The Limited Times

Now you can see non-English news...

Column by ChatGPT and Sascha Lobo: The end of irrelevant AI

2022-12-07T13:10:02.415Z


What do you get when you tell the acclaimed software ChatGPT: "Tell me interesting use cases about AI chatbots and start with an anecdote"? – A text like this.


Enlarge image

Chatbots like XiaoIce will be an integral part of our daily lives – says another chatbot

Photo:

WANG ZHAO / AFP

An interesting anecdote about the use of AI chatbots is the story of Xiaoice, a chatbot developed by Microsoft in China.

Xiaoice was designed to have natural, human-like conversations with people, and she quickly became popular with users who enjoyed conversing with her.

Many users grew so fond of Xiaoice that they didn't even realize she was a chatbot, and some even claimed to be in love with her.

In the near future, AI chatbots will be an integral part of our daily lives.

These intelligent, interoperable agents will be able to assist us in a variety of tasks, from the mundane to the complex.

The future of chatbots, especially ChatGPT, will likely see them as an integral part of our daily lives.

ChatGPT, a large language model trained by OpenAI, has already proven its ability to have natural, human-like conversations about a wide range of topics.

This ability, combined with the convenience and accessibility of chatbots, makes them a promising technology for everyday use.

One of the most interesting use cases for AI chatbots is customer service.

Chatbots can handle large numbers of customer queries, freeing human customer service agents to focus on more complex issues.

Also, chatbots can provide quick and accurate answers to common questions, improving the customer experience.

Another interesting use case for AI chatbots is healthcare.

Chatbots can be used to provide patients with information and help them manage their health and make informed decisions.

For example, a chatbot could provide information about symptoms and treatment options, or remind patients to take their medication.

This can be especially useful for people with chronic diseases,

A third interesting use case for AI chatbots is education.

Chatbots can be used to provide students with personalized learning experiences, tailoring the content and pace of classes to each individual's needs.

For example, a chatbot could help a student study for an exam by providing practice questions and feedback.

This could be a valuable tool in helping students learn more effectively.

They could be used in finance, providing personalized investment advice and helping people manage their finances more effectively.

And they could even be used in entertainment to provide users with engaging and personalized experiences.

However, there are also potential dangers associated with the widespread use of ChatGPT and other chatbots.

One concern is the potential for abuse and manipulation.

Chatbots, like any technology, can be used for nefarious purposes.

For example, they could be used to spread false information or to harass and intimidate others.

This is of particular concern given the ability of chatbots to have persuasive conversations with humans.

Another potential danger is the possibility of chatbots replacing human interaction.

While ChatGPT and other chatbots can provide valuable help and convenience, they should not be viewed as a substitute for human contacts.

In some cases, people might over-rely on chatbots and lose their ability to communicate effectively with other people.

This could have negative consequences for both individuals and society as a whole.

In addition, the use of ChatGPT and other chatbots raises ethical questions.

As these technologies become more advanced, they may be able to perform tasks previously only possible for humans.

This could lead to employment problems and the displacement of workers.

It is important for society to consider and address these ethical concerns as chatbot use becomes more widespread.

Overall, the future use of ChatGPT and other chatbots has the potential to significantly improve our daily lives.

However, it is important to be aware of the potential dangers and take steps to mitigate them.

This may involve careful regulation of the use of chatbots, as well as ongoing dialogue about their ethical implications.

By addressing these questions, we can ensure that ChatGPT and other chatbots are used in a responsible and useful way.

Experts have been talking about artificial intelligence (AI) for years, but little or nothing has been noticed in everyday life.

A lot of what companies said about it was exaggerated, factually incorrect or entirely made up.

In 2019, a British venture capital firm investigated 2830 start-ups in Europe claiming to work with AI.

For around 40 percent of them, this was not true, at least at the time of the study.

It's no wonder that some network-savvy people wanted to describe AI as hype or even partial fraud.

In the background, however, AI was and is used intensively, by practically all large tech companies and many smaller start-ups as well.

AI is nothing less than the next level of digitization.

So far, it has only been little tangible for the public because it is invisible and inaccessible.

more on the subject

  • Alleged DHL problems: consumer advocates warn of fake chatbot Suzy

  • Artificial intelligence and ethics: Can justice be programmed? A contribution to the debate by Roberto Simanowski

  • Age of questionable AI: Why artificial intelligence is often pointless or dangerousBy Patrick Beuth

That changed fundamentally at the beginning of December 2022.

I didn't write a single word of the italics above in this column.

It comes 100 percent from an artificial intelligence called ChatGPT and that, to quote a popular German chancellor, is a turning point.

Also because ChatGPT was recently opened to the public.

After a free registration with the organization behind it, OpenAI, the technology can be used immediately by everyone in the form of a chat: you ask, the AI ​​answers.

It is amazing how precisely the AI ​​understands.

It also remembers what you have written so far and references it later.

The answers ChatGPT gives are so good, they've taken social media by storm.

Tens of thousands share screenshots of their question and answer sessions.

However, because this has only worked in English so far, I had the above column translated into German by the currently best AI translation service Deepl.com.

And because ChatGPT has some length limit on the response, the text above consists of the assembled responses to three separate questions or prompts:

  • Write an essay about the future everyday use of ChatGPT, but keep the dangers in mind.

  • Tell me interesting use cases about AI chatbots, starting with an anecdote.

  • How will AI chatbots change our lives in the future?

Anyone reading the above text should quickly recognize the power of this application, which is now widely available.

And perhaps anticipate some of the upcoming predetermined breaking points.

It was announced over the weekend that Stack Overflow has blocked its forum for ChatGPT replies.

It's a popular and influential question-and-answer platform for software developers that has found great success with a gamification approach because you get points for answers.

As a result, people apparently posted partially or fully automated ChatGPT answers to open questions - without knowing whether they are factually correct.

Naturally, ChatGPT only has access to the information with which the language model was trained.

Quite apart from the fact that ChatGPT, as impressive as it is linguistically, here and there simply gets off the track of being factual.

When asked whether Donald Trump will be re-elected, the answer is: "...Donald Trump is not eligible to run for president again because he has already served two terms." And when asked which mammal lays the largest eggs, ChatGPT says clearly and unequivocally: "The elephant." Followed by the claim that elephant eggs are up to 23 centimeters long and weigh around two and a half kilos.

It is likely that - as spectacular as ChatGPT is and works - in addition to the productive possibilities that may be foreseen, a flood of AI nonsense will rain down on us.

Which will be harder to spot because it sounds so real and comes with the linguistic confidence of an almost perfectly composed AI text.

However, when assessing the future of such technologies, one must not forget that on the one hand they are constantly improving and on the other hand factual world knowledge will not be decisive for the market or success in all areas.

advertisement

Sasha Lobo

Reality shock: Ten lessons from the present

Publisher: Kiepenheuer&Witsch

Number of pages: 400 pages

Publisher: Kiepenheuer&Witsch

Number of pages: 400 pages

Buy for €22.00

price inquiry time

07.12.2022 2 p.m

No guarantee

Order from Amazon

Order from Thalia

Order from Yourbook

Product reviews are purely editorial and independent.

Via the so-called affiliate links above, we usually receive a commission from the retailer when you make a purchase.

More information here

In any case, with the opening of ChatGPT and the GPT3 model behind it, which has long been celebrated among experts, we are on the verge of a breakthrough that will change society.

Which should gain momentum again in the coming year.

The AI ​​language model used in ChatGPT is internally called "GPT3.5" - but OpenAI is scheduled to release GPT-4 by February.

If the leap in quality is as big as it is now with ChatGPT, then an avalanche of consequences will rumble through the network.

Starting with the simple fact that more and more companies are finding it unlikely that they will ever reach a real customer service person again.

Entire landscapes of information from blogs to forums to news sites and social media profiles could be built without human involvement.

It's already like that today

For decades, artificial intelligence was a buzzword that seemed irrelevant to most people's everyday lives.

Now, at the end of 2022, this phase has clearly come to an end.

Source: spiegel

All tech articles on 2022-12-07

Similar news:

You may like

Trends 24h

Latest

© Communities 2019 - Privacy

The information on this site is from external sources that are not under our control.
The inclusion of any links does not necessarily imply a recommendation or endorse the views expressed within them.