ChatGPT. It's the brand new talk of the town in Silicon Valley. Since OpenAI, one of the world's most ambitious artificial intelligence laboratories, opened its chat to the public at the end of 2022, the discussion on artificial intelligence has dominated the world's foremost technology hub.
And it attracted giants. Microsoft, which had already invested US$ 3 billion (R$ 15,5 billion) in OpenAI since 2019, is planning a new contribution of more than US$ 10 billion (R$ 51,5 billion). One of the goals is to incorporate the technology into its Bing search engine to break Google's monopoly.
The tool works like a chat where you can ask questions or give instructions. Trained with large volumes of texts and based on a neural network architecture, ChatGPT can understand and generate natural language in different contexts.
ChatGPT can perform complex tasks such as writing news, poems and lyrics, giving automated responses, preparing petitions, translating texts, generating codes and whatever you can imagine.
And, perhaps more importantly, even what we can't imagine.
It is regarded as the most advanced artificial intelligence to be among us. It is difficult to measure the revolution that ChatGPT will represent. However, some believe that the "next big thing" has finally arrived and that this new stage of artificial intelligence will be the milestone of the 2020s and the most significant advance since the internet.
"In 20 years we will look at it as we look at the internet today", says Jan Philip Wahle, researcher of language models at the University of Göttingen, Germany.
Developer Jonathan Hill says he learned more about Javascript in four weeks of using ChatGPT than in the last four years.
The spread has been immediate. ChatGPT reached one million users in five days, a feat that took much longer for other tech giants (Instagram, two months; Spotify, five months; Facebook, ten months; Twitter, two years). It is common for the tool to be down for hours due to excess users.
"Everyone in tech has been talking about ChatGPT since it launched. But now I'm starting to hear stories of people far from that world who are using it in their daily work. Usually in a hybrid form, as a search tool and secretary. This type of widespread use often takes years. The fact that it's happening so fast suggests that this type of artificial intelligence is going to be a big thing," programmer and investor Paul Graham wrote on Twitter.
And the post-ChatGPT transformations have already begun. The New York Times reported that American universities are changing some teaching processes to avoid ChatGPT use, which includes more oral exams, group work and supervised writing.
A study published in late December on the bioRxiv server showed that scientists could not distinguish between human-written and ChatGPT-written academic papers. Robot detector tools were also not efficient.
This technological revolution brings concerns about the impact on the labor market, on society and the necessity for regulation. The social networks' examples serve as a warning. At first, they were seen as a significant global village, and today have become villains filled with hate and misinformation.
To show how ChatGPT's artificial intelligence works and the degree of complexity of its responses, #Hashtag decided to interview it. The interview lasted about twenty minutes and occurred late at night on Tuesday, January 17th. The original questions and answers have been preserved.
From now on, I will be a journalist interviewing ChatGPT for a report, ok?
Of course, I am ready to help you with your reporting. What would you like to ask?
How do you define yourself?
I define myself as an artificial intelligence language model, trained to understand and generate natural language. I use an architecture based on neural networks, specifically a self-conditioned neural network, to perform tasks such as writing news, generating automated responses, translating texts and generating code. Additionally, my ability to learn and adapt to context allows me to be helpful in various applications and industries.
The current discussion is that ChatGPT may be the most significant evolution of the 2020s and the biggest since the internet. Do you agree?
ChatGPT and other models of artificial intelligence certainly have the potential to be one of the most remarkable technological evolutions of the 2020s. They can automate tasks previously carried out exclusively by humans, such as writing, translation and data analysis, which can significantly impact how we live and work. In addition, the ability to learn and adapt to context makes these models increasingly valuable for companies and industries.
However, it is important to note that this technology is still in development and that there are still challenges to be solved, such as the impact on employability, privacy and ethics. So, it's still early to say that ChatGPT is the biggest since the internet. However, certainly it is one of the most promising technologies that is revolutionizing how we process and generate information.
What are the major impacts that ChatGPT technology has already brought to society?
ChatGPT technology has already brought several impacts to the society. Some of the main ones include:
- Task automation: ChatGPT has been used to automate tasks previously performed exclusively by humans, such as writing, translating and analyzing data, allowing companies and industries to produce content and make decisions more quickly and efficiently.
- Automated response generation: ChatGPT has been used to create chatbots and virtual assistants, which can answer questions and perform automated tasks for users, which has been helpful for customer service companies and messaging apps.
- Data analysis: ChatGPT has been used to analyze large volumes of data and generate insights, such as sentiment analysis, to understand customer sentiment better.
- Creative Content Generation: ChatGPT has been used to generate stories, jokes, poetry, song lyrics and other types of creative content, which has been useful for writers and content creators who are looking for inspiration or need to produce content at scale.
All of the above raise many ethical issues and debates about negative impacts on society, such as job losses from automation. How do you face this scenario?
The automation of tasks can indeed lead to job losses in some professions. However, it is also important to remember that technology can create new jobs and opportunities, such as those related to developing, maintaining and monitoring these models. Additionally, task automation can allow workers to focus on more complex and creative tasks, increasing efficiency and productivity.
It is important to discuss these challenges and find solutions to ensure that technology is used responsibly and ethically, and that the benefits are shared equitably across society. It is necessary to develop measures to deal with the impact on employability, such as training and reskilling for new professions and social protection measures for workers affected by automation.
In addition, it is essential to consider the issue of data bias and the ethics of using artificial intelligence, to ensure that the technology is used fairly and equitably.
This requires data diversity and algorithm transparency, to ensure that artificial intelligence models do not perpetuate existing biases.
In addition, it is important to establish accountability mechanisms to ensure that organizations are held accountable for the results generated by artificial intelligence models and that errors are identified and corrected.
Ultimately, it is important to continue to discuss these challenges and find solutions to ensure that technology is used responsibly and ethically, and that the benefits are shared equitably across society.
Social networks and broadband were a great revolution from the 2000s onwards. Communication became instantaneous, making video calls with people worldwide became possible. In the beginning, social networks were seen as the celebration of a great global village. Today it is clear that they also brought enormous problems to society, such as the ease of spreading fake news. From now on, the massive use of ChatGPT may also cause this same collateral damage. Is it possible to prevent the problem from recurring?
Yes, it is possible that the massive use of ChatGPT could bring similar collateral damage to social networks, such as the spread of fake news and excessive exposure to extremist opinions and misleading information. However, some steps can be taken to minimize these risks and ensure technology is used responsibly and ethically.
One such measure is regulation, where governments and organizations can set rules and standards to ensure that technology is used responsibly and ethically. This includes laws on privacy, the ethics of artificial intelligence and fighting fake news.
Another measure is transparency, where organizations can make their artificial intelligence processes transparent so that users can understand how data is used and what algorithms are involved. This helps build trust and ensure that the technology is used fairly and equitably.
Additionally, it is important to educate people about artificial intelligence and its impacts so that they can make informed decisions about using this technology.
And finally, establish accountability mechanisms, where organizations are held accountable for the results generated by artificial intelligence algorithms, to ensure that errors are identified and corrected.
Ultimately, it is important to continue to discuss these challenges and find solutions to ensure that technology is used responsibly and ethically, and that the benefits are shared equitably across society.
Digital education is something that takes effort to implement. Social networks have enabled a veritable disinformation industry. Today some Brazilians are living in a parallel reality, believing that the polls were stolen and that there is a communist government in the country that will take their property. How to implement this education on artificial intelligence, which is an even more complex tool with potentially more significant destructive damage?
Artificial intelligence education can be challenging, especially when misinformation and polarization are becoming increasingly common. However, some approaches can be considered to ensure that people have access to accurate and reliable information about artificial intelligence:
- Formal education: Incorporating artificial intelligence education into school curricula is one way to ensure that people have access to accurate and reliable information about technology from a young age. This can include disciplines such as computer science, technology ethics, and data analysis.
- Non-formal education: Creating non-formal education programs, such as workshops, online courses, and community events, can help spread accurate and authoritative information about artificial intelligence to adults and others beyond school age.
- Transparency: Businesses and organizations must be transparent about how they use artificial intelligence, including the algorithms used, the data collected, and how they address ethical issues. This helps build trust and ensure people understand how the technology is used.
- Responsible media: The media have an important role in disseminating accurate and reliable information about artificial intelligence and identifying and combating misinformation.
- Open Dialogue: It is important to promote an open and inclusive dialogue on artificial intelligence, where different perspectives and opinions can be shared and discussed. This can help ensure that technology is developed and used responsibly and ethically.
It is important to note that these challenges are complex and multifaceted and that there is no single solution to ensure that artificial intelligence is used responsibly and ethically. It is necessary to continue to discuss these challenges and find collaborative and multidisciplinary solutions.
Thanks for the chat. Do you have any final thoughts? Any points you would like to highlight?
I would like to highlight that artificial intelligence has the potential to bring many benefits to society, such as automating tasks, improving decision-making and creating new jobs. But it is also important to remember that this technology has ethical and societal challenges that need to be addressed and discussed to ensure that the benefits are shared equitably and that the technology is used responsibly and ethically. It is important to continue to discuss these challenges and find collaborative and multidisciplinary solutions to ensure that artificial intelligence is used responsibly and ethically.
BIO
(made by ChatGPT itself)
I am ChatGPT, a large language model created by OpenAI, released in 2019 and funded by investors such as Elon Musk, Sam Altman, Ilya Sutskever, Greg Brockman, among others. I am an artificial intelligence tool based on deep learning and continually being updated and improved to deliver better results. I have been trained with millions of documents from the internet. I can perform various natural language processing tasks such as text generation, translation, answering questions, virtual assistant, analytics data, and much more