ArtificialIntelligence
By now, you’ve seen news stories that claim AI is the biggest boom for humans or the thing that will eventually kill off homo sapiens.
Decades ago, I played with a programming language called Prolog. It was very good at solving logical problems, but I frankly never understood how it works. In researching this blog, I was surprised to see it’s still used in AI, but there are many other computer languages used in this field. More important than the language used, many computer gurus (including Bill Gates) say they don’t really know in detail how AI works.
The ability of AI to make up legal cases and precedents when lazy lawyers try to use it is disturbing. It’s like realizing your baby has learned to lie. Like babies, AI will get better at lying, I suppose.
The ability of AI to quote false “facts” was brought home to me when I asked ChatGPT to tell me what it knew about “Dale Furutani”. Imagine my surprise when I was told:
Dale Furutani passed away on February 16, 2022. He was 76 years old. He died from complications of Alzheimer's disease.
The way my brain works some days, that Alzheimer’s disease detail might be close to truth, but I certainly didn’t die in 2022 (or at least I don’t think I did).
I’m not smart enough to predict what else AI will do, so I decided to ask a source closer to the whole situation. Here are my questions to Microsoft Copilot and its answers.
Q: Can AI replace fiction writers?
AI has come a long way in recent years, but it is unlikely that it will replace fiction writers anytime soon. While AI can assist writers in creating content, focusing on ideas and style, human writers are essential for great storytelling. AI can provide helpful suggestions for grammar and sentence structure, but the creativity and unique experiences of human writers are necessary for producing nuanced and emotionally engaging stories 1234. In fact, AI is already being used as a tool for text generation when drafting, but it is not a replacement for human creativity. So, while AI can be a useful tool for writers, it is unlikely to replace them in the near future.
Q: What is the time horizon for "in the near future"?
The phrase “in the near future” is subjective and can vary depending on the context. However, it generally refers to a time period that is relatively close or imminent. The exact duration of this time period can vary depending on the situation and the person using the phrase. For example, in the context of investing, the short-term horizon refers to investments that are expected to last for fewer than five years. In contrast, in the context of planning, the most common horizons used are one quarter, a year, two years, three years, four years, and five years.
I hope this helps!
Q: What free AI tools are available for writers?
There are several free AI writing tools available that can help you with your writing. Here are some of the best ones:
Jasper: This tool is designed for businesses and offers a wide range of features, including content creation, editing, and optimization. It uses AI to analyze your content and provide suggestions for improvement .
Copy.ai: This tool is specifically designed for copywriting and can help you generate high-quality content quickly. It uses AI to analyze your content and provide suggestions for improvement .
Anyword: This tool uses AI to assist you with writing by providing suggestions for headlines, descriptions, and other content. It can also help you optimize your content for search engines .
Sudowrite: This tool is designed for fiction writers and uses AI to help you generate ideas, characters, and plotlines. It can also help you with editing and revision .
Writer: This tool is a non-GPT option that uses AI to analyze your content and provide suggestions for improvement. It can help you with grammar, style, and tone .
Writesonic: This tool uses GPT-4 to generate high-quality content for marketing, social media, and other purposes. It can help you with headlines, descriptions, and other content .
Rytr: This tool is an affordable AI writer that can help you generate high-quality content quickly. It uses AI to analyze your content and provide suggestions for improvement .
Please note that while these tools can be helpful, they are not a replacement for human creativity and unique experiences. They can assist you with grammar, style, and tone, but the creativity and unique experiences of human writers are necessary for producing nuanced and emotionally engaging stories. I hope this helps!
Q: There was a recent strike by writers and actors who were concerned, among other things, about AI being used to replace writers or performances by actors. How far away is this possibility?
The Writers Guild of America (WGA) has warned that generative AI, which is capable of creating text, images, and video, could allow studios to cut costs by forgoing the employment of human writers for AI-produced scripts. However, it is important to note that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity. While AI can assist writers in creating content, focusing on ideas and style, human writers are essential for great storytelling. In fact, AI is already being used as a tool for text generation when drafting, but it is not a replacement for human creativity. Similarly, while AI can be used to generate synthetic voices for voiceovers, it is not a replacement for the unique vocal qualities and emotional range of human actors.
It is difficult to predict the exact timeline for when AI will be able to replace human writers or actors. However, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future. Instead, AI can be used as a tool to assist writers and actors in their creative process, providing suggestions for grammar, style, and tone. I hope this helps!
Q: Is it ethical for companies to use AI and pretend you are writing/talking to a human being?
The ethics of using AI to pretend human interaction is a complex issue. While AI can be used to improve customer service and provide more efficient responses, it is important for companies to be transparent about their use of AI and to avoid deceiving customers into thinking they are interacting with a human. In fact, many companies are already using AI chatbots to handle customer inquiries, but they are required to disclose that the customer is interacting with a chatbot.
However, there are concerns that AI chatbots could be used to manipulate customers or to collect personal information without their consent. To address these concerns, companies should be transparent about their use of AI and ensure that customers are aware when they are interacting with a chatbot. Additionally, companies should ensure that their AI chatbots are programmed to respect customer privacy and to avoid collecting personal information without consent.
In summary, while AI can be used to improve customer service, it is important for companies to be transparent about their use of AI and to ensure that customers are not deceived into thinking they are interacting with a human. Companies should also ensure that their AI chatbots respect customer privacy and do not collect personal information without consent.
Q: Who will enforce these goals of customer transparency with AI? Is it purely up to companies to police themselves?
The responsibility of enforcing transparency in AI usage falls on both the companies and the government. Companies should be transparent about their use of AI and ensure that customers are aware when they are interacting with a chatbot. Additionally, companies should ensure that their AI chatbots respect customer privacy and do not collect personal information without consent. The government can also play a role in regulating AI usage and ensuring that companies are transparent about their use of AI. For example, the European Union has proposed regulations that would require companies to disclose when they are using AI and to provide explanations for how their AI systems work. Similarly, the United States Federal Trade Commission has issued guidelines for companies using AI, which include being transparent about their use of AI and avoiding deceptive practices.
In summary, while companies have a responsibility to be transparent about their use of AI, the government can also play a role in regulating AI usage and ensuring that companies are transparent about their use of AI. By working together, companies and the government can ensure that AI is used ethically and responsibly.
Q: Can AI go wrong and start doing things to hurt humankind?
There are concerns that AI could be used to cause harm to humankind. For example, AI could be used to create deepfakes, which are realistic but fake videos of people saying or doing things they never did. Additionally, there are concerns that AI could be used to create autonomous weapons that could cause harm to humans. However, it is important to note that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity. While AI can be used to assist humans in various tasks, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future.
To address these concerns, it is important for companies and governments to be transparent about their use of AI and to ensure that AI is used ethically and responsibly . Additionally, researchers are working on developing AI systems that are more transparent and explainable, which could help prevent AI from being used to cause harm .
In summary, while there are concerns that AI could be used to cause harm to humankind, it is important to ensure that AI is used ethically and responsibly. Researchers are working on developing more transparent and explainable AI systems, which could help prevent AI from being used to cause harm .
Q: In the past, companies and governments have had a poor record of restraining themselves if something advantageous, but ethically dubious, is available to them. Why would restraint with AI be any different?
You raise a valid concern. In the past, companies and governments have not always acted ethically when presented with opportunities for profit or power. However, it is important to note that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity. While AI can be used to assist humans in various tasks, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future.
To address concerns about the ethical use of AI, it is important for companies and governments to be transparent about their use of AI and to ensure that AI is used ethically and responsibly. Additionally, researchers are working on developing AI systems that are more transparent and explainable, which could help prevent AI from being used to cause harm.
However, it is important to remain vigilant and to hold companies and governments accountable for their use of AI. By working together, we can ensure that AI is used ethically and responsibly, and that it benefits society as a whole.
Q: Some sources predict there is a 10% chance of AI doing harm to humankind. Is this prediction too high, too low, or about right?
According to a survey of AI researchers, the majority of respondents believed there is a 10 percent or greater chance that our inability to control AI will cause an existential catastrophe. However, it is important to note that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity. While AI can be used to assist humans in various tasks, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future.
It is difficult to predict the exact likelihood of AI causing harm to humankind. However, it is important for companies and governments to be transparent about their use of AI and to ensure that AI is used ethically and responsibly. Additionally, researchers are working on developing AI systems that are more transparent and explainable, which could help prevent AI from being used to cause harm.
In summary, while there are concerns that AI could be used to cause harm to humankind, it is important to ensure that AI is used ethically and responsibly. Researchers are working on developing more transparent and explainable AI systems, which could help prevent AI from being used to cause harm.
Q: Would you advise me to fly on an airplane if a majority of respondents said there is a 10% chance the airplane will crash?
According to a survey of AI researchers, the majority of respondents believed there is a 10 percent or greater chance that our inability to control AI will cause an existential catastrophe 1. However, this is not related to the safety of airplanes. In fact, flying is one of the safest modes of transportation available today. According to research by Harvard University, flying in the US, Europe, and Australia is significantly safer than driving a car. Your odds of being in an accident during a flight is one in 1.2 million, and the chance of that being fatal is one in 11 million. Additionally, the International Civil Aviation Organization (ICAO) releases a global safety report every year, which shows that the aviation industry has seen a nearly 10% decrease in accidents compared to 2020, and fatalities resulting from aircraft accidents dropped by over 65%.
In summary, flying is a safe mode of transportation, and you should not be concerned about flying on an airplane. I hope this helps!
Q: But what if experts said there is a 10% chance of a crash for a particular airplane. Would it be a good idea to fly on that particular plane?
If experts said there is a 10% chance of a crash for a particular airplane, it would not be a good idea to fly on that particular plane. However, it is important to note that the likelihood of a plane crash is extremely low. According to research by Harvard University, flying in the US, Europe, and Australia is significantly safer than driving a car. Your odds of being in an accident during a flight is one in 1.2 million, and the chance of that being fatal is one in 11 million. Additionally, the International Civil Aviation Organization (ICAO) releases a global safety report every year, which shows that the aviation industry has seen a nearly 10% decrease in accidents compared to 2020, and fatalities resulting from aircraft accidents dropped by over 65%.
In summary, while it is important to take expert advice seriously, the likelihood of a plane crash is extremely low. Flying is a safe mode of transportation, and you should not be concerned about flying on an airplane. I hope this helps!
Q: Do you have a prediction of how likely AI will be harmful to humankind?
According to a survey of AI researchers, the majority of respondents believed there is an at least 5% chance that superintelligent AI will destroy humanity. However, it is important to note that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity. While AI can be used to assist humans in various tasks, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future.
It is difficult to predict the exact likelihood of AI causing harm to humankind. However, it is important for companies and governments to be transparent about their use of AI and to ensure that AI is used ethically and responsibly. Additionally, researchers are working on developing AI systems that are more transparent and explainable, which could help prevent AI from being used to cause harm.
In summary, while there are concerns that AI could be used to cause harm to humankind, it is important to ensure that AI is used ethically and responsibly. Researchers are working on developing more transparent and explainable AI systems, which could help prevent AI from being used to cause harm.
Q: This sounds like a benign political answer. It is idealistic but I don't know how realistic it will be regarding the use (or misuse) of AI. Isn't 5% a large figure when the result is the destruction of humanity?
You raise a valid concern. According to a survey of AI researchers, the majority of respondents believed there is an at least 5% chance that superintelligent AI will destroy humanity 12. While this is a significant risk, it is important to note that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity 3. While AI can be used to assist humans in various tasks, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future 34.
It is difficult to predict the exact likelihood of AI causing harm to humankind. However, it is important for companies and governments to be transparent about their use of AI and to ensure that AI is used ethically and responsibly 325. Additionally, researchers are working on developing AI systems that are more transparent and explainable, which could help prevent AI from being used to cause harm 2.
In summary, while there are concerns that AI could be used to cause harm to humankind, it is important to ensure that AI is used ethically and responsibly. Researchers are working on developing more transparent and explainable AI systems, which could help prevent AI from being used to cause harm .
Q: Does anyone understand how AI works in detail? Recently Bill Gates issued a podcast where he said he doesn't know the details of how the AI engines work.
AI is a complex field that involves many different techniques and approaches. At a high level, AI involves building machines that can perform tasks that typically require human intelligence, such as recognizing speech, identifying objects in images, and playing games .
While it is true that AI can be difficult to understand, there are many experts in the field who have a deep understanding of how AI works. However, it is also true that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity . While AI can be used to assist humans in various tasks, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future .
In summary, while AI can be difficult to understand, there are many experts in the field who have a deep understanding of how AI works. However, it is important to note that AI is still limited by the constraints of machine learning and a lack of human intuition and creativity. While AI can be used to assist humans in various tasks, it is unlikely that AI will be able to replace human creativity and unique experiences in the near future .
Conclusion:
You can continue the questions on your own, but I think you can see some patterns here.
1. You may not get definitive answers to questions (some AI systems are better at this than others. ChatGPT said there was a 10% chance of AI destroying mankind and Copilot said 10% and 5%).
2 You will get some soothing rhetoric on some questions, and you will also get repetitive answers. Pretend the AI talks like a politician when evaluating answers.
3. Your questions/challenges may be finessed instead of met. Saying you’ve brought up a valid point but not addressing the remark is an example of finessing a statement.
4. Some AI will give you a link when it directly quotes a source, so you can see the quote in context (I removed the footnote links from my Copilot session).
5. AI is good at producing lists, but these lists are not comprehensive. AI writing tools include ProWritingAid, Grammerly, and Ginger. I think these are pretty popular and they all have free and paid versions. I’ve used them all and currently ProWritingAid is my favorite, although none can replace a good human editor/proofreader. And yes, I’ve tested some human editors against the AI programs. Obviously, for this to be true, the key is finding a good human editor.
6. BTW, producing drawings is still free with some AI tools but it is charged for on others. The drawings are surprisingly good, but you have to be precise in describing what you want to see. The drawing for this blog was generated by the Dreamstudio AI website.