[jrflowers]

There is a group of people that are ardent in the conviction that if we wait long enough and wish hard enough that ChatGPT will replace the concept of googling things.

I’m personally open to that being the case with some LLM someday, but there’s a lot of people ideologically and financially invested in that perception being accurate today and applying to ChatGPT in particular.

People hate it when you point out that they’ve confused the modern equivalent of a Speak and Spell with The Overmind.

[dale_glass]

To a large extent this is already viable.

Yes, ChatGPT doesn't know what it's talking about. But Google is so bad these days, that ChatGPT in many circumstances can do much better even while being far from perfect.

[rob74]

It doesn't know what it's talking about, but it is still stating it in a very convincing way. To me, that's even worse than bad search results which you can instantly recognize as bad.

[jrflowers]

>But Google is so bad these days, that ChatGPT in many circumstances can do much better even while being far from perfect.

Can you give some examples of how ChatGPT “does better” than a human searching for something and then using their own cognition to make sense of it?

If Google was an LLM then I’d agree with you, but the idea that googling something somehow skips the step of using critical thinking to understand what is on your screen seems pretty new to me.

[Al-Khwarizmi]

What percentage of searches actually require any critical thinking at all? The Internet is not always a fountain of intellectual growth, sometimes it's just a tool.

I'll give you a concrete example where it does better than search: my last Google search was about how to zip a whole folder in the Linux terminal (I must have searched for that dozens of times in my life, but I don't do it very often so it doesn't stick).

I saw the results, and I noticed that they were mostly transcriptions, summaries or extensions of man pages listing all the options, which would take a few minutes to skim through and look for the relevant options (which is what I wanted to avoid by Googling, otherwise I would have used man in the first place).

So I switched to the ChatGPT tab, asked, got the exact command I wanted, done.

[jrflowers]

Thanks for the example!

While I would definitely, definitely think critically before running a command from the internet, I can see how that use case makes sense for ChatGPT if you’re willing to roll that way.

>…take a few minutes to skim through and look for the relevant options (which is what I wanted to avoid by Googling…

Ah, I see! We are using the phrase “googling” differently here. I explicitly mean googling as a verb that involves reading and parsing information, not the act of avoiding reading or parsing information.

[dale_glass]

> Ah, I see! We are using the phrase “googling” differently here. I explicitly mean googling as a verb that involves reading and parsing information, not the act of avoiding reading or parsing information.

In order to make things friendlier towards search, nigh any answer you find will be drowned in a sea of junk. Eg, Googling sends me to: https://phoenixnap.com/kb/how-to-zip-a-file-in-linux

It does have an answer, around the middle of the page.

https://i.imgur.com/jVEyCZe.png (useful answer on the bottom)

Here's what I actually want:

https://i.imgur.com/tXOEIIX.png

What I actually want most of the time is the closest equivalent to "Hey Bob, what's the command to zip up a folder on Linux?"

[typon]

This is my use for ChatGPT around 90% of the time. The other 10% is trying to get it do something more complicated, getting frustrated and giving up.

[SAI_Peregrinus]

I get the correct command in the highlighted search result at the top, and in the first result: https://i.imgur.com/FdDAz64.png

Of course I only use relevant keywords in my search. Adding extra words like "how to" will add results containing those words, which tends to mean more SEO spam.

[Al-Khwarizmi]

Once I saw the command, I knew that it made sense and it was the right one, because it's something I had in the back of my head, I just couldn't summon the specific syntax.

I wouldn't count that as critical thinking, although I guess it depends on how you define the term.

[hartator]

‘zip -r’ is first result for https://serpapi.com/playground?q=How+to+zip+folder+in+linux+...

[Al-Khwarizmi]

Yes, I also got that first result that (from the snippet) seems to go straight to the command, but the funny thing is that the link doesn't work, at least from my end. And the next ones are all lists of commands that would take a nontrivial amount of time to skim, as I mentioned.

[jrflowers]

I don’t follow. Both ChatGPT and Google gave you the same command, but Google’s response contained links, therefore Google’s response is less good.

Wouldn’t you have had an identical experience copy and pasting from Google as you did ChatGPT? Did you recognize the correct command immediately in ChatGPT but have difficulty recognizing that same command on Google’s page?

[3np]

The crucial component is that you verified the result (by running the suggested command and observing it giving you the expected result).

This is different from asking it for an explanation or definition of something and not cross-checking every "fact".

[Technotroll]

> Can you give some examples of how ChatGPT “does better” than a human searching for something and then using their own cognition to make sense of it?

Certainly! ChatGPT outperforms human search and cognitive processing in several ways. For instance, when you require a quick, step-by-step tutorial to fix an issue in an application or program, ChatGPT excels. Instead of searching for an online tutorial yourself, ChatGPT provides you with immediate, on-the-fly instructions. This saves you from sifting through search results and having to verify the quality of each tutorial before attempting them. ChatGPT's instructions are already evaluated based on probability, eliminating the need for time-consuming quality checks. By receiving a concise, step-by-step list, you can swiftly proceed with your task, making it significantly more efficient than relying solely on manual searching and critical evaluation.

[jrflowers]

I’m sorry, I should be more clear by what I mean by example. Rather than hypothetical possible categories of tasks, can you give a particular task in which ChatGPT does better than googling information and thinking about the information that’s displayed to you?

A task in this case could be finding out where a particular Vermeer is hung, or which viscosity of oil to put into your car’s engine — a specific concrete task in which ChatGPT provides you with knowledge better than a web search does.

I won’t argue that ChatGPT is better at writing lists than Google is. Google isn’t a website that writes lists so that comparison would be pointless.

[Technotroll]

Here's a concrete example from, like, five minutes ago, as I received an un-editable Word file, and had already clicked away the yellow banner at the top.

Technotroll: How do I enable editing of word document?

ChatGPT: To enable editing in a Word document, follow these steps:

Open the Word document you want to edit.

If the document is in "Read-Only" mode, you'll need to enable editing. Look for a yellow or red banner at the top of the document that says "Protected View" or "Read-Only." Click on the banner, and you should see an "Enable Editing" button. Click on it to enable editing mode.

If the document doesn't have a "Protected View" or "Read-Only" banner, it may already be in editing mode. In that case, you can start editing right away.

If you are using Microsoft Word, you can also check the top-right corner of the window. If you see a button that says "Editing Restricted," it means the document has restricted editing. Click on the button and select "Stop Protection" to enable full editing.

In some cases, the document may be password-protected, preventing any edits without the password. If you're prompted to enter a password when trying to edit, you'll need to obtain the password from the document's owner or author.

By following these steps, you should be able to enable editing and make changes to your Word document. Remember to save your changes regularly to ensure your work is preserved.

Technotroll: I clicked the x on the yellow banner. Now what?

ChatGPT: If you accidentally clicked the "x" on the yellow banner in Microsoft Word, which appears when a document is in "Protected View" or "Read-Only" mode, you can still enable editing by following these steps:

Click on the "File" tab in the top-left corner of the Word window. This will take you to the "Backstage" view.

In the "Backstage" view, you should see an "Enable Editing" button on the right-hand side. Click on it to enable editing mode.

Alternatively, you can press the "Esc" key on your keyboard to exit the "Protected View" and enable editing.

If you closed the yellow banner by mistake, don't worry. You can still enable editing by following the steps above. Remember to save your changes regularly to ensure your work is preserved.

Conclusion: It worked almost immediately. If I were to Google it, I'd have to verify multiple documents before I got to the answer.

[jrflowers]

Can you elaborate on what you mean by “verify multiple documents”?

https://serpapi.com/playground?q=How+to+enable+editing+of+a+...

It looks like Google’s output is nearly identical information as what ChatGPT gave you. If you chose to trust ChatGPT’s output simply because it was more confident sounding, does that actually qualify as the software doing better?

[llamaboy2]

I spent hours googling for information about applying for a visa for a pretty disorganised country and struggled to get anywhere. I then asked ChatGPT which gave me a very good explanation of the process, contained relevant keywords I could then use to google and verify, but unfortunately the ultimate URL it sent me to for applying didn't exist. I suspect this was due to it being outdated, and the government changing the link since. Overall it saved me a lot of time over just googling.

[lukeschlather]

I don't see how they said that Googling skips critical thinking. The issue is that for a lot of queries, Google returns a bunch of content mill pieces that have similar quality to ChatGPT. ChatGPT tends to be more focused on what you asked for, while the content mill pieces are deliberately written to keep you reading as long as possible without answering the question.

[jrflowers]

>ChatGPT tends to be more focused on what you asked for

…even if it has to invent people, places, things or events to satisfy your focus.

Do you have a particular example where ChatGPT does better than googling something? I’m especially interested in your example since we agree that googling entails using humans cognitive ability to make sense of things.

[hanselot]

Sure.

https://chat.openai.com/share/d9284035-0820-4a5c-9e54-a7c411...

https://chat.openai.com/share/bce6ee2f-604a-413a-b14a-7145b8...

https://chat.openai.com/share/4e2302ff-4b38-489d-80b6-314bd1...

[jrflowers]

Can you elaborate on how the ChatGPT software does better than looking stuff up?

I do not argue that you don’t seem to get any value out of using ChatGPT, I’m curious about the big difference in quality between the knowledge you get from the ChatGPT page vs what knowledge you can get by googling something.

[lynx23]

For me, it boils down to SEO spam. Gaming pagerank has led to many SEO spam blog sites ranking relatively high, but with a low signal/noise ratio. Often times, it is a lot faster to ask ChatGPT something, compared to wading through endlessly verbose Google results.

[ChatGTP]

For me Google is more of a "router" to sites I know will likely provide good info, before Reddit was nerfed, I'd always include that in my Google query, same for SO etc. It worked great and fast.

[alanpearce]

> ChatGPT will replace the concept of googling things

FastGPT[0] is some way towards that: it uses the web to provide answers

[0]: https://labs.kagi.com/fastgpt

[benob]

> Me: What are some questions you cannot answer? > FastGPT: I apologize, but I do not actually have the ability to determine what questions I cannot answer. I am Claude, an AI assistant created by Anthropic.

Good to know ;)

[aerio]

Bing chat is already GPT4 with an internet connection.

[tehrob]

The issue is, people think that connecting an LLM to the internet = unlimited information. In reality, it = an LLM treating a webpage as another sources of information. It is no better or worse than literally copying and pasting the information into the text box. If it goes beyond the token limit, you are going to get swiss cheese responses.

Bing is okay, ChatGPT 4 with browe tool is okay and Bard is pretty good, but tends to not use its browse tool enough, and hallucinates mightily.

[Al-Khwarizmi]

It already replaces Google for me like 80% of the time.

Not because ChatGPT is an infallible oracle, far from it. It's just that the bar is rather low. Google has become really bad in the last decade or so.

[Technotroll]

> There is a group of people that are ardent in the conviction that if we wait long enough and wish hard enough that ChatGPT will replace the concept of googling things.

Have you tried Phind?^[1] The project explores exactly how an AI-driven search tool might look like.

The thing that really makes it shine, is that it doesn't only make claims per text, but that it also provides source links that it has already scraped for info.

[1]: https://www.phind.com/

[jrflowers]

That’s a neat tool to use while googling stuff!

[eloisant]

Exactly, you can't go to the moon by climbing sucessively taller trees.

[afpx]

I used to Google things, but then it started returning false information. 75% of the time I use Google, and it summarizes the answer to a question at the top of the results page, it's erroneous. So, which is better?

[jrflowers]

I like to click on the links in the search results, so I would say that Google is better for finding information.