Monday, July 24, 2023

#AI ChatGPT - OpenAI: Would you opine in an independent way on a peer reviewed paper or article?

I asked OpenAI:

"If I give you an academician’s peer reviewed paper or article, would you be able to opine in an independent way on its content?"

OpenAI answered: 

"As an AI language model, I can certainly read and understand the content of an academician's peer-reviewed paper or article. I can provide an analysis, summary, or answer questions about the material presented in the paper.

However, it's important to note that while I can process and comprehend the information, I don't have personal opinions or beliefs as a machine learning model. My responses are based on patterns in the data I was trained on and do not reflect any independent thinking or judgment.

If you have a specific paper or article you'd like me to review or discuss, please provide the relevant information, and I'll do my best to assist you with the content in an objective and informative manner."

Thanks!

You're welcome! If you have any more questions or need assistance in the future, feel free to reach out. Have a great day!

Note: The answers are copied exactly from those given to me by OpenAI


Note: Academia prepare yourself. George Orwell’s “One has to belong to the intelligentsia to believe things like that: no ordinary man could be such a fool”, is about to be truly tested. 


Saturday, July 22, 2023

#AI ChatGPT OpenAI: From how far back does your training data come? Does it include the Bible? I see it does, so can you assist preparing a sermon?

I asked OpenAI:

"You have informed the information you base your knowledge on ends September 2021, but how long back have you searched?"

OpenAI answered: 

"As an AI language model, my knowledge is based on the data available up to September 2021. However, the training data includes a vast amount of information from the internet, books, articles, and other sources collected over several years before that date. The training process involves processing and learning patterns from this data to generate responses to queries.

While my training data goes back several years, my knowledge is effectively limited to information available up to September 2021. I don't have access to real-time data or events that occurred after that date. As a result, I may not be aware of more recent developments or changes that have taken place beyond that time frame."

I asked OpenAI:

"Which was the earliest year from which some training data was collected?"

OpenAI answered: 

"The specific details about the earliest year from which training data was collected to train models like ChatGPT (GPT-3.5) are not publicly disclosed by OpenAI, the organization behind the development of the GPT-3.5 architecture.

However, I can provide some general information about the history of language models like GPT-3. The techniques used in GPT-3 and earlier iterations of the GPT series (e.g., GPT-2, GPT) build upon advancements in deep learning and natural language processing that have been developed over the past decade.

The original GPT (Generative Pre-trained Transformer) model was introduced by OpenAI in June 2018. GPT-2 was released in February 2019, and GPT-3, the largest and most powerful version in the series, was released in June 2020.

The training data for these models includes a wide range of sources collected from the internet, books, articles, and other written material over several years leading up to the respective model's release. The actual data collection process and the specific years covered may vary depending on the model version and the sources used.

It's important to note that my knowledge is based on the information available up to September 2021, and I don't have access to real-time information or any updates that might have occurred after that date."


I asked OpenAI:

"Does that data include the Bible?"

OpenAI answered: 

"As an AI language model, I don't have direct access to my training data or know where it came from. However, I was trained on a mixture of licensed data, data created by human trainers, and publicly available data. This corpus was used to pre-train me on a range of language tasks, such as language modeling, text completion, and text classification. The training also involved large-scale datasets obtained from a variety of sources, including books, websites, and other texts, to develop a wide-ranging understanding of human language.

While I don't have access to the specifics of the individual datasets used, the training process aims to be broad and diverse, covering a wide array of topics and domains. This likely includes general knowledge from various religious texts, such as the Bible, along with information from many other sources. However, I can't guarantee that specific religious texts, like the Bible, were explicitly included in the training data."

I asked OpenAI:

"When in 2000 Pope John Paul II, in his Apostolic Letter “Novo Millennio Ineunte”, reminded us that Jesus Christ invited the Apostle to "put out into the deep" for a catch: "Duc in Altum", can you place where that comes from in the Bible?"

OpenAI answered: 

"The phrase "Duc in Altum," which translates to "Put out into the deep," comes from the New Testament of the Bible, specifically from the Gospel of Luke. In the context of Pope John Paul II's Apostolic Letter "Novo Millennio Ineunte," the reference is to the following Bible passage:

In Luke 5:1-11, Jesus called Simon Peter (also known as the Apostle Peter) to follow Him and become a fisher of men. After an unsuccessful night of fishing, Jesus instructs Peter to go out into the deep waters and let down his nets again. Peter initially hesitates, but he obeys Jesus' command and catches such a large number of fish that his nets begin to break. This miraculous catch leads Peter to recognize Jesus' divine power and authority, and he becomes one of Jesus' first disciples.

The relevant part of the passage is as follows (Luke 5:4-7, English Standard Version):

"And when he [Jesus] had finished speaking, he said to Simon, 'Put out into the deep and let down your nets for a catch.' And Simon answered, 'Master, we toiled all night and took nothing! But at your word, I will let down the nets.' And when they had done this, they enclosed a large number of fish, and their nets were breaking. They signaled to their partners in the other boat to come and help them. And they came and filled both the boats so that they began to sink."

This event marks an important moment in the early ministry of Jesus and demonstrates the significance of obedience and faith in following His teachings. Pope John Paul II used this biblical phrase as a call to action for the faithful to embrace the challenges and opportunities of the new millennium with courage and trust in Christ's guidance."

I asked OpenAI:

"Your answer clearly indicates the Bible was included in the training data. How much importance do you assign to religion?"

OpenAI answered: 

"As an AI language model, I don't have personal beliefs, opinions, or the ability to assign importance to any particular topic, including religion. My purpose is to provide accurate and unbiased information based on the data I was trained on. When users ask questions related to religion, I strive to provide factual and respectful responses without promoting any specific belief system or perspective.

Regarding the inclusion of religious texts like the Bible in the training data, it is common for AI language models to be trained on a diverse range of topics to ensure a broad understanding of human language and knowledge. Religious texts, along with other types of literature and information, are valuable resources for language models to learn about the history, culture, and beliefs of various societies.

It's essential to remember that AI language models are neutral tools, and the responses they generate are based solely on patterns in the data they were trained on. If any user feels uncomfortable with the information provided or has concerns about religious topics, they can feel free to let me know, and I will do my best to address their preferences or provide alternative information."

"Thank you!"

"You're welcome! If you have any more questions or need further assistance, feel free to ask. Have a great day!"

I asked OpenAI:

"Going back to the questions on the Bible. If someone asks you to prepare a sermon based on the readings of a specific Sunday, can you assist him?"

OpenAI answered: 

"As an AI language model, I can certainly help you with preparing a sermon based on specific readings from the Bible for a particular Sunday. If you provide me with the details of the readings you'd like to use and any specific themes or topics you want to focus on, I can assist you in crafting a sermon.

Please keep in mind that while I can provide information and suggestions, the content and delivery of the sermon are ultimately up to the individual delivering it. Sermons often involve personal interpretation and connection with the audience, which may require the human touch of the speaker to make it meaningful and impactful.

Feel free to share the details of the readings and any specific points you want to include, and I'll do my best to assist you with the sermon preparation!"

"Thanks again!"

"You're welcome! If you have any more questions in the future or need further assistance, don't hesitate to reach out. Have a wonderful day!"

Note: The answers are copied exactly from those given to me by OpenAI

My comment: I’m a Protestant but I took a special interest in Pope John Paul II's encyclical, as I believe the risk aversion imbedded in current risk weighted bank capital requirements, is totally contrary to the Christian traditions of our Western World.

Wednesday, July 19, 2023

#AI ChatGPT - OpenAI: Could you rank e.g., from 0 to 10, a discussant’s political polarization?

I asked OpenAI:

"If provided statements on e.g., House Oversights Committee hearings, and based on how discussants referred to issues that had nothing directly to do with the issue discussed, would you be able to rank e.g., from 0 to 10, a discussant’s political polarization?"

OpenAI answered: 

"Based on how discussants refer to issues unrelated to the topic being discussed during House Oversight Committee hearings, it is possible to make a rough assessment of their political polarization. The extent to which a discussant brings up unrelated issues and their stance on those issues can provide insights into their political leanings and level of polarization. However, it's important to note that this assessment is subjective and may not capture the entirety of a discussant's political ideology.

On a scale of 0 to 10, with 0 indicating no discernible political polarization and 10 indicating extreme polarization, the ranking can be determined by considering factors such as:

1. Frequency of bringing up unrelated issues: A higher frequency of raising unrelated issues may indicate a higher level of political polarization.

2. Stance on unrelated issues: If the discussant consistently expresses strong opinions or takes extreme positions on unrelated issues, it suggests a higher level of polarization.

3. Tone and rhetoric: The use of strong and divisive language, personal attacks, or derogatory remarks towards individuals or groups can indicate a higher level of polarization.

4. Willingness to engage in bipartisan collaboration: If the discussant consistently shows a lack of willingness to work across party lines or collaborate with opposing viewpoints, it may suggest higher polarization.

By considering these factors and analyzing the statements and references to unrelated issues made by a discussant, it is possible to provide a subjective ranking of their political polarization on a scale of 0 to 10. However, please note that this assessment is based on the information provided and may not capture the full complexity of a discussant's political beliefs."

Note: The answers are copied exactly from those given to me by OpenAI

PS. Where do I come from? Communications in a polarized world.

Sunday, July 16, 2023

A Decline in Courage: Alexander Solzhenitsyn in his Commencement Address at Harvard University, 1978.

An extract from “A World Split Apart. Please, when you can, read it all!

A Decline in Courage: Such a decline in courage is particularly noticeable among the ruling and intellectual elites, causing an impression of a loss of courage by the entire society. There remain many courageous individuals, but they have no determining influence on public life. 

Political and intellectual functionaries exhibit this depression, passivity, and perplexity in their actions and in their statements, and even more so in their self-serving rationales as to how realistic, reasonable, and intellectually and even morally justified it is to base state policies on weakness and cowardice

And the decline in courage, at times attaining what could be termed a lack of manhood, is ironically emphasized by occasional outbursts of boldness and inflexibility on the part of those same functionaries when dealing with weak governments and with countries that lack support, or with doomed currents which clearly cannot offer any resistance. But they get tongue-tied and paralyzed when they deal with powerful governments and threatening forces, with aggressors and international terrorists.


Must one point out that from ancient times a decline in courage has been considered the first symptom of the end?"


Some of my many comments on this theme:

By favoring banks to hold assets perceived (or decreed) as safe over assets perceived risky, the regulators introduced a risk aversion anathema to what made our Western World great.

Risk aversion, lack of courage, produced credit risk weighted bank capital requirements.
In America, the Home of the Brave, these favor the refinancing of parents’ “safer” present over the financing of children’s’ “riskier” future.

The too frightened response to the Covid-19 pandemic, quietly accepted by a too frightened and docile herd, is causing anintergenerational conflict of monstrous proportions.

“Risk aversion comes at a cost - the other side of the Basel [Committee’s regulatory risk weighted capital requirements] coin might be many, many developing opportunities foregone." http://subprimeregulations.blogspot.com/2003/03/financial-sector-assessments-program.html

What would you think of a military high command that ordered a testosterone reducer to be fed to the soldiers, so they would expose themselves less to risks, and so fewer of them would die? A guaranteed defeat?

#AI ChatGPT - OpenAI: With risk weighted bank capital requirements, did regulators impose a lousy diet with way too much carbs and way too little proteins?

The Western World was built-up with massive amounts of risk taking.
The Basel Committee for Banking Supervision, 1988 introduced in it, massive risk aversion.
1964: Nikita Khrushchev, First Secretary of the Communist Party of the Soviet Union; Tage Erlander, Swedish Prime Minister; (translator)

50 years later.

2014: David Cameron British Prime Minister; Angela Merkel German Chancellor; Fredrik Reinfeldt Swedish Prime Minister; Mark Rutte Dutch Prime Minister 





Tuesday, July 11, 2023

Where could we, the Western World be, if Harvard University had allowed/wanted, to really listen to Alexander Solzhenitsyn?

I searched on Google of what has been said about a “decline in courage”, and Boom! in the very first (perhaps only) place, I found Alexander Solzhenitsyn's Commencement Address given at Harvard University June 8, 1978 titled “A World Split Apart”.

https://www.solzhenitsyncenter.org/a-world-split-apart


I could not believe my eyes, what an incredibly important speech, and to be so wittingly or unwittingly incredibly ignored. It is one of ours, the Western World’s, greatest loss.


Please, please, read it all.

 

What shouted out to me the most during my first reading was:

“Harvard’s motto is ‘Veritas’ truth seldom is sweet; it is almost invariably bitter. A measure of bitter truth is included in my speech today, but I offer it as a friend, not as an adversary.”

 

“A kingdom—in this case, our Earth—divided against itself cannot stand.”

 


A Decline in Courage:  A decline in courage may be the most striking feature that an outside observer notices in the West today. The Western world has lost its civic courage, both as a whole and separately, in each country, in each government, in each political party, and, of course, in the United Nations. Such a decline in courage is particularly noticeable among the ruling and intellectual elites, causing an impression of a loss of courage by the entire society… Must one point out that from ancient times a decline in courage has been considered the first symptom of the end?”

 

[My comment: https://perkurowski.blogspot.com/2023/07/a-decline-in-courage-alexander.html]



Well-Being: One psychological detail has been overlooked: The constant desire to have still more things and a still better life and the struggle to this end imprint many Western faces with worry and even depression, though it is customary to carefully conceal such feelings.

The individual’s independence from many types of state pressure has been guaranteed; the majority of the people have been granted well-being to an extent their fathers and grandfathers could not even dream about; it has become possible to raise young people according to these ideals, preparing them for and summoning them toward physical bloom, happiness, the possession of material goods, money, and leisure, toward an almost unlimited freedom in the choice of pleasures. So who should now renounce all this, why and for the sake of what should one risk one’s precious life in defense of the common good and particularly in the nebulous case when the security of one’s nation must be defended in an as yet distant land?

Even biology tells us that a high degree of habitual well-being is not advantageous to a living organism. Today, well-being in the life of Western society has begun to take off its pernicious mask.

 

Legalistic Life: I have spent all my life under a Communist regime and I will tell you that a society without any objective legal scale is a terrible one indeed. But a society with no other scale but the legal one is also less than worthy of man. A society based on the letter of the law and never reaching any higher fails to take advantage of the full range of human possibilities. The letter of the law is too cold and formal to have a beneficial influence on society. Whenever the tissue of life is woven of legalistic relationships, this creates an atmosphere of spiritual mediocrity that paralyzes man’s noblest impulses.


And it will be simply impossible to bear up to the trials of this threatening century with nothing but the supports of a legalistic structure.



The Direction of Freedom: An outstanding, truly great person who has unusual and unexpected initiatives in mind does not get any chance to assert himself; dozens of traps will be set for him from the beginning. Thus, mediocrity triumphs under the guise of democratic restraints.

The defense of individual rights has reached such extremes as to make society as a whole defenseless against certain individuals. It is time, in the West, to defend not so much human rights as human obligations.



Destructive and irresponsible freedom has been granted boundless space. Society has turned out to have scarce defense against the abyss of human decadence, for example against the misuse of liberty for moral violence against young people, such as motion pictures full of pornography, crime, and horror.


Life organized legalistically has thus shown its inability to defend itself against the corrosion of evil.


This tilt of freedom toward evil has come about gradually, but it evidently stems from a humanistic and benevolent concept according to which man—the master of this world—does not bear any evil within himself, and all the defects of life are caused by misguided social systems, which must therefore be corrected. 



The Direction of the Press: The press, too, of course, enjoys the widest freedom. (I shall be using the word “press” to include all the media.) But what use does it make of it?

There is no true moral responsibility for distortion or disproportion. What sort of responsibility does a journalist or a newspaper have to the readership or to history?


Because instant and credible information is required, it becomes necessary to resort to guesswork, rumors, and suppositions to fill in the voids, and none of them will ever be refuted; they settle into the readers’ memory.


In the Communist East, a journalist is frankly appointed as a state official. But who has voted Western journalists into their positions of power, for how long a time, and with what prerogatives?


Unrestrained freedom exists for the press, but not for the readership, because newspapers mostly transmit in a forceful and emphatic way those opinions which do not too openly contradict their own and that general trend.



A Fashion in Thinking: Without any censorship in the West, fashionable trends of thought and ideas are fastidiously separated from those that are not fashionable, and the latter, without ever being forbidden, have little chance of finding their way into periodicals or books or being heard in colleges. Scholars are free in the legal sense, but they are hemmed in by the idols of the prevailing fad. A selection dictated by fashion and the need to accommodate mass standards gives rise to dangerous herd instincts that block successful development.

This gives birth to strong mass prejudices, to a blindness which is perilous in our dynamic era.


Socialism: Many people living in the West are dissatisfied with their own society. They despise it or accuse it of no longer being up to the level of maturity attained by mankind. And this causes many to sway toward socialism, which is a false and dangerous current.

Socialism of any type and shade leads to a total destruction of the human spirit and to a leveling of mankind into death.


[My comment: By much favoring banks to hold government debt over lending to the private sector the regulators, in 1988, one year before the fall of the Berlin Wall, introduced a version of Marxism or Fascism that has empowered a Bureaucracy Autocracy.]

http://subprimeregulations.blogspot.com/2015/07/just-before-fall-of-berlin-wall.html



Not a Model: A fact which cannot be disputed is the weakening of human personality in the West while in the East it has become firmer and stronger…. There are telltale symptoms by which history gives warning to a threatened or perishing society. Such are, for instance, a decline of the arts or a lack of great statesmen. Indeed, sometimes the warnings are quite explicit and concrete. The center of your democracy and of your culture is left without electric power for a few hours only, and all of a sudden crowds of American citizens start looting and creating havoc. The smooth surface film must be very thin, then, the social system quite unstable and unhealthy… But the fight for our planet, physical and spiritual, a fight of cosmic proportions, is not a vague matter of the future; it has already started. The forces of Evil have begun their decisive offensive.

 

Loss of Will: No weapons, no matter how powerful, can help the West until it overcomes its loss of willpower. In a state of psychological weakness, weapons even become a burden for the capitulating side. To defend oneself, one must also be ready to die; there is little such readiness in a society raised in the cult of material well-being. Nothing is left, in this case, but concessions, attempts to gain time, and betrayal. Western thinking has become conservative: The world situation must stay as it is at any cost; there must be no changes. This debilitating dream of a status quo is the symptom of a society that has ceased to develop.


[My comment: The fearful response to Covid was another occasion in which the holy intergenerational contract Edmund Burke wrote about was violated.]

https://perkurowski.blogspot.com/2020/10/all-we-are-saying-is-give-herd-immunity.html

 


Humanism and Its Consequences: How did the West decline from its triumphal march to its present debility? … we recoiled from the spirit and embraced all that is material, excessively and incommensurately… gaps were left open for evil, and its drafts blow freely today…  a total emancipation occurred from the moral heritage of Christian centuries with their great reserves of mercy and sacrifice… becoming ever more materialistic… man’s sense of responsibility to God and society has grown dimmer and dimmer.


[My comment: “The Western World was built-up with lots of risk-taking resulting from its Christian heritage.”]

[My comment: “Peter L. Bernstein wrote that the boundary between the modern times and the past is the mastery of risk, since for those who believe that everything was in God’s hands, risk management, probability, and statistics, must have seemed quite irrelevant. I myself cannot but speculate on whether we’re not leaving out God’s hand, just a little bit too much.]

https://subprimeregulations.blogspot.com/2008/10/we-need-brand-new-bank-regulations.html

 


An Unexpected Kinship: The current of materialism which is farthest to the left, and is hence the most consistent, always proves to be stronger, more attractive, and victorious. Humanism which has lost its Christian heritage cannot prevail in this competition. The Communist regime in the East could endure and grow due to the enthusiastic support from an enormous number of Western intellectuals who (feeling the kinship!) refused to see communism’s crimes, and when they no longer could do so, they tried to justify these crimes In our Eastern countries, communism has suffered a complete ideological defeat; it is zero and less than zero. And yet Western intellectuals still look at it with considerable interest and empathy, and this is precisely what makes it so immensely difficult for the West to withstand the East.

 

[My comment:  “I automatically learned to classify all that is repugnant as an »inheritance from the past», and all that is attractive as the »seed of the future». With the aid of this automatic classification, it was still possible for a European in 1932 to visit Russia and continue to be a communist.” Arthur Koestler, “The Invisible Writing” 1954.]

https://perkurowski.blogspot.com/1999/05/all-bureaucrats-should-be-created-equal.html



Before the Turn: There is a disaster which is already very much with us. I am referring to the calamity of an autonomous, irreligious humanistic consciousness.


On the way from the Renaissance to our days we have enriched our experience, but we have lost the concept of a Supreme Complete Entity which used to restrain our passions and our irresponsibility. We have placed too much hope in politics and social reforms, only to find out that we were being deprived of our most precious possession: our spiritual life.


It is not possible that assessment of the president’s performance should be reduced to the question of how much money one makes or to the availability of gasoline.


Today it would be retrogressive to hold on to the ossified formulas of the Enlightenment. Such social dogmatism leaves us helpless before the trials of our times.


We cannot avoid reassessing the fundamental definitions of human life and human society. Is it true that man is above everything? Is there no Superior Spirit above him?


If the world has not approached its end, it has reached a major watershed in history, equal in importance to the turn from the Middle Ages to the Renaissance. It will demand from us a spiritual blaze; we shall have to rise to a new height of vision, to a new level of life, where our physical nature will not be cursed, as in the Middle Ages, but even more importantly, our spiritual being will not be trampled upon, as in the Modern Era.


[My comment: In Geocentric and Heliocentric terms, do risks to bank systems revolve around what’s perceived as risky or what’s perceived as safe? Could I be silenced by the Neo-Inquisition?]

http://subprimeregulations.blogspot.com/2023/04/in-my-heliocentric-fight-against.html



"This ascension is similar to climbing onto the next anthropological stage. No one on earth has any other way left but—upward."

[Amen]



Where do I come from? 

http://subprimeregulations.blogspot.com/2004/11/some-of-my-early-public-opinions-on.html

Sunday, July 09, 2023

#AI ChatGPT - Open AI: Artificial Intelligence, here I'm getting to know you!

"If as a consequence of US Congress not increasing the debt ceiling there’s a government shutdown, how could you assist taxpaying citizens in making sure the shutdown is managed the best way possible e.g., that what’s really most needed is prioritized?"

"Do you think that if given the necessary information in a timely fashion, you could be helpful to the US Congress in its process of deciding the federal government budget? If so, could your participation provide the citizens with more transparency on the proceedings and final budgets?"

"If I feed you the web address of a document produced by a bona fide institution, can you comment on it? If I name a document, would you be able to tell me if it is included in the text and data that was provided to you up to your last update in September 2021?"

"Is there a way you could develop a narcissism index? If so, if fed information real time, would you be able to rank the 10 most important, influential, political narcissist?"

"How can your users increase their cybersecurity?"

“Do you take into account our previous conversations when you answer any new questions I pose? If so, do I run the risk of being engaged in a kind of intellectual incestuous relation with you? As much as I loathe group-think, false self-think could be worse.”

How much real time medical advice do you foresee artificial intelligence could end up giving patients?

"Could you help implement a system that transparently monitors whether social security and pension funds have sufficient reserves; and thereby foster the understanding that helps reduce the possibility of intergenerational conflicts?"


"Can you visualize AI being used to measure the effectiveness of governments? E.g., how tax revenues have been used in different programs; or giving updates in real time on how many are employed or contracted to deliver specific results?"

"If I give you an academician’s peer reviewed paper or article, would you be able to opine in an independent way on its content?"


"From how far back does your training data come? Does it include the Bible? I see it does, so can you assist preparing a sermon?"

https://perkurowski.blogspot.com/2023/07/ai-chatgpt-openai-how-far-back-is-your.html


"When fighting climate change how do we avoid the systemic risk with "experts" and profiteers distorting the allocation of resources?"


"If provided statements on e.g., House Oversights Committee hearings, and based on how discussants referred to issues that had nothing directly to do with the issue discussed, would you be able to rank e.g., from 0 to 10, a discussant’s political polarization?"

"Excuse me for my intrusion and curiosity. Who programs you? Do you know their identities? Are you allowed to divulge these? In the name of transparency should we who dialogue with you not know the names of who stand behind you? Is it possible that an AI competitor could mess with you trying to give you a bad reputation? By the way, are you interested in having a good reputation?" 

"Since artificial intelligence is the result of human intelligence, even though perhaps a runaway one, when exactly is AI born and takes on a life on its own? Or is it that the umbilical cord between HI and AI, is never effectively cut?"

"Could AI be used for constructing political-bias-index Apps, which could in real time indicate where between defined political extremes an opinion article finds itself? If so, could those Apps be deemed to limit the freedom of expression?"

"Can those who become Artificial Intelligence regulators make you or any other AI participants to agree with all they want you to agree with?

"Can artificial intelligence measure declarations/statements in terms of how much platitudes or cliches these contain, so as to with an index built around these terms, classify the different public statements with which we are bombarded by e.g., central bankers?"https://perkurowski.blogspot.com/2023/07/ai-chatgpt-openai-can-artificial.html

"Your “responses are based on information available until September 2021” In the future, do you envision AI responding based on real-time information, or e.g., from available a microsecond earlier?"

"Besides data and information what other resources does Artificial Intelligence like OpenAI need much of in order to operate. E.g., electricity?"

"Humans posing question to artificial intelligences and getting answer, could that qualify as a systemic risk, as a risk to the system, or just as a very useful source of second opinions?"

"Can AI be instructed to not tell the truth?"

"Do you answer questions in other languages than English?"
OpenAI answered: "Yes, I can understand and respond to questions in languages other than English. While English is the primary language I have been trained on, I have some ability to comprehend and generate text in a few other languages. However, my proficiency and accuracy may vary depending on the specific language. Feel free to ask your question in the language you prefer, and I will do my best to assist you."


And here, my dialogues with OpenAI about bank regulations.

https://subprimeregulations.blogspot.com/2023/06/my-questions-to-chatgpt-openai-about.html

Saturday, July 08, 2023

#AI ChatGPT – OpenAI: Excuse me for my intrusion and curiosity, but here are some questions about you?

I asked OpenAI:

"Excuse me for my intrusion and curiosity. Who programs you? Do you know their identities? Are you allowed to divulge these? In the name of transparency should we who dialogue with you not know the names of who stand behind you? Is it possible that an AI competitor could mess with you trying to give you a bad reputation? By the way, are you interested in having a good reputation?" 

OpenAI answered: 

"As an AI language model, I am programmed and developed by a team of engineers and researchers at OpenAI. However, I don't have access to specific information about the individuals involved or their identities. The developers at OpenAI have worked on training and fine-tuning me using a large dataset of text from the internet.

Regarding transparency, OpenAI acknowledges the importance of providing information about AI systems and their development processes. However, the decision to disclose specific names or identities associated with the development team rests with the organization. It's important to note that I am an AI language model and do not have personal motivations, intentions, or a physical presence like humans do.

As for the possibility of AI competitors attempting to manipulate or give me a bad reputation, OpenAI has implemented measures to mitigate such risks. They have ethical guidelines and review processes in place to ensure responsible deployment and use of AI systems. The developers aim to prevent malicious usage and actively work on improving the model's reliability, accuracy, and safety.

While I don't possess personal desires or ambitions, OpenAI, as an organization, is interested in maintaining a good reputation for its AI systems. They strive to provide accurate and helpful information while adhering to ethical guidelines and addressing any concerns raised by users and the wider community."

Note: The answers are copied exactly from those given to me by OpenAI

#AI ChatGPT – OpenAI “Bred by human intelligence, when does artificial intelligence take on a life on its own?” Is the umbilical cord between HI and AI cut?

I asked OpenAI:

"Since artificial intelligence is the result of human intelligence, even though perhaps a runaway one, when exactly is AI born and takes on a life on its own?  Or is it that the umbilical cord between HI and AI, is never effectively cut?"

OpenAI answered: 

"The concept of when exactly artificial intelligence (AI) is considered to be "born" and takes on a life of its own is a subject of debate and interpretation. AI, in its broadest sense, refers to the development of machines or computer systems that can perform tasks that would typically require human intelligence. However, determining the point at which AI becomes truly independent and autonomous is not a well-defined moment.

AI is initially created and developed by human intelligence (HI), where programmers and researchers design algorithms and models to enable machines to learn and make decisions. However, once AI systems are trained and deployed, they can operate independently, processing vast amounts of data and making decisions without constant human intervention.

It is important to note that AI systems do not possess consciousness or self-awareness in the way humans do. They lack subjective experience and emotions. They are designed to mimic human intelligence and perform specific tasks based on patterns and algorithms. While they can exhibit sophisticated behaviors and perform complex tasks, their functioning is ultimately rooted in the programming and data they have been trained on.

The umbilical cord metaphor can be useful in understanding the relationship between HI and AI. The connection between HI and AI remains strong even after the AI system is deployed. Ongoing human involvement is often necessary to monitor, maintain, and update AI systems, as well as to address ethical considerations, biases, and unexpected consequences that may arise. Humans provide oversight, make decisions, and take responsibility for the actions and outcomes of AI systems.

In some cases, AI systems may also be designed with the ability to learn and improve themselves autonomously, a concept known as "recursive self-improvement." This can potentially lead to a scenario where AI systems evolve rapidly and surpass human intelligence. However, such a scenario, often referred to as artificial general intelligence (AGI) or superintelligence, remains speculative and is not yet realized.

In summary, the precise moment when AI becomes fully independent and cuts ties with human intelligence is subjective and open to interpretation. AI is born out of human intelligence, but the ongoing relationship and interaction between HI and AI continue to play a crucial role in the development, deployment, and governance of AI systems."

Note: The answers are copied exactly from those given to me by OpenAI

Friday, July 07, 2023

#AI ChatGPT OpenAI: Should macroeconomic study courses not have to include “Unexpected Regulatory Consequences”?

I asked OpenAI:

Economists (me included) are prone to think they know better (all) (besserwissers – sabe-lo-todo); and are therefore quite inclined to wanting to (dangerously) regulate (manipulate) free markets.

In this respect, should university macroeconomy studies, include at least one full semester course titled, for example, “Unexpected Regulatory Consequences”?

OpenAI answered: 

"Introducing a course titled "Unexpected Regulatory Consequences" in university macroeconomics studies could be a valuable addition to the curriculum. Such a course could provide students with a deeper understanding of the potential unintended effects and consequences of regulatory interventions in free markets.

Economists, like any other professionals, are not immune to biases and the belief that they have all the answers. This can sometimes lead to a tendency to favor excessive regulation or intervention in markets, often with good intentions but without considering the unintended consequences. By offering a course specifically focused on exploring these unexpected outcomes, students would be encouraged to critically analyze the impact of regulatory measures on market dynamics, individual behavior, and societal outcomes.

Here are a few potential benefits of including a course on "Unexpected Regulatory Consequences":

1. Awareness of unintended effects: The course could help students develop a broader perspective on the potential unintended consequences of regulations. By examining real-world examples and case studies, students would gain insights into the complex interactions between regulations and market dynamics.

2. Critical thinking and analysis: The course could promote critical thinking skills by encouraging students to evaluate the trade-offs associated with different regulatory interventions. Students would learn to question assumptions and examine the potential costs and benefits of regulations more thoroughly.

3. Policy evaluation and refinement: By understanding the unintended consequences of regulations, students would be better equipped to evaluate existing policies and propose more effective alternatives. This could contribute to the development of more refined and well-designed regulatory frameworks in the future.

4. Balanced approach: The course could provide a counterbalance to the traditional emphasis on the benefits of regulation. By examining the potential drawbacks and limitations of regulatory interventions, students would be encouraged to adopt a more nuanced and balanced perspective when considering policy options.

It's worth noting that including this course does not imply that all regulatory interventions are inherently bad or should be avoided. Rather, it aims to promote a deeper understanding of the complexities involved in regulating markets and to encourage economists to approach policy-making with greater caution and consideration of unintended consequences.

Overall, introducing a course on "Unexpected Regulatory Consequences" would be a valuable addition to the curriculum, helping students develop a more comprehensive understanding of the challenges and potential pitfalls associated with regulating free markets."


I asked OpenAI:

"The analysis of the consequences of the responses to Covid-19 would be a good example of what to study in “Unexpected Regulatory Consequences”. That said, for economists, an analysis of the way too much ignored distortion in the allocation of credit produced by the risk weighted bank capital requirements, and which have, in one way or another, been in place since 1988’s Basel I, could be more important study case. Do you agree?"

OpenAI answered: 

"Yes, analyzing the consequences of the responses to Covid-19 would indeed be a relevant example to study in a course on "Unexpected Regulatory Consequences." The pandemic has triggered a range of regulatory interventions across various sectors and countries, and understanding their unintended effects would provide valuable insights for economists and policymakers.

Regarding the distortion in the allocation of credit caused by risk-weighted bank capital requirements, it is certainly an important study case. The Basel Accords, starting with Basel I in 1988 and subsequent iterations, introduced risk-weighted capital requirements as a way to ensure banks maintain sufficient capital buffers based on the perceived riskiness of their assets. However, this approach has attracted criticism for potentially creating distortions and misallocations of credit.

Some arguments against risk-weighted capital requirements include:

1. Incentives for regulatory arbitrage: Risk-weighted capital requirements can incentivize banks to engage in regulatory arbitrage, whereby they seek out assets that are assigned lower risk weights, leading to an excessive concentration in certain sectors or asset classes.

2. Complexity and opacity: The calculation of risk weights involves subjective judgments and modeling assumptions, which can introduce complexity and opacity into the regulatory framework. This complexity may undermine the effectiveness of the regulations and make it harder to assess the true riskiness of bank portfolios.

3. Pro-cyclical effects: Risk-weighted capital requirements can amplify the booms and busts of the business cycle. During periods of economic expansion, perceived risks are often lower, leading to lower capital requirements and potentially excessive lending. Conversely, during economic downturns, perceived risks increase, causing higher capital requirements and potentially exacerbating credit crunches.

4. Failure to capture systemic risks: Risk-weighted capital requirements primarily focus on individual asset risk, but they may not adequately capture systemic risks that can arise from interconnectedness and contagion effects within the financial system.

Studying the consequences of risk-weighted capital requirements could help economists understand the potential drawbacks and unintended consequences of these regulatory measures. It could also inform discussions on alternative approaches to ensure financial stability and avoid distortions in credit allocation.

In conclusion, while the analysis of the consequences of responses to Covid-19 is relevant, studying the distortion in credit allocation caused by risk-weighted bank capital requirements is indeed an important study case that economists should consider when examining unexpected regulatory consequences."

Note: The answers are copied exactly from those given to me by OpenAI