I Asked the AI Program ChatGPT to Write an Astromart Article – Here Are the Results
In December 2022, a chatbot called ChatGPT stunned the world with its impressive writing abilities. Developed by OpenAI, an Artificial Intelligence (AI) research and deployment company based in San Francisco, ChatGPT interacts with users in a simple conversational way. The quality results produced by the program have been so good that some secondary schools and colleges have already banned it for fear that students might use it to write essays. Microsoft Corporation is reportedly planning to incorporate ChatGPT into its Bing web search engine and Office products later this year. What does the unrelenting progress in AI mean for the future? Is AI likely to threaten certain jobs in the years to come? I put ChatGPT to the test and asked it to write an Astromart article. Here are the results. (Image Credit: NASA, MIT) (Content Credit: Marcel Scharth – University of Sydney, TheConversation.com, and OpenAI-ChatGPT)
AI Might Be Seemingly Everywhere, But There Are Still Plenty of Things It Can’t Do – For Now
By Marcel Scharth – Lecturer in Business Analytics, University of Sydney
These days, we don’t have to wait long until the next breakthrough in artificial intelligence (AI) impresses everyone with capabilities that previously belonged only in science fiction.
In 2022, AI art generation tools such as Open AI’s DALL-E 2, Google’s Imagen, and Stable Diffusion took the internet by storm, with users generating high-quality images from text descriptions.
Unlike previous developments, these text-to-image tools quickly found their way from research labs to mainstream culture, leading to viral phenomena such as the “Magic Avatar” feature in the Lensa AI app, which creates stylized images of its users.
In December, a chatbot called ChatGPT stunned users with its writing skills, leading to predictions the technology will soon be able to pass professional exams. ChatGPT reportedly gained one million users in less than a week. Some school officials have already banned it for fear students would use it to write essays. Microsoft is reportedly planning to incorporate ChatGPT into its Bing web search and Office products later this year.
What does the unrelenting progress in AI mean for the near future? And is AI likely to threaten certain jobs in the following years?
Despite these impressive recent AI achievements, we need to recognize there are still significant limitations to what AI systems can do.
AI excels at pattern recognition
Recent advances in AI rely predominantly on machine learning algorithms that discern complex patterns and relationships from vast amounts of data. This training is then used for tasks like prediction and data generation.
The development of current AI technology relies on optimizing predictive power, even if the goal is to generate new output.
For example, GPT-3, the language model behind ChatGPT, was trained to predict what follows a piece of text. GPT-3 then leverages this predictive ability to continue an input text given by the user.
“Generative AIs” such as ChatGPT and DALL-E 2 have sparked much debate about whether AI can be genuinely creative and even rival humans in this regard. However, human creativity draws not only on past data but also on experimentation and the full range of human experience.
Cause and effect
Many important problems require predicting the effects of our actions in complex, uncertain, and constantly changing environments. By doing this, we can choose the sequence of actions most likely to achieve our goals.
But algorithms cannot learn about causes and effects from data alone. Purely data-driven machine learning can only find correlations.
To understand why this is a problem for AI, we can contrast the problems of diagnosing a medical condition versus choosing a treatment.
Machine learning models are often helpful for finding abnormalities in medical images – this is a pattern recognition problem. We don’t need to worry about causality because abnormalities are already either present or not.
But choosing the best treatment for a diagnosis is a fundamentally different problem. Here, the goal is to influence the outcome, not just recognize a pattern. To determine the effectiveness of a treatment, medical researchers run randomized controlled trials. This way, they can try to control any factors that might affect the treatment.
The confusion between these two types of problems sometimes leads to suboptimal applications of machine learning in organizations.
While the success of recent work in AI demonstrates the value of data-driven models, many of the problems we would want computers to solve require an understanding of causation.
Current AI systems lack this ability, apart from specialized applications such as board games.
Common sense reasoning
Language models such GPT-3 and ChatGPT can successfully solve some tasks requiring common-sense reasoning.
However, the following interaction with ChatGPT, adapted from an experiment by Gary Marcus (Professor in the Psychology Department at New York University) suggests it is not entirely reliable in this respect.
“I’m eight years old. When I was born, my biological mother was in Barcelona and my father was in Tokyo. Where was I born?”
Think through this step by step. It is not mentioned where you were born. All we know is that your biological mother was in Barcelona and your father was in Tokyo at the time of your birth.
Whether AI systems such as ChatGPT can achieve common sense is a subject of lively debate among experts.
Sceptics such as Marcus point out we cannot trust language models to robustly display common sense since they neither have it built into them nor are directly optimized for it. Optimists argue that while current systems are imperfect, common sense may spontaneously emerge in sufficiently advanced language models.
Whenever groundbreaking AI systems are released, news articles and social media posts documenting racist, sexist, and other types of biased and harmful behaviors inevitably follow.
This flaw is inherent to current AI systems, which are bound to be a reflection of their data. Human values such as truth and fairness are not fundamentally built into the algorithms – that’s something researchers don’t yet know how to do.
While researchers are learning the lessons from past episodes and making progress in addressing bias, the field of AI still has a long way to go to robustly align AI systems with human values and preferences.
An Astromart Article Written by ChatGBT
I put ChatGPT to the test and asked it to write an Astromart article about ground-based astronomical observatories. Here are the results.
Guy Pirro request:
Please list the most important ground-based astronomical observatories and tell me 5 interesting facts about each.
- Kitt Peak National Observatory (Arizona, USA):
- Located on the Tohono O'odham Nation in Arizona, Kitt Peak is home to one of the largest collections of optical and radio telescopes in the world.
- It is operated by the National Optical Astronomy Observatory (NOAO) and is a popular site for research and educational programs.
- It is named after the Tohono O'odham word for "mountain," and was established in 1958.
- The observatory is home to 22 optical telescopes and 2 radio telescopes.
- Some of the notable discoveries made at Kitt Peak include the detection of dark matter and the confirmation of the expansion of the universe.
- Mauna Kea Observatories (Hawaii, USA):
- Located on the summit of Mauna Kea on the island of Hawaii, the Mauna Kea Observatories are home to some of the most advanced telescopes in the world.
- The high altitude and dry, stable air make it an ideal location for astronomical observations.
- The Mauna Kea Observatories consist of 13 telescopes operated by 11 countries.
- The Keck Observatory's twin 10-meter telescopes are the largest telescopes in the world.
- The Mauna Kea Observatories have contributed to a number of significant scientific discoveries, including the detection of exoplanets and the confirmation of the existence of dark energy.
- Siding Spring Observatory (New South Wales, Australia):
- Siding Spring Observatory is located in the Warrumbungle National Park in New South Wales, Australia.
- It is home to a variety of telescopes, including the Anglo-Australian Telescope, which has played a key role in many important astronomical discoveries.
- The observatory was established in 1964 and is operated by the Australian National University.
- It is located in a region with low light pollution, making it ideal for observations of distant objects.
- Some of the notable discoveries made at Siding Spring Observatory include the detection of the first quasar and the identification of the most distant known galaxy.
- Cerro Tololo Inter-American Observatory (Chile):
- Located in the Chilean Andes, Cerro Tololo Inter-American Observatory is operated by the National Optical Astronomy Observatory (NOAO).
- It is home to a number of telescopes, including the Blanco Telescope, which is used to study distant galaxies and quasars.
- The observatory was established in the 1960s and is located at an altitude of 2200 meters.
- It is named after the indigenous Quechua word for "hill of the hole," referring to the hole in the mountain that the observatory is built into.
- Some of the notable discoveries made at Cerro Tololo Observatory include the measurement of the expansion rate of the universe and the detection of dark matter.
- Gemini Observatory (Hawaii and Chile):
- The Gemini Observatory consists of two 8-meter telescopes, one located on Mauna Kea in Hawaii and the other on Cerro Pachón in Chile.
- The telescopes are used to study a wide range of celestial objects, including stars, planets, and galaxies.
- The Gemini Observatory is operated by a consortium of universities and research institutions from the United States, Canada, and Chile.
- The telescopes are equipped with advanced instrumentation, including adaptive optics systems that can correct for distortions caused by the Earth's atmosphere.
- Some of the notable discoveries made using the Gemini Observatory include the detection of exoplanets and the measurement of the masses of black holes.
For more information:
Astromart News Archives:
Check out some of my favorite Words of Wisdom:
Do you enjoy reading these postings?
Then click here and buy the Astromart staff a cup of coffee (and maybe even some donuts):
This article is republished from The Conversation under a Creative Commons license. Read the original article.