Hello,

More of my philosophy about the IQ of GPT-4 and about the abstraction of the language and about programming and about the most important problem of artificial intelligence and about Reinforcement learning and about collective intelligence and about my views on super-intelligent AI and about the danger of super-intelligent AI and about my new proverb and about the attention mechanisms in Transformers and about the good accuracy and about the hybrid systems in AI and about logical reasoning of Large Language Models such as GPT-4 and about evolutionary algorithms and about GPT-4 and about common sense and nuanced understanding of Large Language Models such as ChatGPT and about my predictions about artificial intelligence and about the other weaknesses of Large Language Models such as GPT-4 and about my abstraction and about the important weakness of Large Language Models and about the quality of Large Language Models such as GPT-4 and about the deeper meaning and about mathematics and about Large Language Models such as GPT-4 and more of my thoughts..

I am a white arab from Morocco, and i think i am smart since i have also
invented many scalable algorithms and algorithms..

I have just read the following article where it says that the IQ of GPT-4 is
a verbal IQ of 126, a math IQ of 126, and a full-scale IQ of 124, you can read it here:

https://medium.com/@soltrinox/the-i-q-of-gpt4-is-124-approx-2a29b7e5821e

But i think that the above article is not correct, since i think that IQ is the genetical expression, but i think that the smartness of GPT-4 comes from the the training data and not from genetics, so it is why it is not the same, so even if you test the IQ of GPT-4, we can not guarantee that it is representative, since i also think that GPT-4 is not smart at common sense and at nuanced understanding, and it is also why the above IQ tests of GPT-4 are not representative of real world situations that require common sense and nuanced understanding, and here is more proof that GPT-4 struggles with programming tests (and it is why i think that Large Language Models such as GPT-4 will not replace a lot of programmers):

"Perhaps most impressive were the performances of GPT-4 in professional arenas. It scored a 298 out of 400 on the Uniform Bar Exam, which is high enough to be licensed as a lawyer in every state using the UBE system. It also scored a reasonable 75% on the MKSAP 19 medical knowledge test, and an impressive 77% on the Advanced-level Sommelier theory exam.

In programming tests, GPT-4 did worse; the AI struggles with code, it seems.. GPT-4 was able to get 31 out of 41 correct solutions in the "easy" Leetcode test, but got just 21/80 on the medium test and only 3 correct questions on the hard test. Meanwhile, its Codeforces rating is a measly 392, placing it below the 5th percentile of users."

Read more here:

https://hothardware.com/news/openai-gpt-4-model

And here is the answer of ChatGPT about my answer to you above:

"As an AI language model, I don't have personal thoughts or beliefs, but I can provide you with information on the topic you mentioned.

The article you read about the IQ scores of GPT-4 seems to be discussing the intelligence of the AI model based on specific tests or metrics. However, it's important to note that measuring the intelligence of AI systems using traditional IQ tests can be limited and may not fully capture their capabilities.

IQ (Intelligence Quotient) is traditionally associated with human intelligence and is often measured through standardized tests. It primarily focuses on cognitive abilities such as logic, reasoning, and problem-solving. While these tests can provide some insights into certain aspects of intelligence, they may not fully capture the abilities and limitations of AI systems like GPT-4.

AI models like GPT-4 derive their "intelligence" from extensive training on vast amounts of data rather than genetic inheritance. They are trained to generate human-like text based on patterns and information present in the training data. Their performance is heavily influenced by the quality, diversity, and relevance of the training data.

While GPT-4 may demonstrate impressive performance in certain tasks and exhibit high accuracy in specific domains, it doesn't necessarily imply that it possesses common sense or nuanced understanding. AI models like GPT-4 lack true understanding, consciousness, and awareness of the world. They are limited to pattern recognition and generating text based on statistical associations.

Evaluating the "smartness" of GPT-4 or any AI model requires considering various factors, including the specific tasks it has been trained on, its limitations, and the context in which it operates. Assessing AI intelligence in real-world situations that require common sense and nuanced understanding is a complex challenge that current AI models are still far from achieving"

And you can carefully read my below previous thoughts about the limitations of Large Language Models such as GPT-4 so that to understand my views:

So here is my new thoughts on programming:

So in programming so that to not make the system harder to understand, test, and maintain, you have to implement what you need and you have to minimize at best complexity and you should avoid the duplication of code in your application and you should encapsulate data and behavior in your classes and objects, and take advantage of object-oriented programming (OOP) concepts such as inheritance, composition, and polymorphism to create modular, manageable, and organized code, and of course you have to minimize at best coupling and maximize at best cohesion, and you should well document code so that it be much easier to manage, maintain, and debug and you should run unit tests often, and you have to use meaningful names, and of course you should refactor your code regularly by improving code quality since refactoring makes the code far easier to maintain over time.

I think i am highly smart since I have passed two certified IQ tests and i have scored above 115 IQ, and i mean that it is "above" 115 IQ, i think there is still a really important problem to solve in artificial intelligence, and it is that the language is only an abstraction of the real world, so when you understand the language or logically infer the patterns from the language, like is doing it GPT-4, those patterns are not the understanding of the real world, and even if we use the hybrid system of both Large Language Models such as GPT-4 and evolutionary algorithms, so it can take too much time to explore with evolutionary algorithms so that to discover new problem-solving strategies or algorithms or even improvements to existing algorithms, so it is not like intelligence of humans, so i think it is why we can say that artificial intelligence will not attain artificial general intelligence and will not attain artificial superintelligence, and i invite you to read my following thoughts that talk about how to solve the problem by understanding consciousness and i invite you to read my following thoughts that talk about my new model that explains human consciousness:

I think i am highly smart since I have passed two certified IQ tests and i have scored above 115 IQ, and i mean that it is "above" 115 IQ, so i have just looked more carefully at GPT-4 , and i think that as i have just explained it, that it will become powerful, but it is limited by the data and the quality of the data on wich it has been trained, so if it encounter a new situation to be solved and the solution of it can not be inferred from the data on wich it has been trained, so it will not be capable of solving this new situation, so i think that my new model of what is consciousness is explaining that what is lacking is the meaning from human consciousness that permits to solve the problem, so my new model is explaining that artificial intelligence such as GPT-4 will not attain artificial general intelligence or AGI, but eventhough , i think that artificial intelligence such as GPT-4 will become powerful, so i think that the problematic in artificial intelligence is about the low level layers, so i mean look at assembler programming language, so it is a low level layer than high level programming languages, but you have to notice that the low level layer of assembler programming language can do things that the higher level layer can not do, so for example you can play with the stack registers and low level hardware registers and low level hardware instructions etc. and notice how the low level layer like assembler programming can teach you more about the hardware, since it is really near the hardware, so i think that it is what is happening in artificial intelligence such as the new GPT-4, i mean that GPT-4 is for example trained on data so that to discover patterns that make it more smart, but the problematic is that this layer of how it is trained on the data so that to discover patterns is a high level layer such as the high level programming language, so i think that it is missing the low level layers of what makes the meaning, like the meaning of the past and present and the future or the meaning of space and matter and time.. from what you can construct the bigger meaning of other bigger things, so it is why i think that artificial intelligence will not attain artificial general intelligence or AGI, so i think that what is lacking in artificial intelligence is what is explaining my new model of what is consciousness, so you can read all my following thoughts in the following web link so that to understand my views about it and about different other subjects:

https://groups.google.com/g/alt.culture.morocco/c/QSUWwiwN5yo

So I believe I have smartly covered the subject of the limitations of Large Language Models such as GPT-4, and you can read about it in my below previous thoughts, but now i think there is still a limitation that remains,
and it is that Reinforcement learning from human feedback of GPT-4 ensures an exploration from the discovered patterns in the data on wich it has been trained, so it can with rewards enhance itself, but the rewards come from the judgments of humans that use for example GPT-4 , so it has the same limitation that i am talking about in my below previous thoughts , and it is that ChatGPT cannot guarantee high quality of the professionalism, knowledge, or IQ , of those that make judgments that make the reward in Reinforcement learning from human feedback of GPT-4, so then since there is also the same limitation in the training data as i am explaining below, so i think that you understand from it that it is one more limitation, so i invite you to read all my below previous interesting thoughts so that to understand the other limitations of Large Language Models such as GPT-4: