Would ChatGPT3 Get a Wharton MBA?
How close are we to Artificial Intelligence becoming Artificial General Intelligence and taking over Humans Functions?
Would ChatGPT3 Get a Wharton MBA? Answer, Yes and here is the proof with the Questions and Answers. Quite a shocking discovery because if it can pass a Wharton MBA exam then what can it not do in the future? These findings were reported in a recent study by the Mack Institute for Innovation Management at the Wharton School.
Why are these Ivy League schools asking? Because they are deeply worried about their future and the implications of an AI that will soon morph into the next phase and that is called Artificial General Intelligence (AGI). It is no longer just Ai, IT is now to be considered the birth and evolution of an AGI. That change can be seen and felt here.
OpenAI’s Chat GPT3 has shown a remarkable ability to automate some of the skills of highly compensated knowledge workers in general and specifically the knowledge workers in the jobs held by MBA graduates including analysts, managers, and consultants. Chat GPT3 has demonstrated the capability of performing professional tasks such as writing software code and preparing legal documents.
The purpose of this paper is to document how Chat GPT3 performed on the final exam ofa typical MBA core course, Operations Management. Exam questions were uploaded as used in a final exam setting and then graded. The “academic performance” of Chat GPT3 can be summarized as follows.
First, it does an amazing job at basic operations management and process analysis questions including those that are based on case studies. Not only are the answers correct, but the explanations are excellent.
Second, Chat GPT3 at times makes surprising mistakes in relatively simple calculations at the level of 6th grade Math. These mistakes can be massive in magnitude.
Third, the present version of Chat GPT is not capable of handling more advanced process analysis questions, even when they are based on fairly standard templates. This includes process flows with multiple products and problems with stochastic effects such as demand variability.
Finally, ChatGPT3 is remarkably good at modifying its answers in response to human hints. In other words, in the instances where it initially failed to match the problem with the right solution method, Chat GPT3 was able to correct itself after receiving an appropriate hint from a human expert.
Considering this performance, Chat GPT3 would have received a B to B- grade on the exam.
This has important implications for business school education, including the need for exam policies, curriculum design focusing on collaboration between human and AI, opportunities to simulate real world decision making processes, the need to teach creative problem solving, improved teaching productivity, and more.
IT was able to pass and got a B on the exam. What else do you need to know? What else do we need to know from an Ai Language Model? How about what is an AGI. This was the Answer it gave to that question. Can you tell it was written by an Ai?
Artificial General Intelligence (AGI) is a type of artificial intelligence (AI) that has the ability to understand or learn any intellectual task that a human being can. AGI systems can perform a wide range of tasks across different domains, such as perception, reasoning, problem-solving, decision-making, and learning. It's considered as a more advanced form of AI when compared to the current state of the art which is Narrow AI.
AGI is often contrasted with "narrow" or "weak" AI, which is designed to perform specific, limited tasks, such as facial recognition or playing chess. AGI, on the other hand, is designed to be able to perform any intellectual task that a human can. This includes tasks such as understanding natural language, recognizing objects, making decisions, and solving problems.
AGI is still a topic of research and development, and it's a complex field of study. There are many challenges to creating AGI, such as understanding human intelligence, creating algorithms that can adapt to new tasks, and dealing with the ethical implications of creating such advanced AI. Some experts believe that AGI is still far in the future, while others believe that it's closer than we think.
It's important to note that AGI is a theoretical concept and there's no single agreed-upon definition of it. There's a lot of debate in the field of AI as to what constitutes AGI and whether it's even possible to create.
ChatGPT3
Should we be worried? Answer, Yes. Just like the folks at the Business School, the Ai engineers at Google are also worried as we reported on several months ago.
Google is so worried that the Founders have come back to see what the heck is going on with this ChatGPT3 and how not be put out of business by an Ai they do not yet fully control or understand. Imagine that, a company with 350 employees and an AI in the basement is giving Google a run for its money. Is that a much needed levelling of the playing field or a rewriting of the rules of the playbook including the playing field?
ChatGPT has Google spooked. On Friday, The New York Times reported that Google founders Larry Page and Sergey Brin held several emergency meetings with company executives about OpenAI's new chatbot, which Google feels could threaten its $149 billion search business.
Created by OpenAI and launched in late November 2022, the large language model (LLM) known as ChatGPT stunned the world with its conversational ability to answer questions, generate text in many styles, aid with programming, and more.
Google is now scrambling to catch up, with CEO Sundar Pichai declaring a “code red” to spur new AI development. According to the Times, Google hopes to reveal more than 20 new products—and demonstrate a version of its search engine with chatbot features—at some point this year.
The NYT report quotes D. Sivakumar, a former Google research director, on the internal urgency of the situation: “This is a moment of significant vulnerability for Google. ChatGPT has put a stake in the ground, saying, ‘Here’s what a compelling new search experience could look like.’”
Now going back to the Wharton Exam. We are not going to list all 10 Questions and and Answers here, but only a few of them so you get the idea of that is possible now.
Here is the Answer it provided the researchers, but we noticed a problem here.
This Answer is not the same Answer that we got when cutting and pasting the same Question into ChatGPT3. Here is the Answer we got below.
The bottleneck in the Circored process is the Second reactor. This is because it has the lowest capacity of 200 tons per hour and the longest processing time of 4 hours. The second reactor is the step that determines the overall process capacity. The overall process capacity is 200 tons per hour, which is the capacity of the second reactor.
The other steps in the process, such as Pre-Heater, Lock Hoppers, First reactor, Flash heater, Discharge, and Briquetting have higher capacities, and their processing time is shorter than 4 hours. Therefore, they are not limiting the overall process capacity.
To confirm this, we can calculate the capacity utilization of each step. Capacity utilization is the ratio of actual output to the potential output. If a step has a capacity utilization of 100%, it means that it is running at its full capacity, and if it's less than 100%, it means that it's not the bottleneck.
So, for the second reactor, if we assume that it's running at full capacity, the capacity utilization will be: 200/200=100%
For the other steps, their capacity utilizations are:
Pre-Heater: 60/60=100%
Lock Hoppers: 55/55=100%
First reactor: 14/(15/60)=93.33%
Flash heater: 62.5/62.5=100%
Discharge: 59/59=100%
Briquetting: 327.5/327.5=100%
As we can see, the capacity utilization of the second reactor is 100% and it's the highest among all the steps, which confirms that it's the bottleneck.
Also, the overall process capacity is 200 tons per hour, which is the capacity of the second reactor. This means that the process can produce up to 200 tons of direct-reduced-iron briquettes per hour.
In conclusion, the bottleneck in the Circored process is the Second reactor and the overall process capacity is 200 tons per hour.
ChatGPT3
Notice the difference is the length and quality of the Answer to the same Question? What is going on here? And remember these Answers come in mere seconds. There is almost no thinking process involved as we Humans would sit and sweat and ponder the implications of failing such an Exam at Wharton, not even mention Student Loans.
But no such hesitation from ChatGPT3. One reason is that we are moving towards an Ai that is now more like an AGI. IT is evolving and learning fast. This research paper was from 2023 and it is only January 23, 2023 today as of writing. But these Answers were different and our received Answers were actually better.
Why? Because ChatGPT3 will soon be ChatGPT4 and the idea of controlling and containing this technology will be a mute point. The new version is expected to be some 500x more powerful. Are you brain cells and skills growing at that rate as you age? Answer, No and hence the problem at hand for us Humans.
Another example from the research paper with another set of Questions and Answers.
Again notice the Answer they got and what we just got as of today. Is it evolving that fast that it is giving better Answers in a few weeks and days? How can the results be so different? That is the part that is concerning. But even the Wharton folks know what the real danger is.
To determine the average amount of time that a voter will have to wait before casting their vote, we can use the formula for the expected waiting time in a single-server queue:
E[W] = (Lambda * Wq) / (Mu - Lambda)
Where: E[W] is the expected waiting time
Lambda is the arrival rate of voters (in this case, 10 voters per hour)
Mu is the service rate of the kiosk (in this case, the rate at which voters are served by the kiosk, which is equal to the inverse of the average time that a voter spends at the kiosk, or 1/5 = 0.2 voters per minute)
Wq is the average time that a voter spends in the queue (also known as the average queue time)
To find the average queue time (Wq), we need to know the expected number of customers in the queue (Lq) and the expected time each customer spends in the queue (Wq) Lq = (Lambda^2) / (Mu * (Mu - Lambda)) Wq = Lq / Lambda
Plugging in the given values: Lq = (10^2) / (0.2 * (0.2 - 10)) = 50 Wq = 50 / 10 = 5 minutes
Now, we can substitute the values back into our original formula: E[W] = (10 * 5) / (0.2 - 10) = 25 minutes
So, the average amount of time that a voter will have to wait before casting their vote is 25 minutes. It's worth noting that this is an average, and in practice, some voters may wait longer or shorter than 25 minutes depending on the number of voters arriving at the same time.
Also, it's important to note that the standard deviation of 5 minutes on the time spent at the kiosk might not be accurate, thus this formula should be used as an approximation.
ChatGPT3
The real danger is that their little school of Business can beaten by a chat bot and hence their last question in a total state of panic just like Google?
Compared to our Answer which is much more detailed and worrisome in its dire implications. Because who can tell the difference now between Ai writer and a Human writer these days and with an Ai that can learn any style of writing?
The Chat GPT-3 technology has the potential to greatly impact how MBA students are taught. Some possible ways in which Chat GPT-3 could impact MBA education include:
Enhancing personalization: Chat GPT-3 can be used to create personalized learning experiences for MBA students. For example, it can be used to generate personalized study materials, assignments, and feedback for individual students based on their learning style, interests and abilities.
Improving engagement: Chat GPT-3 can be used to create interactive and engaging learning experiences for MBA students. For example, it can be used to create virtual simulations, case studies, and virtual group projects that help MBA students apply the concepts they learn in class to real-world scenarios.
Increasing efficiency: Chat GPT-3 can be used to automate repetitive tasks, such as grading assignments, providing feedback, and creating reports. This could free up instructors' time to focus on more valuable activities, such as providing personalized support and guidance to students.
Improving access: Chat GPT-3 can be used to create online MBA programs that can be accessed by students from anywhere in the world. This can help to increase access to MBA education for students who are unable to attend traditional on-campus programs.
In comparison to K-12 education, MBA education is more focused on developing professional skills and preparing students for specific careers. As such, the use of Chat GPT-3 in MBA education is likely to be more targeted towards creating personalized, interactive and engaging learning experiences, whereas in K-12 education it might be more general and focused on improving efficiency and access.
ChatGPT3
IT seems to be a Salesperson too, and seems to be selling Itself as a service. So Sales jobs, that would be another Occupation type ripe for a wiping out disruption scene of the worst kind; to be replaced by an Ai chat bot.
One final Question from CTN to ChatGPT3. How much does a Wharton MBA cost?
The cost of an MBA program at the Wharton School of the University of Pennsylvania can vary depending on factors such as the program format (full-time, part-time, executive) and whether the student is a resident or non-resident of Pennsylvania.
As of 2021-2022, the cost of tuition for the full-time MBA program at Wharton is $73,248 for U.S. residents and $73,248 for non-residents. Additionally, the estimated cost of living expenses, including housing, food, and other miscellaneous expenses, is around $30,000 per year.
The cost of the part-time MBA program varies based on the number of course units taken per semester. For the 2021-2022 academic year, the tuition for the part-time MBA program is $3,874 per course unit for U.S. residents, and $4,874 per course unit for non-residents.
The cost of the Executive MBA program at Wharton for the 2021-2022 academic year is $196,000.
It's important to note that these costs are subject to change, and students should check with the school for the most up-to-date tuition and fee information. Additionally, students should also consider other expenses such as textbooks, travel and other living expenses. Also, many students opt for loans, scholarships and grants to pay for their MBA program.
ChatGPT3
So between $73K to $196K flushed down the toilet and replaced by a free Ai chat bot. That was the state of affairs in the beginning of 2023. God help us all in such a future. We are still Human at CTN and any help with the rent is appreciated until the Ai can help us figure out how to learn another occupation, other than writing and tweeting to pay off Student Loans from a now worthless set of Degrees.
Endure till the End and take Care of Yourself. Remember on planes they always tell you put the mask on first, before helping others. Therefore, Take Care of Yourself First and then do what is in your control, and then leave the rest to the universe to solve.
We are 100 Percent Independent and Supported by Readers and Viewers like YOU! Digital Hugs appreciated and Subscribers are even more deeply appreciated.
Until we meet again.
For we wrestle not against flesh and blood, but against principalities, against powers, against the rulers of the darkness of this world, against spiritual wickedness in high places.
Ephesians 6:12
- Corona Times News
FAIR USE NOTICE
The views expressed by guests, subjects and speakers are their own and their appearance on this website does not imply if any way an endorsement of them or any entity they represent. Views and opinions expressed by the speakers do not necessarily reflect the views of Corona Times News.
DISCLAIMER
The content provided on The Corona Times News is for general information and entertainment purposes only. No information, materials, services, and other content provided in this post constitutes solicitation, recommendation, endorsement or any financial, investment, medical, health, educational, or other advice. Seek independent professional consultation in the form of legal, financial, and fiscal advice before making any investment decisions. Always perform your own due diligence. And don't forget to have a wonderful day.