299/worldwide-market-...
[2] https://www.statista.com/statistics/1328893/global-file-shar...
Even Google winning the AI wars leaves them worse off as the operating profit potential of querying an AI vs their search index has to be far lower.
As to usage, once you start to integrate ChatGPT into your workflows it can meaningfully benefit vs traditional search. Ive been able to find information on specific programming language concepts, with generated examples, far faster than searching.
I can ask it about GameDev concepts and ask for bulleted lists or higher/lower level of detail in the answers. Information is presented in a much easier to consume manner
That being said, most stocks that are considered defensive are quite overvalued on a fundamental basis. I would consider a PE of 26 for Coke quite undesirable, though there’s much worse
In some ways, it might even be good. It's suffering from a kind of advertising resource curse nowadays, and being forced and able to diversify its economy would be best in the long term.
They had an enormous moat and edge in search, but not seeing it for this next wave of AI. Barrier to entry seems far lower
> Employees were encouraged to spend up to twenty-percent of their paid work time pursuing personal projects. The objective of the program was to inspire innovation in participating employees and ultimately increase company potential. For Google's part, Gmail and AdSense both arose out of side projects. In 2013, Google discontinued 20 percent time.
What has Google released since 2013[0]? Stadia?
Then you tack on that Google Search as of today is basically unusable/broken with people needing to append site:, double-quoting everything, or enabling verbatim search to get high quality results. Heck, on top of that, I also have a uBlock configuration that removes 280 domains from Google Results because they're all auto-generated spam of Stackoverflow answers.
There is something deeply wrong with the culture inside Google.
[0] https://en.wikipedia.org/wiki/Google#2012_onward
- GCP Suite (a full integrated and consistent suit, answering so many things)
- Google Workspace (trust me when you get to know everything that is possible you will be amazed)
- Tensorflow and other Machine Learning applications
Google Cloud is a worse clone of AWS, is that innovative? Redmond-style photocopying?
I'll give you TensorFlow, but we're talking about that being their death knell, so congratulations about signing their own death-warrant?
This certainly hasn’t been my experience. I’ve found GCP products to be much better/easier to deal with than their AWS counterparts.
It went from "spend 20% on whatever project you find interesting!" to "spend UP TO 20% on a project your manager approves of and can defend from their manager, with routine reporting on the status, direction, and potential outcomes."
Employees went from wanting to work at Google for the "20% Time" to not using it because it was a huge hassle that could risk their career advancement, if your 20% time project didn't pan out. It went from a perk to a gamble almost overnight.
The result in the same either way though: Google stopped innovating.
Can you describe exactly what you mean? If there is a way to hide specific domains from showing in search results, it would be an incredible boon for me.
https://github.com/quenhus/uBlock-Origin-dev-filter
In particular look in the dist folder, find your search engine(s) of choice, and then get the blocklist you'd like. Paste into "MyFilters" in uBlock.
Bonus: Here's one that entirely blocks Youtube Shorts in your Subscriptions feed:
https://github.com/quenhus/uBlock-Origin-dev-filter
In particular look at: dist/google/ and stackoverflow_copycats.txt
Since I can’t paste screenshots from my terminal, you can see the sector P/Es on page 6:
https://www.spglobal.com/spdji/en/documents/performance-repo...
I can say the exact same thing about countless other large companies: Facebook, Intel, Microsoft, Boeing, AMD, AT&T, I could go on and on. At some point, launching innovative new products isn't really that important for a company, when many people on the services that company provides.
Disrupt yourself before someone else does.
I'm not "blaming" them, it's the cycle of life. Gravity eventually wins.
This is also a key reason for all the layoffs: Growing, innovating companies cannot ONBOARD staff fast enough, because their value is decided by how big they will be in the future and how fast they can get there. People are a profit centre. But mature companies' (in mature industries) only source of increased value is in efficiency, getting the same revenues with less costs. So people are a cost centre and they succeed by showing they're efficient (aka laying off workers).
Google search results are just screwy. Probably all that money is interfering with the algorithm.
Windows: Most use Chrome (Google default), the rest use Edge (Bing default).
MacOS: Safari (Google default) and Chrome (Google default)
Android: Chrome (Google default)
iOS: Safari (Google default)
So it looks like the only vulnerability here would be iOS and then possibly PC/MacOS if enough users switch their browser.
(and its not like Microsoft couldn't pay them either anyway)
I'm not saying DDG is amazing, only that you don't need a "Mercedes" to pick up milk.
And with Edge being "basically chrome", and supporting Chrome plugins, the switching cost from Chrome -> Edge is quite small.
But for mobile, Android + iOS dominate...so that all goes to Google.
I think this could mean that Bing + ChatGPT has a really opportunity to beat Google in Search...it's gonna be hard, but I've never even considered them more than a distant 2nd option until now.
Yes, finally we are going to see a shift, but their 'dominance' is not going to necessarily change that much in some kind of 'step function'.
I suggest that Siri is about to get a lot better, and act more like we wanted it to act a decade ago.
As amazing as ChatGPT is, it's actually not that useful for most regular people other than as a more human form of search.
I think Google results will improve quickly enough that whatever MS does will seem novel but not necessarily have some kind of huge consumer impact.
We'll see search for company info and help directories get a lot better.
Remember that both MS and Google are 'etablished' companies, the later a bit slow moving and not firing on all fronts.
Why would anyone think a company that can't get Skype to work, is going to marvel the world with some 'new thing'.
OpenAI folks are on a roll, rapidly trying to make cool looking experiments, focused on 'wowing the world' not on direct revenues. Making that translate into products is another dimension altogether.
The most interesting stuff will come from startups.
The correct interface for ChatGPT + search is just...ChatGPT. But it can also show you a list of web search results, when it's appropriate.
A super-clean interface, that always shows you exactly what you want.
That would be a killer feature and represent a real threat to Google.
https://blogs.microsoft.com/blog/2023/02/07/reinventing-sear...
I've seen this with many human published articles on the Internet too. The litany of citations fool everyone into thinking that the article is credible, but when I actually read the citations, they don't support the article at all.
"Get answers instead of being overwhelmed by options. Bing looks at search results across the web and summarizes responses to your specific questions and needs."
There's summarised cited searches and then there is the more ChatGPT option which is also available.
This is the intended behavior. It kind of ruins serendipitious web surfing via search. I look through 4 pages of 100 results in less than a minute and the web as google search presents it just feels so shallow now.
I also suspect the first set is very very small...
It reminds me of when Wikipedia was new and we were told repeatedly that we couldn't trust it (by teachers, articles, etc.). It didn't matter if we could point to studies that found Wikipedia had similar accuracy to other encyclopedias. They objected on the grounds that anyone could edit it and anything on it _could_ be wrong and there's no publisher or paid editors to ensure accuracy.
ChatGPT tends to do well on common questions, where the answer is plastered in hundreds of articles across the internet. The internal cooking temperature of a steak is a great example of this. There are many other types of questions it fails at.
A better example of where you shouldn't trust ChatGPT is asking it the distance between two cities. It'll get it right for a few common pairs of cities (eg London to Paris), but it'll give you a wrong answer for most less common pairs (eg London to Cairo).
Also ChatGPT is only knowledgeable about general things, but even there it makes errors. It's basically a very complex scraping algorithm, the more interesting part is the language generation; even then this stuff seems at least unethical if not illegal since it's using other people's work/research without citation.
Who checks if that book actually exists and is not made up? Especially if it's not a highly politically charged topic.
And then there are circular citations. Someone posts unverified/false info on wikipedia. Then it gets cited by some blog or other media that wikipedia considers trustworthy. And that then gets added to wikipedia as a reliable source.
Rare: 120-125°F (49-52°C) Medium-Rare: 130-135°F (54-57°C) Medium: 140-145°F (60-63°C) Medium-Well: 150-155°F (66-68°C) Well-Done: 160°F (71°C) and above
It's important to note that cooking steaks at low temperatures for extended periods of time can result in a more tender and flavorful finished product, compared to cooking steaks at high temperatures for a shorter amount of time.
Looks great to me.
Here's a chat I had today with ChatGPT:
Q: Who was the first US president with a last name starting with R?
A: Rutherford B. Hayes was the first US president with a last name starting with "R."
Q: no, a surname starting with R
A: Rutherford B. Hayes was the first U.S. President with a surname starting with "R."
Q: no, Rutherford is his first name
A: The first US president with a surname starting with "R" was Richard Nixon.
Q: no, Richard is his first name
A: The first U.S. President with a surname starting with "R" was James A. Garfield.
Here it's obvious ChatGPT is spouting nonsense, but in other cases it may not be.
Q: Who was the first US president whose surname begins with "R"?
A: The first US president whose surname begins with the letter "R" was John Quincy Adams.
Q: Adams does not begin with "R"
A: I apologize for the mistake. The first US president whose surname begins with the letter "R" was Rutherford B. Hayes.
Q: Hayes does not begin with "R"
A: My apologies for the mistake, the first US president whose surname begins with the letter "R" was James A. Garfield.
Q: Garfield does not begin with "R"
A: I apologize for the error. The first US president whose surname begins with the letter "R" was Richard Nixon.
Q: Nixon does not begin with "R"
A: I apologize for the mistake. The first US president whose surname begins with the letter "R" was George Washington.
Q: Washington does not begin with "R"
A: I apologize for the mistake. The first US president whose surname begins with the letter "R" was Franklin D. Roosevelt.
Q: Wasn't Theodore Roosevelt president before FDR?
A: Yes, you are correct. Theodore Roosevelt was the 26th President of the United States, serving from 1901 to 1909. He was the first US president whose surname begins with the letter "R." Thank you for pointing out the error in my previous answer.
So at least it's capable of parroting the correct answer after you deliver it. :-)
At least one person is working on this:
https://twitter.com/hsu_steve/status/1623388682454732801
While something like this would of course be incredible, even just current ChatGPT + the ability to web search for you would be quite amazing.
If MS isn't ready to completely replace Bing, then they should've made it an entirely separate page: bchat.com or something.
If someone built something that parsed sentences, stored facts, learned relationships between them, learned enough language processing to make connections between them in order to be able to say something new about the subject it didn't already know before-hand, then I'd be on that train. Right now I only see misery in our future if we just work on honing ChatGPT and it's ilk to better simulate BS.
I guess they opted for the search results as the default with the chat on the side as the link list is the current interface.
That's the pipedream, but in reality isn't the case yet even using just ChatGPT.
Bing's implementation is trying to balance raw ChatGPT outputs, with summarised cited responses in search.
I do think they need to speed up the animation for generating the summarised or ChatGPT result though...
are what?
>I don't get the HN hate of Google as a search tool. Yes, SEO has made searching more difficult, but Google is still by far the best search engine provided that your searches are focused and you use search tools (e.g., excluding terms, focusing on certain sites, etc.). I've tried other search engines (e.g., DDG, Bing) and they just aren't as good as Google.
What if their search is better just because way, way way more people use it?
If it existed on the internet, Google would find it for you and it was usually the top resault. It was amazing.
Today, it's a shadow of its former self.
You regularly have to search, wade through the ads that are written like informative articles, adjust your query slightly and repeat the process. It's rubbish.
The web was overwhelmingly informational up to an inflection point where it became overwhelmingly commercial. That's the thing people are upset about.
And it's not Google's fault.
But it also remains true that Google's search just doesn't work well for many people, and that some alternatives work better for them.
No, back then if you searched a topic you were MUCH more likely to find self hosted content from someone who nerded out on an issue and is sharing their insight, not publishing boilerplate because they feel they need to.
Google solved a big problem and then went to sleep while counting their money. They even started to be evil.
Now the original problem has evolved but Google hasn't managed to keep up.
Content that is just literally directly copied from other domains often.
Focusing on certain sites? If you know what site you want, why not just go there? You don't need Google for that.
I've had very limited success with their search modifiers. The main one I want to work is the literal search by putting things in quotes. But I don't think that has ever actually worked for me.
If they brought back the + modifier and it worked, that would also go far.
Its some combination of:
1. ChatGPT is so much better than previous versions that Google themselves was stunned by the utility.
2. Incompetence/Gross negligence across Google
3. No way for them to reconcile the lost ad revenue, so they released nothing. This case is hard to argue for, as they would know theyre a sitting duck.
Regardless I am hoping for a massive Google failure. Theyre the ones responsible for the SEO content waste land that is the modern internet. We have all suffered at the feet of their ad machine
Google is a monopoly, there is nothing anyone can do. Their search engine and business model has structured the internet and thus society. This thing needs to die
The same OpenAI ran by Sam Altman, who just last year was part of a crypto biometric scam called “Worldcoin” that attempted to collect biometric data from some of the worlds poorest in exchange for a shitcoin?
I’m sure they’ve done their due diligence and aren’t just pushing out a broken product as quickly as possible after it went viral because they saw dollar signs…
> I’m sure they’ve done their due diligence and aren’t just pushing out a broken product as quickly as possible after it went viral because they saw dollar signs…
Why wouldn't they? If they bet and win, they significantly disrupt the search market and many others. If they don't, people still don't use Bing. The rest of their business will continue on as is.
It's a no brainer.
Microsoft also?
> Why wouldn't they? If they bet and win, they significantly disrupt the search market and many others. If they don't, people still don't use Bing. The rest of their business will continue on as is.
The GP was responding to a post that said that Microsoft 100% did their due diligence.... I'm unsure to what you are responding.
Most of my web searches are for looking up specific things, to find the specific link(s) that contains the information I need. These aren’t searches that are going to be made better or faster by an ML model-they’re not natural language queries, they’re just a bunch of terms.
I do agree though, that without citations to the original source - any "Facts" that ChatGPT offers are absolutely untrustworthy.
I… don’t really get it either.
But I’m also a cranky person who can’t stand every damn thing being a video whether it makes sense for the content or not, etc.
Even before this, you've seen the search engines add features to cater to that kind of use, things like Siri handing off questions it didn't understand to a search engine (as well as the other assistants that can do that), indications of this behavior in how companies like Google show themselves being used in ads.
Of course, regardless of the true prevalence of that behavior, it's probably in Google et al.'s favor to encourage that. Regular search sort of inherently cedes some power and control to the pages the results are coming from, where you're sending users away to if their answer isn't right in the snippet. But the "answer box" features, or an LLM that just tells you "the answer to your question" directly on the page keeps you there, treating the search page as your source of information and not somewhere else.
Beyond that, most of the results that rank for anything are plainly worse LLM blogspam padded for SEO. All you're doing here is cutting out the middleman.
The problem with chat gpt for factual question search is, of course, that it's not factual. It's job is to produce coherent sentences, not actually tell you factual information. So until they manage to get that right it's not a superior product.
There are two types of search, people looking for a specific resource (like searching for a song on youtube) and people just looking for an answer to a question. If a LLM can be factually accurate, its a superior search product for that specific use, which is probably the majority of search.
That said, ChatGPT does a very good job of understanding what I am looking for. If Microsoft could just insert this understanding into its regular search algorithms it would seem likely to significantly improve the quality of search results.
It’s also worth mentioning that Google PageRank was not the first search engine. No, it was good 4-5 years after the first usable search engine came to market. I think the same will be true for AI chat.