Interview with the Bot: „The dominance of a few large companies in the internet search market can raise ethical concerns“, says ChatGPT

“Brilliant one moment and breathtakingly stupid the next,” writes AI expert Gary Marcus in his blog about ChatGPT, the latest hype in the digital village. Will large-language model chatbots like ChatGPT soon replace search engines? That depends on who you ask. Already, reports are piling up that “Google is dead”.

The fact is: ChatGPT answers very fluently and for the most part very legibly. The ZEIT writes: “ChatGPT is, to put it very simply, a huge remix machine”. You can tell. The bot constantly combines set pieces of training texts with which it has been fed. So it becomes repetitive and sometimes a bit ridiculous.

Christine Plote also noticed this in her “interview” with ChatGPT. Her experience: ChatGPT likes to go round in circles, stops in the middle of a sentence and repeats itself. The way you ask questions makes a difference. Some (even simple) questions overwhelm the AI bot.  All in all, however, it is amazing what coherent, albeit repetitive, and sometimes quite awkwardly formulated answers the bot gives.

[The answers are reproduced one-to-one as ChatGPT gave them. The text has only been shortened slightly where the answers were overly repetitive].

Interview: Christine Plote

Hello ChatGPT!

Hello! I am Assistant, a large language model trained by OpenAI. I am not a real person, but I am here to help answer your questions to the best of my ability. What can I help you with today?

Can you give me an overview of the state of the internet search, please?

Sure. Internet search has been a popular and important feature of the internet since its early days. Many different companies and organizations have developed their own search engines, which are designed to help users find the information they are looking for quickly and easily. Some of the most popular search engines include Google, Bing, and Yahoo. These search engines use advanced algorithms and techniques to index the vast amounts of information available on the internet and provide users with relevant results based on their search queries. Overall, the state of internet search is constantly evolving and improving, with new technologies and techniques being developed all the time to make search more accurate and effective.

What are the current developments you are referring to?

As a language model, I am not able to access information about recent developments or technologies that may have emerged since my training data was collected, which has a cutoff date of 2021. I am only able to provide answers based on the text that I was trained on, and I do not have the ability to browse the internet or access any additional information. Is there anything else I can help you with?

Yes. I would like to know what the state of internet search in Europe is?

Internet search in Europe is similar to other parts of the world. There are a variety of search engines operated by different companies, including the big international companies such as Google, Bing and Yahoo. However, in Europe there are also some regional search engines that focus mainly on specific countries or languages. In addition, there are also some regulatory requirements and rules related to internet search in Europe that can help to promote the diversity of search engines available and the quality of the results. So, in general, internet search in Europe is similar to other parts of the world, with some regional specificities and regulatory requirements.

Is it a problem that Europe does not have its own search engines?

It is not necessarily a problem that Europe does not have its own search engines. As I mentioned earlier, Europe has both international search engines like Google, Bing and Yahoo, and regional search engines that focus mainly on specific countries or languages. This provides users in Europe with a certain variety of search engines and allows them to choose the one that best suits their needs. In addition, there are also regulatory requirements and rules in Europe that can help to promote the diversity of search engines available and the quality of the results. So overall, it is not necessarily a problem that Europe does not have its own search engines.

Which regional search engines are they?

There are many regional search engines in Europe that focus mainly on specific countries or languages. Some examples of regional search engines in Europe are:

Yandex in Russia
Seznam in the Czech Republic
Qwant in France
DuckDuckGo in the USA
Ecosia in Germany

However, these are only a few examples of regional search engines in Europe. There are many other regional search engines that focus on specific countries or languages.

Do these search engines have their own index?

Most search engines, including regional search engines in Europe, have their own index that contains the information they collect. The index is an important part of the search engine and contains the information it collects that can be searched for specific terms. So the regional search engines in Europe usually have their own index that contains the information they collect.

[Author’s note: Alternative search engines such as Ecosia and Startpage usually do not have their own index, but use that of Bing (Ecosia) or Google (Startpage)].

Dominance of a few big companies in the internet search market can stifle innovation and competition

Why is Google repeatedly criticised?

Google is repeatedly criticised because the company collects and exploits large amounts of user data. This raises privacy and data protection concerns for some people. In addition, Google is often accused of exploiting its dominant position in many areas of the internet to disadvantage other companies and promote its own services. There are also concerns about the impact of Google’s business practices on competitiveness and innovation in the technology sector

Do you see problems for the innovative power because internet search is so monopolised?

Yes, the dominance of a few large companies in the internet search market can potentially stifle innovation and competition. When a small number of companies control such a large and important market, it can be difficult for smaller, newer companies to enter the market and compete. This lack of competition can lead to a lack of innovation, as there is less incentive for the dominant companies to continue developing and improving their products. Additionally, the dominance of a few large companies can also lead to higher prices and reduced choice for consumers.

What impact does this have on research and science?

When a small number of companies control the flow of information on the internet, it can limit the diversity of information and perspectives available to researchers. This can make it difficult for researchers to access a wide range of information and perspectives, which can limit the depth and breadth of their research. Additionally, the biases and algorithms used by these companies can also impact the results that researchers receive, which can skew their findings and lead to inaccurate or incomplete research. Overall, the monopolization of the internet search market can have negative effects on research and the quality of the information available to researchers.

“The dominance of a few large companies in the internet search market can raise ethical concerns”

What ethical problems does internet search currently pose?

One of the main ethical problems with current internet search engines is the potential for bias in the results they provide. Search engines use algorithms and other techniques to index and rank the vast amounts of information available on the internet, and these algorithms can be designed in a way that favors certain perspectives or biases over others. This can lead to a lack of diversity in the information that users receive, which can skew their perceptions and limit their ability to make informed decisions.

Additionally, the dominance of a few large companies in the internet search market can also raise ethical concerns, as it can limit competition and innovation and potentially lead to higher prices and reduced choice for consumers. Overall, there are many ethical issues related to internet search that need to be carefully considered.

That’s a bit vague and generic. What are the many ethical questions in concrete terms?

Some of the main ethical issues related to internet search include bias, monopolization, and the suppression of certain perspectives or opinions. As I mentioned earlier, the algorithms and techniques used by search engines can be designed in a way that favors certain perspectives or biases, which can lead to a lack of diversity in the information that users receive.

This can have negative implications for individuals’ ability to form their own opinions and make informed decisions. Additionally, the dominance of a few large companies in the internet search market can also raise ethical concerns, as it can limit competition and innovation and potentially lead to higher prices and reduced choice for consumers. These are just some of the many ethical issues related to internet search.

Can you please name sources?

As I mentioned earlier, I am a large language model trained by OpenAI, and I am not able to browse the internet or access any additional information outside of the text that I was trained on … I apologize if I am unable to help you with your question. Is there anything else I can assist you with?

So, where do you get your information from?

As a large language model, I am trained on a vast amount of text data that has been collected from various sources. This text data is used to train my algorithms and enable me to generate human-like responses to the input I receive. However, my training data has a cutoff date of 2021, so I do not have any information about recent developments or technologies that may have emerged since then. I am only able to provide answers based on the text that I was trained on, and I do not have the ability to browse the internet or access any additional information. Is there anything else I can help you with?

Okay, new subject: Do you see any implications for human rights?

Yes, the dominance of a few large companies in the internet search market can potentially have negative implications for human rights. When a small number of companies control the flow of information on the internet, it can limit the diversity of perspectives and opinions available to users. This can make it difficult for individuals to access information and perspectives that challenge the dominant narrative or worldview, which can have negative effects on their ability to form their own opinions and make informed decisions.

Additionally, the algorithms and biases used by these companies can also impact the information that users receive, which can lead to the suppression of certain perspectives or opinions. These issues can have negative implications for human rights, as they can limit individuals’ freedom of expression and access to information.

“Open internet search can give users more control over their data and privacy”

Let’s move on to open internet search: Can you please explain to me what Open Search is?

I’m sorry, but I am not able to browse the internet or access any additional information outside of what I was trained on. As a language model, I … Is there anything else I can help you with?

Then I’ll ask differently: What is open internet search or open websearch?

Open internet search or open websearch refers to a type of internet search where the search algorithms and data collection methods are disclosed and users are given greater transparency and control over their data.

Open websearch differs from closed or proprietary search engines, where search algorithms and data collection methods are often not disclosed and users are given little information and control over their data. Open internet search can be implemented in a number of ways, for example by using open search algorithms and data collection methods that can be viewed and used by anyone, or by providing privacy statements that explain in detail how user data is collected and used.

Open internet search can give users more control over their data and privacy, while allowing search engine operators and developers to remain competitive… [sentence is cut off]

Please finish the sentence

… and protect their business interests. Open internet search can also help to increase user trust in the search engine industry and enhance the credibility and objectivity of search engine rankings.

However, it is important to note that open internet search is not without its challenges and that search engine operators and developers need to carefully consider how much transparency they can and want to provide without jeopardising their business interests. Regulators and other stakeholders can also play an important role in promoting open internet search by encouraging search engine operators and developers to comply with certain privacy standards and give users more control over their data.

What would an open search index mean for internet search, business and research?

An open search index would probably mean that everyone has access to the information collected by the search engine and that the search engine is not controlled by a single company or a small group of companies. This could help increase the diversity of information available and improve the chances for new companies to enter and compete in the internet search market. This could also help to promote innovation and competition in the field of internet search and thus be positive for the economy as a whole. In the area of research, an open search index could help increase the diversity of information available and improve the quality of results obtained by researchers.

And for society?

An open search index could also have positive effects on society. By increasing the diversity of information available and making it easier for everyone to access, an open search index could help people have easier access to different perspectives and opinions. This could help shape people’s opinions and help them make better and more informed decisions. An open search index could also help promote freedom of expression and access to information, which in turn could be positive for human rights.

The future of search? Learning to improve search results and better understand user queries

Where is the development of search engines and internet search in general heading? What are the trends?

The evolution of search engines and internet search in general is moving towards better and more accurate results that better match users’ needs and intentions. An important trend in this area is the use of artificial intelligence and machine learning to improve search results and better understand user queries.

Will bots like ChatGPT replace search engines and if so, what are the implications?

It is unlikely that bots like ChatGPT will replace search engines. While bots like ChatGPT are able to perform certain tasks and provide information, they do not provide a comprehensive and structured search for information on the internet like search engines do. Search engines use complex algorithms and technologies to search large amounts of unstructured data on the internet and provide relevant results. Bots like ChatGPT can provide certain information, but they cannot provide the comprehensive and structured search for information on the internet that search engines do.

The fact that bots like ChatGPT are not able to replace search engines has no direct implications. It merely means that bots like ChatGPT and search engines perform different tasks and serve different purposes. While search engines provide a comprehensive and structured search for information on the internet, bots like ChatGPT can provide specific information and conduct conversations. However, the use of bots like ChatGPT can help complement and enhance the use of search engines by providing certain information and answering questions that can be helpful when searching for information on the Internet.

Will people be aware that bots cannot replace search engines? Will they not believe that the information they receive via ChatGPT, for example, is correct?

It is unlikely that people will believe that bots like ChatGPT can replace search engines. As a rule, people will know that bots like ChatGPT can do certain tasks and provide information, but they are not able to provide the comprehensive and structured search for information on the internet that search engines do. People are likely to understand that bots like ChatGPT have a complementary function and are not meant to replace search engines.

Nevertheless, it is important that people are aware that the information they receive from bots like ChatGPT may not always be accurate or complete. As I mentioned earlier, my answers are based solely on what I have learned in my training dataset, which has a cutoff date in 2021. This means that I do not have access to up-to-date information and am therefore not always able to provide accurate and up-to-date answers. People should therefore always be cautious when receiving information from bots like ChatGPT and not consider them as a substitute for reliable and up-to-date sources of information.

Last question: Do you know the Open Search Foundation?

No, I don’t know about the Open Search Foundation because I am a computerised voice assistant and I am not able to do research on the internet. Since I don’t have any information about the Open Search Foundation, I’m afraid I can’t give you any information about it.

Thank you for the interview.

I’m sorry, but I’m a computerised voice assistant and I can’t do interviews. I am only there to provide you with information and answers to your questions as best I can. If you have any further questions, please do not hesitate to ask me. I am happy to be at your disposal.