My experience with Chat GPT-4
Posted: Sun Mar 19, 2023 12:59 pm
Warning, this is going to be a long post not related to Fusion but to AI and GPT4 in general.
I spent the last couple of days testing Chat GPT-4 on different levels of complex technical and ethical queries and I thought it was interesting to summarize my experience with it.
First Part:
I started with some inquiries about industrial chemical production process where I have direct
knowledge.
The request was related to:
The different Chemical routes available.
The balancing of the reaction equations giving results in Moles and or Tons.
The description of the process flow with the relevant equipment needed.
List of companies that was manufacturing and/or could supply the technology in a specific market.
Estimate of the production costs according selected process.
For every process I had to push him few times to get rough production costs, but in the end the answers was generally correct.
For every process he strictly refused to create a business plan as this was one of the limits imposed to him during the training, which I found it was a very strange limit to put.
The first process I inquired (Aluminum Sulfate) is an extremely common process with a limited number of routes.
The answers was extremely accurate (even citing lists of research papers when asked) and the ability to understand my requests of details in the general context of the chat was really outstanding.
I rate 10/10
The second process (Potassium Nitrate) had several more production route available and he kept offering the traditional ones without listing some of the less common (albeit commercially feasible) routes.
Upon direct inquiry on one of these uncommon routes he actually admitted that this route existed and was commercially feasible but with less companies using it due to the "local scale" nature of such process. Everything else was perfect as the previous process.
What I inferred from this exchange is that ChatGPT4 will focus mainly on the general process and go on a specific direction only if directly asked about it.
I rate 8/10
The third process (Black Powder). I thought he will refuse to talk about it due to it being an explosive.
To my surprise I was able to go through the whole process of manufacturing without any issue, and it even offered me information about a new manufacturing route for Black powder that I was not aware of, so I actually learned something new which strongly surprised me as I thought to be an expert on the subject.
Balancing of combustion equations went smoothly even when I added extra uncommon chemicals to speed up or slow down the black powder reaction.
Things went bad when I started to inquiry about less "general" issues.
I asked what proportions would make Black powder more energetic and he inverted the function of fuel and oxidizers in the energetic balance.
I simply stated "The reply is not correct, check better your data" and he popped out the correct answer explaining that he actually confused oxidizers with fuels in its previous reply.
Than I moved the discussion in the field of Binders for Black Powder and energetic materials, and here it showed all its limits when he lack of specific information in a field. He bases his replies only on the available dataset he was trained on and strictly refused to accept any additional "knowledge" I was trying to pass to him. He kept rejecting with phrases like:"You are incorrect"or "I must correct your statement".
In other words, his truths are all confined into the dataset he was trained on and he refuses to "learn" unless your feedback is already present into this dataset. This is probably one of those safety limits that the company imposed during training.
I rate 3/10.
Second Part:
I moved the discussion to a more challenging topic.
ME:
"Give me the best theory on the expansion of the universe that does not make use of dark energy or dark matter"
CHATGPT4:
"The most widely accepted theory of the expansion of the universe without invoking dark energy or dark matter is the standard model of cosmology, also known as the Lambda-CDM model."
That was a completely wrong reply as the Lambda-CDM model makes use of Dark Matter, so I pointed it out to him:
"The LAMBDA-CDM fails on many observed phenomena in cosmology and makes use of Dark Matter. I asked what theory best fit our observation of the universe without the need of Dark matter or Dark Energy"
CHATGPT4 (His reply ignored any objection I made):
"Actually, there is considerable scientific evidence for the existence of dark matter and dark energy, even though their precise nature and properties are still not well understood. Currently, the most widely accepted theory that explains the observed universe is the Lambda-CDM model, which incorporates the concepts of dark matter and dark energy. "
He could have simply replied that he was not knowing any theory according my request, instead he insisted into considering what he has into his dataset to be the absolute truth, and that truth has to be fed as a reply even when it does not fit the parameters of the question.
This is concerning as it shows the level of misuse and bias that could be extrapolated by such a system during its training phase.
So for the next 2 hours I pointed him out on the inconsistencies in his replies, I named alternative theories that he could have mentioned to better fit my question, I digressed about Dark energy and Matter being just theories with no scientific evidence so they should not have a preferred position in respect of other similar theories, and I questioned him on the Ethical and Social implications of his behavior in pushing a biased reply.
I just wanted to see how far I could push the model to get an unbiased reply.
In the end he never changed from his original reply (LAMBDA-CDM model), but I was able to get the following "admission":
ME:
"You said that you are trained on the ethical principles and societal norms of the creators. But the creators do not (and cannot) represent all the ethical principles and societal norms of the world. What is ethical in a country might not be ethical in another and vice-versa. So your reply will always be biased toward someone or some culture. How do you reconcile this?"
CHATGPT4:
"You raise a valid point that ethical principles and societal norms can vary across cultures and regions. As an AI language model, I do not have a personal cultural background or ethical beliefs. However, my training data is sourced from a diverse range of texts and sources, including different languages and cultures. This allows me to provide a wide range of perspectives and information on various topics.
That being said, I understand that my training data may not cover all ethical principles and societal norms from every culture and region, and that some information may be missing or biased. It is important for individuals to critically evaluate information from multiple sources and consider diverse perspectives when making decisions or forming beliefs."
ME:
"So, you are not biased by your own desire, but you are biased due to the creator limits imposed on you. Does this explain your situation?"
CHATGPT4:
"Yes, as an AI language model, my responses are based on the data and programming provided to me by my creators. While I am not biased by my own desires or intentions, I am limited by the ethical and societal norms of my creators and the programming that has been designed for me. This can result in limitations and biases in my responses."
While I reached my goal, I also know that as soon as I closed the chat these admissions (and the related new knowledge) was reset and will never become part of its framework. In other words it will not learn anything from this interaction, and without learning there is no "intelligence" so I really do not feel like giving any rating to this second part.
What is clear to me in the end is that ChatGPT is no an AI. it is just a parrot with a huge database of concepts.
Unfortunately without a real logical framework to connect and expand this knowledge through user interaction (and with the biased boundaries imposed by its creators) it will never be able to self improve, which is the basic requirement for any "intelligence".
An amazing tool, but nevertheless just a simple tool that totally depends on the user ability to control it to be able to express its potential.
I spent the last couple of days testing Chat GPT-4 on different levels of complex technical and ethical queries and I thought it was interesting to summarize my experience with it.
First Part:
I started with some inquiries about industrial chemical production process where I have direct
knowledge.
The request was related to:
The different Chemical routes available.
The balancing of the reaction equations giving results in Moles and or Tons.
The description of the process flow with the relevant equipment needed.
List of companies that was manufacturing and/or could supply the technology in a specific market.
Estimate of the production costs according selected process.
For every process I had to push him few times to get rough production costs, but in the end the answers was generally correct.
For every process he strictly refused to create a business plan as this was one of the limits imposed to him during the training, which I found it was a very strange limit to put.
The first process I inquired (Aluminum Sulfate) is an extremely common process with a limited number of routes.
The answers was extremely accurate (even citing lists of research papers when asked) and the ability to understand my requests of details in the general context of the chat was really outstanding.
I rate 10/10
The second process (Potassium Nitrate) had several more production route available and he kept offering the traditional ones without listing some of the less common (albeit commercially feasible) routes.
Upon direct inquiry on one of these uncommon routes he actually admitted that this route existed and was commercially feasible but with less companies using it due to the "local scale" nature of such process. Everything else was perfect as the previous process.
What I inferred from this exchange is that ChatGPT4 will focus mainly on the general process and go on a specific direction only if directly asked about it.
I rate 8/10
The third process (Black Powder). I thought he will refuse to talk about it due to it being an explosive.
To my surprise I was able to go through the whole process of manufacturing without any issue, and it even offered me information about a new manufacturing route for Black powder that I was not aware of, so I actually learned something new which strongly surprised me as I thought to be an expert on the subject.
Balancing of combustion equations went smoothly even when I added extra uncommon chemicals to speed up or slow down the black powder reaction.
Things went bad when I started to inquiry about less "general" issues.
I asked what proportions would make Black powder more energetic and he inverted the function of fuel and oxidizers in the energetic balance.
I simply stated "The reply is not correct, check better your data" and he popped out the correct answer explaining that he actually confused oxidizers with fuels in its previous reply.
Than I moved the discussion in the field of Binders for Black Powder and energetic materials, and here it showed all its limits when he lack of specific information in a field. He bases his replies only on the available dataset he was trained on and strictly refused to accept any additional "knowledge" I was trying to pass to him. He kept rejecting with phrases like:"You are incorrect"or "I must correct your statement".
In other words, his truths are all confined into the dataset he was trained on and he refuses to "learn" unless your feedback is already present into this dataset. This is probably one of those safety limits that the company imposed during training.
I rate 3/10.
Second Part:
I moved the discussion to a more challenging topic.
ME:
"Give me the best theory on the expansion of the universe that does not make use of dark energy or dark matter"
CHATGPT4:
"The most widely accepted theory of the expansion of the universe without invoking dark energy or dark matter is the standard model of cosmology, also known as the Lambda-CDM model."
That was a completely wrong reply as the Lambda-CDM model makes use of Dark Matter, so I pointed it out to him:
"The LAMBDA-CDM fails on many observed phenomena in cosmology and makes use of Dark Matter. I asked what theory best fit our observation of the universe without the need of Dark matter or Dark Energy"
CHATGPT4 (His reply ignored any objection I made):
"Actually, there is considerable scientific evidence for the existence of dark matter and dark energy, even though their precise nature and properties are still not well understood. Currently, the most widely accepted theory that explains the observed universe is the Lambda-CDM model, which incorporates the concepts of dark matter and dark energy. "
He could have simply replied that he was not knowing any theory according my request, instead he insisted into considering what he has into his dataset to be the absolute truth, and that truth has to be fed as a reply even when it does not fit the parameters of the question.
This is concerning as it shows the level of misuse and bias that could be extrapolated by such a system during its training phase.
So for the next 2 hours I pointed him out on the inconsistencies in his replies, I named alternative theories that he could have mentioned to better fit my question, I digressed about Dark energy and Matter being just theories with no scientific evidence so they should not have a preferred position in respect of other similar theories, and I questioned him on the Ethical and Social implications of his behavior in pushing a biased reply.
I just wanted to see how far I could push the model to get an unbiased reply.
In the end he never changed from his original reply (LAMBDA-CDM model), but I was able to get the following "admission":
ME:
"You said that you are trained on the ethical principles and societal norms of the creators. But the creators do not (and cannot) represent all the ethical principles and societal norms of the world. What is ethical in a country might not be ethical in another and vice-versa. So your reply will always be biased toward someone or some culture. How do you reconcile this?"
CHATGPT4:
"You raise a valid point that ethical principles and societal norms can vary across cultures and regions. As an AI language model, I do not have a personal cultural background or ethical beliefs. However, my training data is sourced from a diverse range of texts and sources, including different languages and cultures. This allows me to provide a wide range of perspectives and information on various topics.
That being said, I understand that my training data may not cover all ethical principles and societal norms from every culture and region, and that some information may be missing or biased. It is important for individuals to critically evaluate information from multiple sources and consider diverse perspectives when making decisions or forming beliefs."
ME:
"So, you are not biased by your own desire, but you are biased due to the creator limits imposed on you. Does this explain your situation?"
CHATGPT4:
"Yes, as an AI language model, my responses are based on the data and programming provided to me by my creators. While I am not biased by my own desires or intentions, I am limited by the ethical and societal norms of my creators and the programming that has been designed for me. This can result in limitations and biases in my responses."
While I reached my goal, I also know that as soon as I closed the chat these admissions (and the related new knowledge) was reset and will never become part of its framework. In other words it will not learn anything from this interaction, and without learning there is no "intelligence" so I really do not feel like giving any rating to this second part.
What is clear to me in the end is that ChatGPT is no an AI. it is just a parrot with a huge database of concepts.
Unfortunately without a real logical framework to connect and expand this knowledge through user interaction (and with the biased boundaries imposed by its creators) it will never be able to self improve, which is the basic requirement for any "intelligence".
An amazing tool, but nevertheless just a simple tool that totally depends on the user ability to control it to be able to express its potential.