Google vs ChatGPT: The end of Google as we know it? A comparison

With the recent launch of ChatGPT by OpenAI, many have started to wonder if this could be the end of Google as we know it. 

One does not have to spend much time on Twitter to come across speculations and statements about how this is the end of Google.

It was one of my first reactions as well. 

Why should users browse different links back and forth in search of the answer they are looking for when ChatGPT is more than capable at providing the answer?

And in general, this is a topic we at SEO.ai discuss a lot - e.g., what will be the reaction from Google when these generative language models become better and better at producing endless but still helpful content. But that's a different blog post topic for later.

So to explore the question of Google vs. ChatGPT, I made a small test with a comparison.

See this example on a SEO related question answered:

Question: what length is the proper to use for a title tag when optimising for SEO?

‍Answer: When optimising a title tag for SEO in Google, it's best to keep the length between 50 and 60 characters. This will ensure that the title is properly displayed in the search results without getting cut off. It's also important to include keywords in the title that are relevant to the content on the page, as this can help improve the page's search engine ranking.
‍

Asking a similar question in Google creates something like this in a featured snippet:

‍Answer: Optimising your title tags is one of the easiest ways to help improve your rankings on Google. They signal to Google what your page is about. Generally, it's best to keep title tags between 50 to 60 characters. This way, words won't get cut off on desktop or mobile SERPs.

‍

The answer quality is almost equal and what I call a tie. 

But looking at the graphical aesthetics, ChatGPT is a clear winner. Just look at how much noise and clutter the user has to look past in Google to find the answer below the ads.

Google, on the other hand, wins by an easy way to navigate to more answers and in different directions. Also, some questions I might not have considered by my initial question but can be inspired to consider now.

The results are richer, and Google spends a lot of time optimising that. 

In many cases, people also need to know the source of the answer/data. This is currently a black box with the different GPT models. 

And then there is the question of speed.

This has almost been one of its core traits from the inception of Google. Being extremely fast. Not only is the answer generated faster, but for me, as a user, it's much faster to click, interact and skim content than it is to create different queries and have a conversation going to learn more. And for some time to come, this will be the deciding factor for most users.

And it's not like Google is behind in the AI space. They are notorious for testing different technologies and approaches for better search results. 

Google is also already using ML/artificial intelligence (AI) to understand the queries asked in order to determine what kind of results to show - and whether there is a featured snippet to be shown, product images or the weather forecast. 

With the acquisition of DeepMind back in 2014 and continuous backing, it's not like Google do not have access to these evolving technologies. Earlier this year, DeepMind launched the GPT3 competitor Chinchilla. And that's beside the thousands of internal developers at Google.

In 2009, Wolfram Alpha (a search engine that directly answers factual queries by computing the answer from structured data, rather than providing a list of documents or web pages that might contain the answer) was speculated to be a Google killer. 

‍

But as we know by now, that is nowhere the case.

It also comes down to the math and how these models are built. 

Language models like GPT3 and ChatGPT are trained on massive datasets and as a whole. But it's not real-time data and news searches or information on recent data will not be within the scope. Just try to ask ChatGPT about recent Soccer World Cup results. 

So ChatGPT is a mind-blowing good tool and great for integrating into other services (we are currently doing this as well for SEO.ai) - and these types of technologies will for sure revolutionize many types of tasks and information queries - but for the broader public, it won't overtake Google anytime soon.

‍

And just to illustrate how good the technology is, this is the TDLR summary of this article according to ChatGPT:

The recent launch of ChatGPT, a generative language model trained by OpenAI, has sparked speculation about its potential to disrupt Google's search engine.

A comparison test reveals that ChatGPT is capable of providing similar quality answers to Google, but Google has the advantage of being able to navigate to more answers and in different directions. Google also has the advantage of speed and the ability to understand queries using AI.

However, ChatGPT has the advantage of graphical aesthetics and the ability to generate answers faster.
It is also unknown whether ChatGPT's answers can be trusted as it is a "black box" in terms of the source of its information.

‍

Facts about ChatGPT

ChatGPT is a language model developed by OpenAI, a research lab founded by Elon Musk and Sam Altman. It is a deep learning-based natural language processing (NLP) system that can generate human-like text. It is trained on a massive dataset of over 8 billion web pages. This gives it a huge advantage over

How does Google use AI in its search queries?

Google does already use AI in its search queries, but it is not as advanced as ChatGPT. Google uses AI to understand the context of the query and to provide more relevant results. It also uses AI to understand the intent of the query, so it can provide more accurate results.

What questions could we have answered in this article 

The following questions are some of the ones we should have answered according to the SEO.ai analysis. Some of them we hope we covered, and some of them we will dive more into in other blog posts.

1. What are the main differences between Google and ChatGPT?
2. How do Google and ChatGPT compare in terms of AI capabilities?
3. What advantages does ChatGPT have over Google?
4. How does ChatGPT's natural language processing compare to Google's?
5. What type of applications is each platform best suited for?
6. What advantages does Google have over ChatGPT?
7. What are the key benefits of using either Google or ChatGPT?
8. How do their cost models compare?
9. How reliable and accurate are the results of Google and ChatGPT?
10.  What are the most important features of ChatGPT that set it apart from Google?

We also asked ChatGPT what questions it would be good to cover in an article like this: 

1. What is ChatGPT, and how does it differ from Google?
2. How does ChatGPT work, and how does it differ from Google's search engine?
3. What are the pros and cons of ChatGPT compared to Google?
4. What are some examples of questions that can be asked of ChatGPT but not Google?
5. What are some examples of questions that can be asked of Google but not ChatGPT?
6. How can ChatGPT and Google be used together to get the most out of both?
7. How are ChatGPT and Google updated and maintained, and how do they differ in this regard?
8. What are some other major differences between ChatGPT and Google?
9. Which platform would you recommend to a user looking for answers to specific questions, and why?

You can then determine which ones you prefer.

‍