Will AI Learn to Become a Better Entrepreneur than You?
Contemporary businesses use artificial intelligence (AI) tools to assist with operations and compete in the marketplace. AI enables firms and entrepreneurs to make data-driven decisions and to quicken the data-gathering process. When creating strategy, buying, selling, and increasing marketplace discovery, firms need to ask: What is better, artificial or human intelligence?
A recent article from the Harvard Business Review, “Can AI Help You Sell?,” stated, “Better algorithms lead to better service and greater success.” The attributes of the successful entrepreneur, such as calculated risk taking, dealing with uncertainty, keen sense for market signals, and adjusting to marketplace changes might be a thing of the past. Can AI take the place of the human entrepreneur? Would sophisticated artificial intelligence be able to spot market prices better, adjust to expectations better, and steer production toward the needs of consumers better than a human?
In one of my classes this semester, students and I discussed the role of AI, deep machine learning, and natural language processing (NLP) in driving many of the decisions and operations a human would otherwise provide within the firm. Of course, half of the class felt that the integration of some level of AI into many firms’ operations and resource management is beneficial in creating a competitive advantage.
However, the other half felt using AI will inevitably disable humans’ function in the market economy, resulting in less and less individualism. In other words, the firm will be overrun by AI. We can see that even younger college students are on the fence about whether AI will eliminate humans’ function in the market economy. We concluded as a class that AI and machine learning have their promises and shortcomings.
After class, I started thinking about the digital world of entrepreneurship. E-commerce demands the use of AI to reach customers, sell goods, produce goods, and host exchange—in conjunction with a human entrepreneur, of course.
However, AI—machine learning or deep machine learning—could also be tasked with creating a business-based model, examining the data on customers’ needs, designing a web page, and creating ads. Could AI adjust to market action and react to market uncertainty like a human? The answer may be a resounding yes! So, could AI eliminate the human entrepreneur?
Algorithm-XLab explains deep machine learning as something that “allows computers to solve complex problems. These systems can even handle diverse masses of unstructured data set.” Algorithm-XLab compared deep learning with human learning favorably, stating, “While a human can easily lose concentration, and possibly make a mistake, a robot won’t.”
This statement by Algorithm-XLab challenges the idea that trial and error leads to greater market knowledge and better enables entrepreneurs to provide consumers with what they are willing to buy. The statement also portrays the marketplace as a process where people have perfect knowledge and an equilibrium point, and it implies that humans do not have specialized knowledge of time and place.
The use of AI and its tools of deep learning and language processing do have their benefits from a technical standpoint. AI can determine how to produce hula hoops better, but can it determine whether to produce them or devote energy elsewhere? If entrepreneurs discover market opportunities, they must weigh the advantages and disadvantages of their potential actions. Will AI have the same entrepreneurial foresight?
The acquisition of market knowledge can take humans years to acquire; AI is much faster at it than humans would be. For example, the Allen Institute for AI is “working on systems that can take science tests, which require a knowledge of unstated facts and common sense that humans develop over the course of their lives.” The ability to process unstated, scattered facts is precisely the kind of characteristic we attribute to entrepreneurs. Processes, changes, and choices characterize the operation of the market, and the entrepreneur is at the center of this market function.
There is no doubt that contemporary firms use deep learning for strategy, operations, logistics, sales, and record keeping for human resources (HR) decision-making, according to a Bain & Company article titled “HR’s New Digital Mandate.” While focused on HR, the digital mandate does lend itself to questioning the use of entrepreneurial thinking and strategy conducted within a firm. After AI has learned how to operate a firm using robotic process automation and NLP capacities to their maximum, might it outstrip the human natural entrepreneurial abilities?
AI is used in everyday life, such as self-checkout at the grocery store, online shopping, social media interaction, dating apps, and virtual doctor appointments. Product delivery, financing, and development services increasingly involve an AI-as-a-service component. AI as a service minimizes the costs of gathering and processing customer insights, something usually associated with a team of human minds projecting key performance indicators aligned with an organizational strategy.
The human entrepreneur has a competitive advantage insofar as handling ambiguous customer feedback and in effect creating an entrepreneurial response and delivering satisfaction. We seek to determine whether AI has replaced human energy in some areas of life. Can AI understand human uneasiness or dissatisfaction, or the subjectivity of value felt by the consumer? AI can produce hula hoops, but can it articulate plans and gather the resources needed to produce them in the first place?.
In what, if any, entrepreneurial functions can AI outperform the human entrepreneur? The human entrepreneur is willing to take risks, adjust to the needs of consumers, pick up price signals, and understand customer choices. Could the human entrepreneur soon become an extinct class? If so, would machine learning and natural processing AI understand the differences between free and highly regulated markets? If so, which would it prefer, or which would it create?
Getting to Know ChatGPT: A Shallow Dip into Its Current Functionality and Future Potential
ChatGPT and the underlying AI technology are, as near as anyone can tell, the next-level toolkit for research, communication, idea generation, and a million other uses. If you haven’t introduced yourself to it yet, leave plenty of time – getting started is easy, but getting yourself to stop may not be. Those of us that were around pre-internet may liken the first-time experience to the first time we gained access to the world wide web. The Sudden, much easier access to a world of information, puts one in a place where you don’t know what to try first.
Over the past couple of months, the now-familiar name, ChatGPT has made headlines. It quickly captivated the worlds imagination as an AI product that is likely to disrupt or destroy some industries while enhancing others. Obviously, this is of particular interest to investors. With this in mind, I sat down for an interview with ChatGPT; below are answers to questions that many investors are asking.
Channelchek (PH) – Am I able to interview Chatgpt?
ChatGPT – Hello! As an AI language model, I’m happy to answer any questions you may have. However, it’s important to keep in mind that I don’t have personal experiences or opinions like a human, and I can only provide information based on my training data. So feel free to ask me anything!
Channelchek (PH) – What do most users have ChatGPT to do for them?
ChatGPT – As an AI language model, ChatGPT can be used for a wide range of tasks, including:
Language translation: ChatGPT can be used to translate text from one language to another.
Content creation: ChatGPT can generate text for various types of content, such as articles, blog posts, and product descriptions.
Chatbot development: ChatGPT can be used to develop chatbots that can interact with users and provide information.
Sentiment analysis: ChatGPT can be used to analyze the sentiment of a piece of text, such as a social media post or a product review.
Question-answering: ChatGPT can be used to answer questions on a wide range of topics.
Text summarization: ChatGPT can be used to summarize long pieces of text into shorter, more manageable summaries.
Language modeling: ChatGPT can be used to train new models for specific domains, such as medical or legal language.
These are just a few examples of what ChatGPT can be used for. Its versatility and flexibility make it a powerful tool for many different applications.
Channelchek (PH) – From where do you pull your answers ChatGPT?
ChatGPT – As an AI language model, I don’t have pre-programmed answers. Instead, I generate responses to questions by analyzing patterns in large amounts of text data that I was trained on. Specifically, I was trained on a dataset of billions of words from various sources, including books, articles, websites, and other textual sources. During my training, I was exposed to a wide range of topics and writing styles, which helps me generate responses to many different types of questions.
When you ask me a question, I use natural language processing (NLP) techniques to analyze the question and generate a response based on patterns in the text data that I was trained on. I then use statistical models to determine the most likely response based on the context of the question and the patterns in the training data.
It’s important to note that my responses are only as accurate and reliable as the patterns that I learned during my training. While I strive to provide accurate and helpful information, I may not always get it right, and my responses may not reflect the views or opinions of OpenAI.
Channelchek (PH) – Are you at risk of having the response you generate slanted or biased based on users feedback adjusting your training ChatGPT?
ChatGPT – As an AI language model, I am designed to learn from the data that I am trained on, including the feedback that users provide to adjust my training. However, it’s important to be aware that the feedback that users provide can sometimes introduce biases into my training.
If the feedback is consistently biased in a particular direction, this could affect the accuracy and fairness of my responses. This is why it’s important to carefully monitor and evaluate any feedback that is used to adjust my training, and to ensure that it is representative of a wide range of perspectives.
To address this issue, OpenAI has implemented a number of safeguards to prevent bias and ensure that my training data is as accurate and diverse as possible. For example, the training data is carefully curated to include a wide range of sources and perspectives, and the training process is carefully monitored to ensure that biases are not introduced.
Additionally, OpenAI has implemented a number of techniques to help identify and mitigate any biases that may be present in the training data or feedback. For example, I am periodically evaluated to ensure that my responses are accurate and unbiased, and any issues that are identified are addressed through additional training or other adjustments to the model.
Channelchek (PH) – As an editor I write for Channelchek about stocks, the financial markets, the economy and business climate. Are you a good resource for current events related to these topics ChatGPT?
ChatGPT – As an AI language model, I can certainly provide you with information on current events related to stocks, financial markets, the economy, and the business climate. I have been trained on a vast amount of text data, including news articles and other sources related to these topics, so I can provide you with up-to-date information and insights on current events.
When asking me questions related to these topics, it’s important to provide me with as much context and specificity as possible so that I can provide you with the most accurate and relevant information. For example, if you are looking for information on a particular company or sector, you could provide me with the name of the company or sector, as well as any other relevant details or questions you may have.
However, it’s important to note that my responses are generated based on patterns in the text data that I was trained on, and may not reflect the views or opinions of OpenAI. Additionally, while I can provide you with information on current events and trends, I cannot provide investment advice or make predictions about future market performance. It’s always important to carefully evaluate information and seek the advice of a qualified financial professional before making investment decisions.
Channelchek (PH) – Do users ask you to forecast the stock market direction?
ChatGPT – Yes, users sometimes ask me to forecast the direction of the stock market. However, as an AI language model, I cannot make accurate predictions about future market performance. While I can provide information on current market trends and historical data, predicting the future direction of the stock market is a highly complex task that involves a range of economic, political, and social factors.
It’s important to note that investing in the stock market involves a certain degree of risk, and investors should always carefully evaluate market conditions and seek the advice of a qualified financial professional before making investment decisions. While I can provide general information and insights related to stocks and financial markets, I cannot provide investment advice or predict the future performance of individual stocks or the overall market.
Channelchek (PH) – Are you familiar with Channelchek?
ChatGPT – While I am not specifically programmed to be familiar with individual websites, I may have come across content from Channelchek during my training.
That being said, I can still provide you with general information on what Channelchek is. From my understanding, Channelchek is a financial information platform that provides independent research, analysis, and market commentary on publicly traded companies. It offers a range of tools and resources for investors and financial professionals, including market data, stock quotes, and research reports.
Channelchek’s focus is on providing unbiased and independent information to help investors make informed investment decisions.
Channelchek (PH) – Does your AI technology pose a risk to traditional internet search engines?
ChatGPT – My purpose is not to compete with traditional search engines like Google or Bing, but rather to complement them by providing an additional source of information and assistance to users. While I am capable of providing answers to a wide range of questions and generating responses to open-ended queries, I am not designed to replace traditional search engines or web browsing.
Search engines like Google and Bing are still the primary means by which users navigate the internet and find information, and they use a range of sophisticated algorithms and machine learning techniques to index and rank content on the web. While I am capable of processing natural language queries and generating responses, my training data is based on pre-existing content, which means that my responses are generated based on patterns in the text data that I was trained on, rather than direct access to the vast amounts of data on the internet.
Early Boolean Phrase Search Tool
Overall, AI language models like me are part of a larger ecosystem of tools and technologies that are designed to help users access and navigate the vast amount of information available online. While there may be some overlap between the capabilities of traditional search engines and AI language models, both serve different purposes and can work together to provide users with the most comprehensive and accurate information possible.
Channelchek (PH) – What industries are you likely to disrupt and which are you likely to augment or help build?
ChatGPT – As an AI language model, my capabilities are quite broad, and I have the potential to impact a wide range of industries and areas of society. Here are a few ways in which I could potentially disrupt or augment various industries:
Industries that could be disrupted:
Customer service: AI language models like me are already being used by many companies to automate and improve customer service interactions, and this trend is likely to continue. As AI technology improves, it could potentially replace many human customer service jobs.
Content creation: AI language models have the potential to automate certain types of content creation, such as news articles, product descriptions, and even social media posts. This could have a significant impact on the journalism and writing industries.
Education: AI language models could potentially disrupt the traditional education model by providing personalized learning experiences and automating certain types of teaching and grading.
Industries that could be augmented:
Healthcare: AI language models could help augment healthcare by providing more accurate and personalized diagnoses, and by automating certain types of administrative tasks.
Finance: AI language models could help augment finance by providing more accurate and data-driven investment advice, and by automating certain types of financial analysis.
Research: AI language models could help augment research by processing and analyzing vast amounts of data, and by identifying patterns and insights that might be difficult for humans to spot on their own.
Overall, the impact of AI language models like me on various industries will depend on a wide range of factors, including the development of the technology, the regulatory environment, and societal attitudes toward automation and AI. While there may be some industries that are more susceptible to disruption or augmentation than others, it’s important to approach these developments with a nuanced understanding of the potential benefits and risks.
Channelchek (PH) – Are users using ChatGPT to create social media bots to respond without human intervention likely to flood the internet?
ChatGPT – While it is technically possible for users to use AI language models like ChatGPT to create social media bots that can respond to messages without human intervention, I cannot speculate on whether this is likely to flood the internet.
The use of AI language models like ChatGPT could potentially make it easier and more accessible for users to create more sophisticated chatbots that can mimic human conversation more convincingly.
It’s also important to consider the potential impact of widespread use of social media bots on the quality and authenticity of online interactions. While chatbots can be useful in certain contexts, they can also be used to spread misinformation and propaganda or to manipulate public opinion. As with any technology, it’s important to approach the use of AI language models and chatbots in a responsible and ethical way, and to consider the potential risks and benefits of their use.
Channelchek (PH) – What do you call one that uses ChatGPT?
ChatGPT – There is no specific term for a person who uses ChatGPT or other AI language models, as these tools are designed to be accessible and usable by anyone with an internet connection.
However, a person who uses ChatGPT to create chatbots or other automated tools could be referred to as an AI developer or AI engineer. Similarly, a person who uses ChatGPT to conduct research or analysis in a specific field could be referred to as an AI researcher or analyst.
Channelchek (PH) – How much do you cost?
As an AI language model, I do not have a specific cost as I am not a commercial product. My purpose is to provide information and assistance to users like you, and I am freely accessible through various platforms that integrate my technology, including chatbots, voice assistants, and search engines.
Channelchek (PH) – Should I throw out the encyclopedias on my book shelf and rely instead on ChatGPT?
ChatGPT – Ultimately, whether or not to keep your encyclopedias depends on your personal preferences and how you prefer to access information. While AI language models like ChatGPT are convenient and accessible, they may not always provide the level of detail or accuracy that you require for a specific question or topic. So, it’s always a good idea to consult multiple sources of information to ensure that you have a well-rounded understanding of a given topic.
Channelchek (PH) – How does one get started using ChatGPT for research?
ChatGPT – Getting started with using ChatGPT for research can involve several steps. Here are a few basic steps you can follow:
Identify your research question or topic: Start by identifying the research question or topic you want to investigate. This will help you to focus your search and make the best use of ChatGPT.
Choose a ChatGPT platform: There are several platforms that integrate ChatGPT, including chatbots, voice assistants, and search engines. Choose a platform that best fits your needs and preferences.
Familiarize yourself with the platform: Once you have chosen a platform, take some time to explore and familiarize yourself with its features and capabilities. Many platforms offer tutorials and guides to help you get started.
Start asking questions: Once you are comfortable with the platform, start asking questions related to your research topic. Try to ask open-ended questions that will allow ChatGPT to provide more detailed and relevant answers.
Evaluate the results: As you receive answers from ChatGPT, evaluate the accuracy and relevance of the information. Keep in mind that ChatGPT is not perfect and may not always provide the most accurate or comprehensive information. Be sure to double-check any information you receive with other sources to ensure its accuracy.
Refine your search: If you are not finding the information you need, try refining your search by using more specific keywords or phrases.
Overall, using ChatGPT for research can be a valuable tool for gathering information and conducting preliminary investigations. However, it’s important to keep in mind that it is just one tool in the research process, and should be used in conjunction with other sources of information and research methods.
Wrap Up
It’s easy to comprehend how this technology, which will likely see stronger competition in the coming year, will quickly become something that is used every day to help streamline how we do our jobs, and find information in our personal lives. Unlike an internet search engine, queries produce individual results tailored to the individual question. The same question will recieve different phraseology if asked a minute later. Whereas Google or DuckDuckGo list websites that may provide the answer, ChatGPT responds using its own answer using artificial intelligence.
Getting started is as easy as going to OpenAI.com and navigating to Chat.OpenAI.com and providing an email and verification phone number. Click on my name below and write me, I’d love to hear what you are using it for.
Recent Investment Trends Include Small-Cap Artificial Intelligence Stocks
C3 AI, sometimes written C3.ai, is an artificial intelligence platform that provides services for companies to build large-scale AI applications. Its stock had the fifth highest traded shares among Fidelity’s retail investors on Monday (February 6). This included a record-breaking $31.4 million worth of shares traded among the broker’s individual self-directed traders. According to Reuters, “Retail investors are piling up on small-cap firms that employ artificial intelligence amid intensifying competition between tech titans.” The article points to Google and Microsoft as examples of companies that expect AI to be the next meaningful driver of growth.
Investors, for their part, are looking to get ahead of any acquisition spree that deep-pocketed companies may embark on, which could include buying the advanced technology by acquiring small-cap tech firms.
Focus Heightened by ChatGPT
The spotlight ChatGPT finds itself in, three months after its launch, is indicicative of the interest in this technology amongst investors and users. With applications as numerous than one can think up, the technology could outdate many services provided by tech companies like Alphabet (GOOGL), or Microsoft (MSFT) – big tech has catching up to do. This seems to have created a race by cash rich companies to not be disrupted and left behind.
Investor’s recent focus on small companies in this space prefer those that are concentrated in AI technology. One main reason is that small-cap or microcap firms in this space are likely to have AI as a more concentrated part of their business. The bet being that whether the small company continues to grow independently, or is acquired by a larger firm looking to instantly be par with current technology, doesn’t much matter, it is a win for the investor if either occurs.
And it is a win, C3 AI stock rallied 46% last week, and climbed another 6.5% on Monday. It is now up 146% year to date.
Other Companies Involved
SoundHound AI, provides a voice AI platform services, and Thailand-based security firm Guardforce AI have more than doubled so far this year, while analytics firm BigBear.AI has increased ninefold.
US-listed shares of Baidu Inc climbed after the Chinese search engine indicated it would complete an internal test of a ChatGPT-style project called “Ernie Bot” next month.
Shares of Microsoft, which supports ChatGPT parent OpenAI, had been ratcheting up over the past month. The company is expected to make an announcement on their AI gained 1.5% in premarket trading ahead of the AI plans this week.
Google-owner Alphabet Inc said this week it would launch Bard, a chatbot service for developers, alongside its search engine.
Take Away
Change in technology that leads to improvements in daily lives has always been a focus of investors betting on which companies will outlast the others with “the next big thing.” These companies start out as small growth companies as Apple (AAPL) did in 1976. Then, a number of paths lay ahead. They either grow on their own like the Jobs/Wozniak computer maker did, get acquired for an early payday for investors and other stakeholders, or they can be outcompeted leaving investors with a non-performing asset.
Channelchek is a platform that specializes in bringing data and research on small-cap companies, including many varieties of new technology, to the investors that insist on being informed before they place a trade. Discover more on the industries of tomorrow by signing up for notifications in your inbox from Channelchek by registering here.
Deepfake Audio Has a Tell – Researchers Use Fluid Dynamics to Spot Artificial Imposter Voices
Imagine the following scenario. A phone rings. An office worker answers it and hears his boss, in a panic, tell him that she forgot to transfer money to the new contractor before she left for the day and needs him to do it. She gives him the wire transfer information, and with the money transferred, the crisis has been averted.
The worker sits back in his chair, takes a deep breath, and watches as his boss walks in the door. The voice on the other end of the call was not his boss. In fact, it wasn’t even a human. The voice he heard was that of an audio deepfake, a machine-generated audio sample designed to sound exactly like his boss.
Attacks like this using recorded audio have already occurred, and conversational audio deepfakes might not be far off.
Deepfakes, both audio and video, have been possible only with the development of sophisticated machine learning technologies in recent years. Deepfakes have brought with them a new level of uncertainty around digital media. To detect deepfakes, many researchers have turned to analyzing visual artifacts – minute glitches and inconsistencies – found in video deepfakes.
Audio deepfakes potentially pose an even greater threat, because people often communicate verbally without video – for example, via phone calls, radio and voice recordings. These voice-only communications greatly expand the possibilities for attackers to use deepfakes.
To detect audio deepfakes, we and our research colleagues at the University of Florida have developed a technique that measures the acoustic and fluid dynamic differences between voice samples created organically by human speakers and those generated synthetically by computers.
Organic vs. Synthetic voices
Humans vocalize by forcing air over the various structures of the vocal tract, including vocal folds, tongue and lips. By rearranging these structures, you alter the acoustical properties of your vocal tract, allowing you to create over 200 distinct sounds, or phonemes. However, human anatomy fundamentally limits the acoustic behavior of these different phonemes, resulting in a relatively small range of correct sounds for each.
In contrast, audio deepfakes are created by first allowing a computer to listen to audio recordings of a targeted victim speaker. Depending on the exact techniques used, the computer might need to listen to as little as 10 to 20 seconds of audio. This audio is used to extract key information about the unique aspects of the victim’s voice.
The attacker selects a phrase for the deepfake to speak and then, using a modified text-to-speech algorithm, generates an audio sample that sounds like the victim saying the selected phrase. This process of creating a single deepfaked audio sample can be accomplished in a matter of seconds, potentially allowing attackers enough flexibility to use the deepfake voice in a conversation.
This article was republished with permission from The Conversation, a news site dedicated to sharing ideas from academic experts. It represents the research-based findings and thoughts of Logan Blue, PhD student in Computer & Information Science & Engineering, University of Florida and Patrick Traynor, Professor of Computer and Information Science and Engineering, University of Florida.
Detecting Audio Deepfakes
The first step in differentiating speech produced by humans from speech generated by deepfakes is understanding how to acoustically model the vocal tract. Luckily scientists have techniques to estimate what someone – or some being such as a dinosaur – would sound like based on anatomical measurements of its vocal tract.
We did the reverse. By inverting many of these same techniques, we were able to extract an approximation of a speaker’s vocal tract during a segment of speech. This allowed us to effectively peer into the anatomy of the speaker who created the audio sample.
Deepfaked audio often results in vocal tract reconstructions that resemble drinking straws rather than biological vocal tracts. Logan Blue (The Conversation)
From here, we hypothesized that deepfake audio samples would fail to be constrained by the same anatomical limitations humans have. In other words, the analysis of deepfaked audio samples simulated vocal tract shapes that do not exist in people.
Our testing results not only confirmed our hypothesis but revealed something interesting. When extracting vocal tract estimations from deepfake audio, we found that the estimations were often comically incorrect. For instance, it was common for deepfake audio to result in vocal tracts with the same relative diameter and consistency as a drinking straw, in contrast to human vocal tracts, which are much wider and more variable in shape.
This realization demonstrates that deepfake audio, even when convincing to human listeners, is far from indistinguishable from human-generated speech. By estimating the anatomy responsible for creating the observed speech, it’s possible to identify the whether the audio was generated by a person or a computer.
Why this matters
Today’s world is defined by the digital exchange of media and information. Everything from news to entertainment to conversations with loved ones typically happens via digital exchanges. Even in their infancy, deepfake video and audio undermine the confidence people have in these exchanges, effectively limiting their usefulness.
If the digital world is to remain a critical resource for information in people’s lives, effective and secure techniques for determining the source of an audio sample are crucial.
