[HN Gopher] Is Google's 20-year search dominance about to end?
___________________________________________________________________
Is Google's 20-year search dominance about to end?
Author : i13e
Score : 129 points
Date : 2023-02-08 20:57 UTC (2 hours ago)
(HTM) web link (www.economist.com)
(TXT) w3m dump (www.economist.com)
| FridgeSeal wrote:
| 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.
| ghshephard wrote:
| 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.
| helf wrote:
| I think because people want to natural language ask questions
| to a virtual butler (Jeeves) and get an answer back in
| digestible natural language form.
|
| 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.
| lvl102 wrote:
| ChatGPT is still a novelty. People will kick tires etc but
| utility is just not there yet.
| bloblaw wrote:
| 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.
| lvl102 wrote:
| 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.
| tootie wrote:
| Betteridge's law right here. I don't see how ChatGPT is going to
| do anything in the search space and it's stunning to see people
| tripping over themselves to declare Microsoft the winner already.
| I'm already predicting they will write down this acquisition for
| a few billion in 2 or 3 years.
|
| AI question and answer searches have existed for a while. Alexa
| does an equivalent job as ChatGPT and I find it to rarely be
| useful. Google's stroke of genius was to skip curation and
| algorithmic ranking in favor of a heuristic. Namely, PageRank. I
| know it's gone through years of refinement, tuning and tinkering,
| but the fundamental basis of popularity is just a way more
| reliable and durable approach than trying to intuit what people
| want based on what's on the page. You'd absolute be back to dark
| days of blackhat SEOs bombing results by inundating GPT with
| keywords. It won't work. The popularity model works with and only
| with a network effect of having zillions of successful searches
| to mine. Maybe Bing has just enough data to be useful and maybe
| ChatGPT can do a marginally better job of giving boxed answers to
| specific questions, but that's not the thing that makes search
| valuable.
| photochemsyn wrote:
| If Google were ever to remove the 'verbatim' option (which is
| lacking in other search engines like Bing as far as I can tell)
| it would become much less useful.
|
| Unfortunately, one cannot enable both 'time' and 'verbatim'
| option under Tools in Google Search. I guess I should go ask
| ChatGPT why that is the case...
| 29athrowaway wrote:
| This is not a real phenomenon, but the ad revenue from this
| article will.
| jasmer wrote:
| Yes and no.
|
| 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.
| sys32768 wrote:
| Maybe what we need is an all-seeing AI browser plug-in that
| transforms and decrapifies the SERPS and sites themselves.
| dilap wrote:
| Microsoft's integration of ChatGPT with Bing is really bad. No-
| one wants a busy search page with a side-bar of ChatGPT; what's
| the point of that?
|
| 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.
| [deleted]
| jurmous wrote:
| In the demo there was a clear Chat tab so you could go into
| chat mode. With the sources below each answer.
|
| 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.
| goatlover wrote:
| 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.
| RockyMcNuts wrote:
| I haven't seen anything like Bing + ChatGPT since the Road
| Runner's rocket powered roller skates.
| mattwad wrote:
| 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.
| antihipocrat wrote:
| 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.
| jurmous wrote:
| 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.
| wcoenen wrote:
| "The new Bing also cites all its sources". That's a quote
| from the microsoft announcement.
|
| https://blogs.microsoft.com/blog/2023/02/07/reinventing-
| sear...
| bergie wrote:
| And users of the New Bing will certainly verify that the
| sources say what ChatGPT claims they do?
| mistercow wrote:
| If they don't, then the traceability of traditional
| search results is just as useless.
| dilap wrote:
| Yes, it's a good point -- in its current form it's a bit hit
| or miss, since it can completely lie to you.
|
| 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.
| TheCoelacanth wrote:
| ChatGPT lies to your face, while Google just finds other
| peoples lies and shows you a list of the best ones.
| emodendroket wrote:
| And the latter gives me a lot more to go on when I wish to
| evaluate what I'm reading.
| dyno12345 wrote:
| and by "best" we mean interspersed within 12 pages of
| heavily ad laden blogspam
| GreedClarifies wrote:
| 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:
|
| Rare: 120-125degF (49-52degC) Medium-Rare: 130-135degF
| (54-57degC) Medium: 140-145degF (60-63degC) Medium-Well:
| 150-155degF (66-68degC) Well-Done: 160degF (71degC) 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.
| cjm42 wrote:
| 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.
| nearbuy wrote:
| 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 130-135degF
| (54-57degC) for medium rare, etc.
| emodendroket wrote:
| "It tells me the right answer" and "I trust it to give me
| the right answer" are two different propositions.
| basch wrote:
| Trust but verify
| emodendroket wrote:
| If I need to verify the information somewhere trustworthy
| why not just skip the first step where I get unreliable
| information?
| nearbuy wrote:
| 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).
| ajdoingnothing wrote:
| 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.
| eclipxe wrote:
| And the spammy "set your default to Bing to get priority
| access". Ugh. It's still MS.
| strangescript wrote:
| This, I nearly laughed out loud when I saw it. They still don't
| get it. Google literally figured this out 20 years ago and beat
| yahoo.
| kazinator wrote:
| > _Once trained on this giant corpus of natural language, the
| chatbot can, when prompted by users' instructions, produce a
| fluently written answer rather than merely serving up a list of
| links._
|
| A word salad of untrustworthy bullshit instead of the pages you
| were looking for is not going to upend search.
|
| It's not a replacement for search in any way.
|
| Now if the search engine could find pages which satisfy complex
| queries in natural language, referencing content and
| relationships among content, that could be something.
| theonlybutlet wrote:
| 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.
| ilc wrote:
| People seem to forget: AI is about data, the ability to process
| it, and having a few smart folks to do algorithms. The third part
| is actually the smallest and easiest part of the trilogy for AI.
|
| Google, has all three. The real question is can they not shoot
| themselves in the foot while doing it.
|
| Also SEO will always target the market leader.
|
| As far as Bing's results: I keep thinking Google is trashy. Then
| I use Bing and I remember just how good Google is. That's my
| personal opinion. I am NOT going to claim they are SEO, and spam
| immune, far from. But they seem to do better than Bing in getting
| what I mean right.
|
| ChatGPT may help MS, but is it a bandaid? Is it just a good PR
| bump? Who knows... Displacing Google is a large task.. and not
| one I'm sure I want MS to win. But I look forward to them trying,
| if only to make Google do better.
| amelius wrote:
| > People seem to forget: AI is about data, the ability to
| process it, and having a few smart folks to do algorithms. The
| third part is actually the smallest and easiest part of the
| trilogy for AI.
|
| MS has them all three too.
|
| And since, as you say, the algorithm part is not the most
| difficult part, others may enter the playing field soon (we
| already have DDG and Kagi, for example, with Kagi now
| experimenting with LLMs too).
| ilc wrote:
| The compute side needs to be solved with money. That may be a
| hurdle for DDG/Kagi.
|
| MS has the money. Data is by far and away the hardest part,
| and DDG's own privacy policies etc will hurt it here, alas.
|
| Personally, I think it is Google's race to win. But they have
| to DO it. If I start getting better results off DDG or Bing,
| I'll switch. I'm fickle, and own no loyality to Google.
|
| I just want my StackExchange answers faster, before Google
| Coder, and Co-Pilot replace me. /s
| paulpauper wrote:
| It's way too premature to say that ChatGPT will overtake Google,
| not to mention Google still derives about half of its income from
| Youtube and 3rd party publisher ads. Every few years the media
| runs with some story about how Bing, Yahoo or whatever will
| overtake Google. Never even comes close.
| jsnell wrote:
| > Google still derives about half of its income from Youtube
| and 3rd party publisher ads
|
| Their Q4 2022 revenue was $76B [0]. YouTube + 3p ads were a
| combined $16.5B. That's about 20%, not about half.
|
| [0]
| https://abc.xyz/investor/static/pdf/2022Q4_alphabet_earnings...
| ElectricSpoon wrote:
| My fear is that more AI will hinder our ability to literally
| search for stuff. The future I dread includes more profiling, a
| stronger search bubble, all of which will just make it the death
| of the objective search engine. As fascinating as AI can be, I
| don't think it's what search engines are missing. That is
| certainly not what I need.
|
| Even today, engines rank your results by geoip, trying to be
| smarter than you ask them to be. Two individuals doing the same
| quoted search will get different results. Perhaps I'm just
| getting old, but I do miss when searching was a matter of writing
| a good query, not a matter of what the engine thinks you will
| want to ask next and what else might interest you.
| dontreact wrote:
| I would bet money that the answer here is no
| cwilby wrote:
| Good odds:
| https://en.wikipedia.org/wiki/Betteridge%27s_law_of_headline...
| 3327 wrote:
| [dead]
| marginalia_nu wrote:
| Yeah, people underestimate Google.
|
| They 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.
| [deleted]
| chem83 wrote:
| Microsoft's insistence on reusing the bing brand and website is
| baffling to me. No one wants to use that shit, but in classical
| Microsoft fashion, they're too attached to old decisions. What a
| missed opportunity to do like they did with IE and kill it in
| favor or something new and fresh.
|
| Ultimately, Microsoft will make it easier for Google to catch up
| because its internal culture is and will continue to be
| unchanged, no matter how much technology they inject from OpenAI.
| Make no mistake, behind the shiny PR, it's still the messy Bing
| AI organization, the demoralized Microsoft Research organization
| and good ol' Microsoft.
| siva7 wrote:
| So i tried Bing again after almost a decade for their ChatGTP
| integration. I can't be the only one who thought this is
| Yahoo/AltaVista/Lycos/etc. revisited. It's a fucking portal
| spamming me with news coverage, not a search engine
| saudade97 wrote:
| 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.
| [deleted]
| bitcurious wrote:
| Remember when image search didn't give up after ~100 images?
| Google has definitely gotten worse, and it's obviously margins-
| motivated.
| ranting-moth wrote:
| 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.
| Aeolun wrote:
| 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.
| jeffbee wrote:
| 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.
| ranting-moth wrote:
| Yes, but other search engines existed before Google. They
| weren't very useful or pleasant to use.
|
| 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.
| pirate787 wrote:
| Incorrect, the web was mainstream by 1996, two years before
| Google even launched.
| xyzelement wrote:
| 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.
| jeffbee wrote:
| 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.
| JohnFen wrote:
| This is absolutely right. The web died about then,
| really. What we have now is shameful and embarrassing,
| and society is poorer for it.
|
| 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.
| pirate787 wrote:
| 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.
| tester756 wrote:
| >your searches are focused
|
| 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?
| emodendroket wrote:
| What if indeed? What does that imply to you? I don't really
| care why it is so much better so long as it is.
| OJFord wrote:
| I've used DDG exclusively for about 10 years, it's good enough
| that I don't realise I'm missing out.
| JohnFen wrote:
| > 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.
| Ingaz wrote:
| I think that ChatGPT3 does not matter a lot.
|
| But a lot of people fed up with Google and will be glad to try
| something different.
|
| It's like when Apple came and eat 15-20% of market of notebooks.
|
| Dominance of Microsoft still not ended.
|
| Actually I suspect that Yandex search is better - I like how they
| preview answers for technical questions. Picture search - seems
| that Google is the worst.
|
| Maybe it's time to start search different topics in different
| engines.
|
| Hm. Actually AI could help to implement such functionality
| danShumway wrote:
| I don't understand this hype and I feel like I'm looking at
| different products than everyone else is. There are very few
| complaints I have about Google that I think this technology helps
| solve, and for most of my complaints, getting summaries of
| searches makes the situation worse, not better. To be completely
| clear: even if the AI was _perfect_ , I don't know that I want
| even an actual human being to sit down and summarize an answer to
| my question rather than show me a list of search results.
|
| The problem with search is not that our answers aren't summarized
| well, it's that the quality of information returned for those
| searches is getting increasingly worse, and we are getting
| increasingly worse at categorizing or filtering that information
| in any useful way. And LLMs pulling information in and
| summarizing it for me is... not helpful? It's summarizing the
| same garbage, except now sometimes it also summarizes it wrong.
|
| But it's not even an issue with the quality (although the quality
| of information from LLMs is also pretty over-hyped I think).
| Conceptually, I don't know that this is a product that I would
| ever want. I can't think of any time where I've sat down to do a
| search on Google or DuckDuckgo and thought, "You know what I
| want? I want these results presented to me in a less structured
| format using natural language and with less granular knowledge
| about where each specific statement is coming from."
|
| At least Bing seems to be trying to do inline citations in some
| of its answers, which is a step up over Google's AI announcement,
| I guess?
|
| Maybe I'm just in the minority on that. Users seem to like this a
| lot. But my ideal version of the Internet is one that decreases
| the number of abstractions and layers and summaries between
| myself and primary data rather than increasing them. My ideal
| Internet is a tool that makes it easier for me to actually find
| things, not a tool that increases the layers between me and the
| raw source/information that I'm looking for. I already have
| enough trouble needing to double-check news summaries of debates,
| events, and research. Getting another summary of the summaries
| doesn't seem helpful to me?
|
| I can think of some ways where I might use an LLM in search, even
| really exciting ways where maybe it could help with
| categorization or grouping, but it doesn't seem like Google/Bing
| are interested in pursuing any of that. I look at both the Bing
| and Google announcements and just think, "why are you making it
| worse?" But who knows, maybe the actual products will sell me on
| the concept more.
| emodendroket wrote:
| You know what it reminds me a lot of? CPedia. It's basically
| the same concept, though, from the sound of it, much more
| capably executed.
|
| I do see LLMs as potentially more useful for "fanciful"
| queries, like "what can I make with kale, tomatoes, and
| mushrooms?"
| guyzero wrote:
| Considering people still go to Bing just to type "Google" I think
| the answer is no.
| rvz wrote:
| No.
|
| The one to end Google's search dominance is an open source
| ChatGPT alternative. That will disrupt both Google, Bing and
| OpenAI.
|
| It's that simple.
| stephc_int13 wrote:
| Google is already a zombie company, and has been for some time,
| still insanely rich and powerful, but they're not cool anymore
| and I think they could be replaced very easily.
|
| Large corporations can seemingly stay alive and kicking for a
| long time after their death. Nokia, Kodak, Palm, RIM just to name
| a few.
|
| I've witnessed the demise of Palm, then Nokia and RIM, following
| similar patterns, when they start reacting it is already over.
|
| RIP Google.
| gcanyon wrote:
| I'm old enough that I remember switching between Yahoo,
| AskJeeves, AltaVista, and others, before abandoning them all for
| Google. I also remember experimenting with a friend to test the
| search engines, and I remember the question/query I used to
| perform the test: I had (at the time) a vague recollection that
| the level of the Atlantic and Pacific oceans near the Panama
| Canal is different; that in addition to raising ships over the
| isthmus, the canal has to raise them overall in one direction,
| and lower them in the other. That seems bizarre, since the oceans
| are connected south of South America, but that was my memory, so
| I asked the search engines. Google was the one engine that
| returned sites that confirmed my vague memory.
|
| So of course, I just tried this with ChatGPT. It glitched mid-
| response, but here's the entire exchange:
|
| Me: Is the level of the ocean the same on both sides of the
| Panama Canal?
|
| ChatGPT: No, the ocean level is not the same on both sides of the
| Panama Canal. The Panama Canal is a man-made waterway that
| connects the Atlantic Ocean to the Pacific Ocean, and its locks
| raise and lower ships to accommodate differences in sea level
| between the two oceans. -- Load failed -- I hit retry The
| Atlantic Ocean side of the canal is higher than the Pacific Ocean
| side, with a difference in elevation of approximately 26 meters
| (85 feet). This difference in elevation is compensated for by a
| system of locks, which raise and lower ships to the appropriate
| level for transit through the canal. The locks fill with water
| from the higher ocean and drain into the lower ocean, allowing
| ships to pass from one ocean to the other without having to
| navigate significant differences in sea level.
|
| Me: Why is the level of the ocean different?
|
| ChatGPT: The difference in sea level between the Atlantic and
| Pacific sides of the Panama Canal is due to various geological
| and oceanographic factors.
|
| One of the main reasons is the shape of the landmass and ocean
| basins. The Atlantic Ocean is relatively shallow and has a
| broader continental shelf, while the Pacific Ocean is deeper and
| has a narrower shelf. This shape influences the ocean currents
| and tides, and helps to maintain a difference in sea level
| between the two oceans.
|
| Another factor is the prevailing winds and currents in the
| region. The trade winds in the Pacific and the prevailing
| westerlies in the Atlantic both play a role in shaping the sea
| levels on their respective sides of the canal.
|
| Additionally, the location of the Panama Canal at the narrowest
| point of the Central American isthmus has a significant impact on
| the difference in sea level between the two oceans. The geography
| of the region funnels ocean currents and water into the narrow
| channel, leading to differences in water pressure and sea level
| on either side.
|
| In summary, the difference in sea level between the Atlantic and
| Pacific sides of the Panama Canal is due to a combination of
| geological and oceanographic factors, including the shape of the
| landmass and ocean basins, prevailing winds and currents, and the
| geography of the region.
|
| -- comment -- Although ChatGPT is correct that the levels differ,
| it is wrong about the amount: it's nowhere near 85 feet. It gives
| believable reasons for the difference, but doesn't mention tides,
| which (as I understand it) are a significant factor. It also
| doesn't mention salinity, which (again, as I understand it) is
| also a factor. I gave it a chance to catch the error:
|
| Me: Is the difference really 85 feet?
|
| ChatGPT: The difference in elevation between the Atlantic and
| Pacific sides of the Panama Canal is approximately 26 meters, or
| approximately 85 feet. However, it's worth noting that this
| figure can vary slightly due to tides, seasonal changes, and
| other factors. The exact difference in elevation can also depend
| on the specific location within the canal, as some areas may be
| slightly higher or lower than others. Nevertheless, the
| difference in elevation between the two sides is typically around
| 85 feet.
|
| -- Comment -- No luck correcting that 85 feet number. I also
| asked about tides and salinity:
|
| Me: Do tides or salinity contribute to the difference?
|
| ChatGPT: Tides and salinity can contribute to the difference in
| sea level between the Atlantic and Pacific sides of the Panama
| Canal, but the main factor is the shape of the landmass and ocean
| basins, the prevailing winds and currents, and the geography of
| the region.
|
| Tides do have an impact on the sea level in the canal, as they
| can cause fluctuations in the water level on both sides. However,
| the impact of tides on the difference in sea level between the
| two oceans is relatively small compared to the other factors
| mentioned above.
|
| Salinity can also influence the sea level, as differences in
| salinity can cause water to expand or contract, leading to
| changes in sea level. However, the impact of salinity on the
| difference in sea level between the Atlantic and Pacific sides of
| the Panama Canal is also relatively small, as differences in
| salinity in the canal are primarily caused by fresh water inputs
| from rivers and rainfall, rather than differences in ocean
| salinity.
|
| In summary, while tides and salinity can contribute to the
| difference in sea level in the Panama Canal, the main factor is
| the shape of the landmass and ocean basins, the prevailing winds
| and currents, and the geography of the region.
|
| -- Comment -- Much has been made of ChatGPT's (sometimes
| unfounded) confidence. I don't know enough about the ocean-level
| subject to judge here. Clearly ChatGPT is confident, but is it
| correct? I don't know. Given that a quick Google search wasn't
| able to convince me that ChatGPT is wrong (apart from the 85 feet
| thing) I'm calling this even on the facts. The experience asking
| ChatGPT was clearly easier than Google.
| yunohn wrote:
| > difference in sea level between the two oceans
|
| Honestly, the number of times ChatGPT inserts this and
| variations of fluff is absolutely bordering on insane. Like,
| that was your question - why include it in every single
| sentence of the answer...
| [deleted]
| fdgsdfogijq wrote:
| 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
| hgsgm wrote:
| 4. Google Search already has lots of useful AI already in it,
| but Google didn't want to integrate a racist, confabulating
| chatbot, forgetting that modern users have no preference for
| truth over lies.
|
| Why are you blaming Google for not being perfect while making
| the best free search engine, after you spent your whole life
| refusing to pay for a non-free one?
| fdgsdfogijq wrote:
| 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
| ESMirro wrote:
| 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...
| peyton wrote:
| Everyone on the planet can already talk to racists by
| typing in 4chan.org. In the meantime, I've found ChatGPT
| useful for learning zsh commands.
| ESMirro wrote:
| 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, owned by two unsavoury
| characters who have history failing to protect the most
| vulnerable.
| rafaelturk wrote:
| Well I'm done with Google, looking forward ChatGPT and Bing being
| serious competition
| jay_kyburz wrote:
| I don't want an AI trained on the sea of garbage that is the
| modern web to answer my questions, but I would love an AI to draw
| on a curated, hand crafted, trusted database of the worlds
| knowledge.
| endisneigh wrote:
| I'd be curious to hear from someone who has a non trivial amount
| of money shorting Google. Anyone can say Google sucks.
| meindnoch wrote:
| I'm $5k short GOOG at 10x leverage.
| karmasimida wrote:
| No
|
| Unless Bard sucks too much
| ilc wrote:
| Bard will improve. They will learn.
|
| Data is king in AI. And nobody beats Google there. They will
| figure out how to leverage that advantage.
| 3327 wrote:
| [dead]
| marricks wrote:
| I think it's interesting to consider why touchscreen mobile
| phones won out over their predecessors.
|
| Touchscreens are worse than buttons, it was a new paradigm to
| learn and the feedback of feeling a button, even small one, is
| better than not. Probably what forever doomed the Touch Bar.
|
| Now for search, chat gbt will probably always be worse than a
| list of results you can get yourself for authenticity if you
| cared about truth.
|
| That said... I don't think people care about truth that much
| these days so a response that seems correct is probably good
| enough. Terrifying times we live in folks.
| humanizersequel wrote:
| >Touchscreens are worse than buttons
|
| 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."
| marricks wrote:
| Maybe 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.
| ignite wrote:
| Buttons are much better than touchscreens, if you have a
| fixed interface that fits in the space available.
|
| Touchscreens win when you need multiple interfaces in the
| same amount of space.
| karaterobot wrote:
| 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.
| PaulDavisThe1st wrote:
| 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.
| freitzkriesler2 wrote:
| 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.
| ESMirro wrote:
| 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...
| jay_kyburz wrote:
| 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.
| timeon wrote:
| > Now for search, chat gbt will probably always be worse than a
| list of results you can get yourself for authenticity if you
| cared about truth.
|
| Irony of this article, predicting end of Google, is that
| articles like this are going to be replaced by these summaries
| too.
| bobthepanda wrote:
| Touchscreen keyboards disappear and free up their real estate.
| That's the main advantage on phones.
| marricks wrote:
| Yep! And people just want big screens to view content.
| doctor_eval wrote:
| Well what else are we supposed to do with them?
| chias wrote:
| 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.
| rileyphone wrote:
| 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.
| phailhaus wrote:
| 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.
| candiodari wrote:
| 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.
| Invictus0 wrote:
| 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.
| chomp wrote:
| 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.
| LightDub wrote:
| How old are you? I don't mean this to be offensive. It's just
| I remember when the same was said about Microsoft when Google
| was up and coming.
|
| I really am getting old ...
| fdgsdfogijq wrote:
| I would love to see google fail. They have held the internet
| hostage for far too long
| outside1234 wrote:
| No
| rexreed wrote:
| 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.
| RosanaAnaDana wrote:
| 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.
| weaksauce wrote:
| 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
| amatix wrote:
| https://kagi.com ?
| [deleted]
| svachalek wrote:
| 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.
| johnla wrote:
| This.
|
| 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?
| Hamuko wrote:
| 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.
| beamgirl wrote:
| 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.
| adamrezich wrote:
| 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.
| beamgirl wrote:
| 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
| pixl97 wrote:
| Also think of how many people will sell their digital
| persona to sell AI generated spam for a little cash in
| return. Ain't nuthin safe from spam.
| runnerup wrote:
| > AI trained on AI generated output becomes crap
| surprisingly quickly
|
| Yet GANs work quite well
| quickthrower2 wrote:
| 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.
| sixQuarks wrote:
| Agreed, I am looking forward to the disruption of google.
| lagrange77 wrote:
| I am looking forward to the disruption of SEO.
| ezoe wrote:
| The last year? Google search was defeated by SEO for more than
| a decade ago for non-English language such as Japanese.
| doctor_eval wrote:
| > This issue with with Googles failure to respond to the deluge
| of SEO driven content in their searches.
|
| I'd argue that they even encouraged it.
| krisroadruck wrote:
| 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.
| basch wrote:
| 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.
| cjbgkagh wrote:
| it sells more ads at a higher price
| blantonl wrote:
| This is a fair argument to make. Normalizing web site
| metadata (which is essentially what SEO is) resulted in
| Google getting crowdsourced work done for them for free.
|
| It has been a self-fulfilling positive feedback loop since
| then.
| mywittyname wrote:
| 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?"
| Aeolun wrote:
| I imagine that ChatGPT would be useless for these things.
| Immediately saying "I'm sorry dave, I can't answer that" even
| now.
| DrSiemer wrote:
| 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.
| kikokikokiko wrote:
| 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.
| TheCondor wrote:
| Isn't Google data driven?
|
| 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?)
| AtNightWeCode wrote:
| 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.
|
| And why is the GoogleBot still on HTTP 1.1...
| massysett wrote:
| 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.
| qrio2 wrote:
| 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?
| Kwpolska wrote:
| > 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.
| kogus wrote:
| I just checked and sure enough, the clickable
| Goooooooooogle is still there at the bottom of search
| results, with ten clickable "o"s.
| jeffbee wrote:
| 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.
| dmd wrote:
| > Haven't seen that in a while, right?
|
| It's still there right now.
| joe_the_user wrote:
| 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.
| sidewndr46 wrote:
| 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.
| ignite wrote:
| 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.
| jgalentine007 wrote:
| I've been having to use Bing to find things. BING.
| gregors wrote:
| >>> I view Google as the yellow pages
|
| So do I. I can't tell you the last time I even held yellow
| pages in my hands.
| zug_zug wrote:
| For one, when I search a recipe, I want less than a 30 page
| document. I've wanted this for 20 years, and so has everybody
| else.
| hnuser847 wrote:
| 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.
| dahdum wrote:
| 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.
| rich_sasha wrote:
| 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.
| massysett wrote:
| OK, I searched "chinese embassy" and the top link is
| "Embassy of the People's Republic of China" at
| http://us.china-embassy.gov.cn.
|
| I'm willing to accept that maybe you are exaggerating to
| make a point. Maybe you have a better example that is
| actually illustrative?
| [deleted]
| freitzkriesler2 wrote:
| 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.
|
| This is why googles utility has collapsed.
| forrestthewoods wrote:
| Here's an example for you.
|
| 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.
| helf wrote:
| 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".
| basch wrote:
| 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.
| emodendroket wrote:
| > It now returns results worse than crawlers from the
| previous era.
|
| That is an absurd exaggeration.
| squiffsquiff wrote:
| 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
| basch wrote:
| 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.
| emodendroket wrote:
| Then ChatGPT won't satisfy you either.
| basch wrote:
| It depends on how state works.
|
| 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."
| lamontcg wrote:
| > 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.
| JohnFen wrote:
| > What are people expecting out of Google that it's not
| delivering?
|
| 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.
| bawolff wrote:
| A start would be to rank official php/python/etc docs higher
| than clickbait sites like geeks4geeks
| devonbleak wrote:
| Amen to this
| emodendroket wrote:
| I also challenge people's memory of it being so much better.
| Was it really? Or just different?
| sshine wrote:
| It was mostly better.
|
| 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.
| squiffsquiff wrote:
| 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.
| emodendroket wrote:
| 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.
| squiffsquiff wrote:
| You're comparing Google how it was then. Not how it is
| now
| emodendroket wrote:
| With Google right now I find what I am looking for almost
| all of the time. I can't say that about the golden oldies
| you're praising.
| polyamid23 wrote:
| I want a button: "never show me content from this domain
| again".
| polyamid23 wrote:
| 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.
| sidewndr46 wrote:
| 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.
| massysett wrote:
| 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.
|
| https://www.verybestbaking.com/toll-
| house/recipes/original-n...
|
| https://www.allrecipes.com/recipe/10813/best-chocolate-
| chip-...
| dahdum wrote:
| It's buried near the bottom of the page, but here's your
| huckleberry: https://www.seriouseats.com/the-food-lab-best-
| chocolate-chip...
|
| Lots of trash out there but Serious Eats is good quality.
| luckylion wrote:
| > What are people expecting out of Google that it's not
| delivering?
|
| Not optimize for "most documents indexed" but "highest
| quality of results". One of them encourages adding spam to
| their index, the other encourages removing spam from their
| index.
| gipp wrote:
| There are _giant_ teams of people at Google whose only job
| is trying to define things like "spam" and "seo abuse"
| more precisely in more diverse contexts. There are equally
| large armies of people outside of it trying to outwit the
| first group and find more and more elaborate loopholes and
| workarounds.
|
| HN is constantly pushing this notion that "spam" is some
| well-defined, solvable problem, so obviously Google wants
| it. That narrative just doesn't make sense from any angle.
| The notion that more click bait _improves_ Google 's bottom
| line is absurd
| basch wrote:
| Their giant teams are an organizational failure then.
|
| Product reviews alone, whether it is enterprise software
| or sports clothing should be something that they can
| easily comb through by hand, as humans, and uprank sites
| that are putting out more than affiliate link assemblies.
| bbor wrote:
| Why wouldn't they do this, if it's scalable and
| profitable? Is your theory just "incompetence"? I can't
| prove that's wrong, but I feel the simpler answer is more
| convincing; that handing off page rank to an army of
| minimum wage call center workers (for every country &
| language in the world...) wouldn't be more effective than
| the existing algorithms at filtering out spam.
| basch wrote:
| Some form of paralysis. They dont have a single leader
| who has taken responsibility for it and corrected it.
| CEO/SVP has too many pots on the stove.
|
| Im legitimately asking, who is responsible for Search at
| Google? Prabhakar Raghavan is SVP, Search, Assistant &
| Ads, and I click under him, he has 8 product groups
| reporting to him, and none of the people are responsible
| for Search. Yossi Matias is responsible for Search
| Engineering.
|
| https://theorg.com/org/google
|
| It may at first come off as a laughable answer, but
| Google Search has been in a directionless spiral since
| Marissa Mayer left. Her Yahoo tenure was not well
| received, but at Google she cared about the end quality
| of the product. Her title was Search Products and User
| Experience. Notice how we have gone from User Experience
| to Search Engineering, forgetting about the people who
| actually use the product.
| Fede_V wrote:
| Absolutely: the challenge is that any signal that you use
| to identify "good websites" from "bad websites" will be
| adversarially optimized by incredibly motivated people.
|
| You are dealing with a moving target that has a huge
| financial incentive. It's a very difficult problem.
| basch wrote:
| I don't agree. You start whitelisting good content
| manually. If babygearlab is the best result for baby
| gear, you start hardcoding it. If seriouseats is the best
| result for recipes, you hard code it. If someone better
| comes along, they get moved up the priority list.
|
| You figure out a way to crowdsource certain decisions and
| establish who you can trust. Ask them questions with
| right and wrong answers. You start to tackle it one
| product category at a time. Instead of pagerank, which
| was a web of who linked to who" you start figuring which
| voters you have who consistently turn in good feedback.
|
| This is some form of metamoderation that slashdot tried
| to implement.
|
| If you are going to be a tastemaker, stop hiding behind
| "the algorithm" having some mind of its own that cant be
| controlled.
| bbor wrote:
| This discussion is pretty sad and frustrating for me. I
| think your conclusion ("Google has no motive to encourage
| spam content that rises to the top using SEO tricks") is
| about as convincing as it gets, but it's completely
| drowned out by a very vague sense that google is a big
| company and therefor it's making search worse on purpose.
| No amount of well-worded HN posts are gonna sway people,
| imo...
|
| Luckily HN posters don't exactly represent a meaningful
| portion of the population.
| Aeolun wrote:
| Search before Google was bad. e.g. I could easily ignore 80%
| of the results on the first page, but at least it was all
| actual content.
|
| 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.
| Stagnant wrote:
| 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.
| unicornmama wrote:
| People don't use Google to search the web. They use Google to
| find answers.
| DrSiemer wrote:
| 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.
| jononor wrote:
| 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?
| DarknessFalls wrote:
| > 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.
| krackers wrote:
| 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.
| [deleted]
| Bhilai wrote:
| Sorry to break it to you folks but if you hated your data being
| with Google, you are in for a surprise on how atrociously bad
| Microsoft is at privacy and security. Multiple close friends who
| have worked at Microsoft tell me that search history data - who
| is searching what, is basically sitting in systems with ACLs so
| bad that 20-30K employees have access through transitive
| membership of groups. To access a customer's data you just need
| to know token which is logged everywhere and is apparently very
| easy to generate. I have heard horror stories from them about
| privacy incidents which never went public.
|
| From what I know about Google, they are serious about least
| privilege type of stuff internally and employees dont get
| arbitrary unbound access to systems or data.
| revskill wrote:
| It's not much about Microsoft. At least it improved human life
| in serious ways (Typescript, VSCode,...). What did Google bring
| to my life ? Nothing except for spam stuffs from Ad, Email,...
|
| You're responsible for your data, not Google, not Microsoft.
| kareemsabri wrote:
| I can't imagine thinking _typescript_ improved human life
| more than Google Search
| eclipxe wrote:
| Peak HN.
| rewgs wrote:
| What an absurd statement. I don't have especially strong
| feelings for Google in any direction, but I can't deny that,
| even if Google had _only_ done search or Maps, that alone
| would be a massive boon for society.
| erklik wrote:
| Uh... Maps? Open, Permissive phone OS compared to the
| alternative? Greatest entertainment/information system,
| especially one that's democraticsed producing media?
|
| In terms dev-related stuff, TensorFlow - literally something
| that's made today's ML possible, Kubernetes, BigTable,
| MapReduce, and yknow, that good old thing called Chrome..
|
| I understand hating on Google. They're not that great, but
| none of the FAANG are "great".. They all have some terrible
| bits, some good bits. However, to say that Google has not
| provided anything except "spam stuffs" is very wrong.
|
| Search alone has changed the entire way that humans consume
| information. I would say that today's internet landscape, for
| better or worse, would not exist without Google.
| amartya916 wrote:
| While it might be fashionable to hate on Google, the question
| "What did Google bring to my life" seems really odd. I can't
| believe I have to say this but search, and more importantly
| good/fast search, is to Google's credit. Typescript and
| VSCode all have, and will continue to have alternatives, but
| for a long time, Google was (some may argue it still is) the
| bleeding edge of search. Anyway, there might be a
| generational thing at play here, if so, I meant no
| condescension.
| revskill wrote:
| You're making assumptions. I listed facts.
| thefurdrake wrote:
| Yeah, I'm gonna need to see some citation on how
| Typescript and VSCode improved life for humanity. Break
| out some of them facts you're talking about.
| revskill wrote:
| I specify "my life", not other's life, and it's a fact.
| Why bother then (i'm curious)?
| canadianfella wrote:
| [dead]
| chris_wot wrote:
| So you think that Google doesn't do fast search? OK.
| mc32 wrote:
| I wouldn't be extraordinarily surprised if this is the case,
| but I do not expect it to be as lax as you suggest and given
| how it's presented to us it reads like someone trying to get
| people to not look at something. If you have things you can
| present as evidence that would carry water for your argument,
| otherwise it's random inflammatory claim on in the internet.
|
| And I agree, Google does take security more seriously than most
| places.
| kikokikokiko wrote:
| 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.
| marcopicentini wrote:
| It's been a while since they stopped innovating.
|
| 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...
| josu wrote:
| >It has been many years since Google has launched an innovative
| new product.
|
| Stadia launched in 2019.
| silisili wrote:
| Stadia wasn't really that innovative, how many times has
| cloud/streaming gaming been done before? I can think of at
| least 3.
|
| Also, it's already dead.
| Sebguer wrote:
| Yeah, OnLive did it back in 2003!
| mertd wrote:
| Which three? Did they actually work with reasonable input
| latency?
| silisili wrote:
| I thought of OnLive, Shadow, and Geforce Now.
|
| 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.
| snuxoll wrote:
| PlayStation Now already existed for years as well.
| rchiang wrote:
| Which they got through their acquisition of Gaikai
| (considered a competitor of OnLive).
| i_love_cookies wrote:
| [dead]
| bobthepanda wrote:
| I suppose successful new product? It's already closed.
| kec wrote:
| OnLive was 2009, PS Now was 2014, and Geforce Now launched in
| 2015.
|
| Stadia might have been well executed from a technical
| standpoint but AAA game streaming wasn't exactly a new and
| innovative idea in 2019.
| joshruby16 wrote:
| And it's dead.
| system16 wrote:
| 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.
| bitL wrote:
| 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.
| hoppyhoppy2 wrote:
| Note that YouTube was acquired by Google in 2006; it's not a
| product that was launched by Google.
| awad wrote:
| 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.
| adam_arthur wrote:
| Agreed that a lot of Google's bets don't get enough
| press/credit re investment potential.
|
| At the same time, a lot of these platforms ran effectively
| unopposed for many years, and now competition in advertising
| is spreading quite rapidly
| [deleted]
| likeabbas wrote:
| 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).
| scarmig wrote:
| Waymo has always been just a year or two from breaking
| through.
|
| Google's gotten through the first 95% of the work, but the
| remaining 95% is gonna take awhile.
| xyzzyz wrote:
| 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.
| peyton wrote:
| Innovation is the practical implementation of new inventions
| to deliver value. Google invented but does not seem to have
| innovated.
| lyu07282 wrote:
| 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.
| somethoughts wrote:
| 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.
|
| I guess only time will tell.
|
| [1] Dropbox Versus The World
| https://www.fastcompany.com/3042436/dropbox-versus-the-world
| mejutoco wrote:
| Last time I tried to sync my computer to gdrive I waited 30
| days before giving up on gdrive. Dropbox took less than 2
| days, and stayed responsive.
| somethoughts wrote:
| 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.
| jibe wrote:
| _Google, Maps, Youtube are of daily use they are monetized
| exclusively by advertising._
|
| I don't know how much. Money it makes, but there is paid API
| access to maps.
| adam_arthur wrote:
| 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
| scarmig wrote:
| 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.
| adam_arthur wrote:
| 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
| valley_guy_12 wrote:
| The article starts, "Nestled in the hills of Mountain View",
| which is worrisome, because as anyone with even a passing
| familiarity with Silicon Valley geography knows, Mountain View is
| mostly flat. And Google's Mountain View offices are located on
| reclaimed baylands, which are especially flat.
|
| I wonder if the article authors were thinking of Xerox PARC's
| offices in Palo Alto's hills? Or the road named "Sand Hill Road"
| that used to have some venture capitalist offices? Other than
| those offices I can't think of any significant hill-based offices
| in Silicon Valley.
| [deleted]
| alexfromapex wrote:
| It's honestly shocking that it's had such a long run. An increase
| in high quality ways to sift through information will be a net
| benefit for society.
| [deleted]
| acqbu wrote:
| https://archive.is/0ULyU
| swayvil wrote:
| I actually prefer Bing these days. (And I don't even run Windows)
|
| Google search results are just screwy. Probably all that money is
| interfering with the algorithm.
| josefresco wrote:
| Let us think about the defaults in our life:
|
| 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.
| bloblaw wrote:
| 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.
| lyu07282 wrote:
| 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)
___________________________________________________________________
(page generated 2023-02-08 23:00 UTC)