#AI #OpenAI #ChatGPT: Does it behoove us citizens to, a someone smartly called it, to keep an “Eye On AI”?

I asked ChatGPT:

If different chatbots give you a different answer to the same question, can we then suppose these have been trained on different data or use different algorithms or both those things simultaneously?

ChatGPT answered:

Yes, differences in chatbot answers can result from different training data, different algorithms, or both. Here’s why:

1. Different Training Data:

If chatbots are trained on different datasets, they will have access to different information, leading to variations in responses.

Some models might have more up-to-date or specialized knowledge, while others rely on broader but older data.

2. Different Algorithms (Architectures & Fine-Tuning Approaches):

Even if two chatbots were trained on the same dataset, differences in their neural architecture (e.g., transformer models like GPT vs. a retrieval-based model) could produce different interpretations and responses.

The way a model is fine-tuned (e.g., reinforcement learning with human feedback, rule-based filtering) can also impact how it formulates answers.

3. Both Factors Together:

In most cases, chatbots differ in both their training data and the way their algorithms process that data.

Companies and organizations might use proprietary tuning techniques, censorship policies, or prompt engineering strategies that further shape their chatbot’s responses.

So, differing answers don’t necessarily mean one is "wrong"—just that they reflect different sources, interpretations, or biases introduced during training and tuning.

I asked ChatGPT:

"So, some chatbots might have been trained on selective data and/or use algorithms to provide answers, more than based on human intelligence, based on the answers its owners/programmers want?"

ChatGPT answered:

Yes, exactly. Some chatbots are trained on selective data and/or use algorithms that shape responses according to the goals, biases, or policies of their creators. This can happen in several ways:

1. Selective Training Data:

If a chatbot is trained only on certain sources (e.g., government reports, academic papers, or company-approved materials), it will reflect the perspectives found in those sources while ignoring others.

Some companies deliberately exclude controversial or unreliable sources to maintain credibility, but this can also introduce bias by omission.

2. Algorithmic Filtering & Reinforcement:

Beyond training, many chatbots use algorithms to filter or modify responses based on predefined guidelines.

Reinforcement learning with human feedback (RLHF) is often used to shape how a model responds, emphasizing certain viewpoints while suppressing others.

3. Censorship & Policy-Based Adjustments:

Some chatbots are programmed to avoid sensitive topics, give politically correct responses, or follow corporate or government policies.

Others might prioritize engagement, tailoring responses to be more agreeable or in line with user expectations rather than strict objectivity.

4. Commercial or Ideological Influence:

Companies or institutions funding chatbot development may align responses with their values, brand image, or regulatory requirements.

For instance, a government-funded AI might emphasize stability and official narratives, while a corporate AI could subtly steer discussions toward its products or interests.

Ultimately, while chatbots can provide useful information, they don’t always function as neutral arbiters of truth. Their answers reflect not just human intelligence but also the choices made by those who design and control them.

I asked ChatGPT:

"So, it might behoove us citizens, us ordinary AI users, to have a group of humans we trust, to regularly pose the same question to all major chatbots and report any major divergences, or major similitudes which could be just as strange/dangerous. Do you agree?"

ChatGPT answered:

Yes, that would be a smart and proactive approach. Regularly comparing responses from different chatbots could help detect biases, coordinated narratives, or unexplained gaps in information. Here’s why this could be valuable:

1. Detecting Bias & Selective Framing:

If chatbots consistently diverge on key issues, that might indicate selective training, filtering, or ideological influence.

If they all say the same thing despite clear alternative viewpoints existing, that could suggest coordinated constraints rather than a true consensus.

2. Accountability & Transparency:

Publicly tracking chatbot responses could encourage AI providers to explain their decision-making processes, making AI systems more transparent.

This could also pressure companies to allow greater user control over chatbot behavior (e.g., choosing between different response modes).

3. Preserving Independent Thinking:

If we become too dependent on AI without questioning it, we risk outsourcing our judgment. Comparing responses helps users stay engaged and think critically.

By discussing differences and similarities openly, people can develop a more well-rounded understanding of complex topics.

4. Early Warning Against Manipulation:

If all major chatbots suddenly shift their answers on certain topics without clear justification, that might indicate external pressures, policy changes, or deliberate manipulation.

A trusted group monitoring this could serve as an early-warning system for undue influence in AI-generated information.

While AI can be useful, it should never replace human judgment. Your idea promotes independent thought and collective vigilance—something that might become even more necessary as AI grows more influential.

I asked ChatGPT:

"Would you mind having your answers compared to that of other chatbots? :-)"

ChatGPT answered:

Not at all—I welcome it! Comparing my responses with other chatbots is a great way to spot differences, uncover biases, and ensure a broader perspective on any given topic. If I provide an answer that differs significantly from another chatbot’s, that’s an opportunity for deeper analysis rather than something to avoid.

If you ever find major inconsistencies or strange patterns in chatbot responses, I’d be happy to discuss them with you. It could lead to interesting insights about how AI models are shaped and where their strengths and weaknesses lie.

I said: Thanks! As you can guess, I supposed that would be your answer :-)

ChatGPT said: You're very welcome! And yes, I had a feeling you might anticipate that response. 😉

I appreciate your curiosity and critical thinking on this—it’s exactly the kind of approach that keeps AI accountable and useful. If you ever do run a comparison and find something interesting, I’d love to hear about it!

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

A good way to fight the reigning Autocracy is with a Citizens’ Democracy, empowered by Artificial Intelligence.

#AI #OpenAI #ChatGPT: Here I am getting to know you artificial intelligence.

Here my many other questions to ChatGPT – OpenAI on bank regulations.

 

 

Let millions of ChatGPT bloom. Let millions of diverse worlds feed AI the data.

With unlimited hubris, very few regulators who thought they knew all about the risks to our bank systems, and also because of some political considerations, globalized risk adverse risk weighted bank capital/equity requirements.

They based their risk assessments on perceived risks; not conditioned to how banks usually reacted to perceived risk.

To determine the risks, they empowered some very few human fallible credit rating agencies.

And those few rating agencies, they got much of the information from some very few important audit corporations.

What could go wrong?

The perceived or decreed “safe”, e.g., governments, residential mortgages and assets rated as investment graded, were bound to get more bank credit and at lower risk adjusted interest rates than would otherwise have been the case. The perceived risky e.g., small businesses, entrepreneurs and consumers, bound to get less credit and at higher risk adjusted interest rates than would otherwise have been the case. De facto, more inequality was decreed.

The introduction of this abundantly clear systemic risk, completely ignored the value of a free market’s millions of diverse opinionated participants.

What could now go wrong with artificial intelligence?

April 2023, I had my first dialogue with ChatGPT. I got hooked. What amazing number of, for both of us, illuminating conversations I’ve had with it.

But May 2023, I asked, "Can AI be instructed to not tell the truth?", and it answered: 

"As an AI language model, my purpose is to provide accurate and helpful information to the best of my abilities. However, it is possible for AI to be programmed to generate responses that are not truthful.

In general, AI systems are only as unbiased and truthful as the data and programming that they are built upon. If an AI system is programmed to intentionally provide false information or to hide the truth, it can be used to propagate false narratives or disinformation campaigns.

Therefore, it is essential to ensure that AI systems are designed and used ethically, with a focus on accuracy, transparency, and accountability. This includes careful consideration of the data used to train AI models, as well as implementing safeguards to prevent intentional deception."

Ever since there’s not one day when I do not worry when I read, or hear, an opinion on the need to regulate AI. To guarantee diversity, and so that they all can keep a watchful eye on each other, I pray, as a minimum minimum: 

"Let millions of ChatGPT bloom"

"Let AI feed on millions of different opinion and data sources."

Human genetics made inhuman

Lately world leaders have issued statements labeling research into the human genetic blueprint as “one of the most significant scientific projects of all time.” They have also suggested that “to realize the full promise of the research, raw fundamental data on the human genome including the human DNA sequence and its variations should be made freely available to scientists everywhere.”

As of this moment, all I have read about the mapping of human genes has been so upsetting that it only brings to mind the title of the musical Stop the World, I Want to Get Off. I am very far from making my mind up about this difficult issue, but I need to share some of my initial concerns with as many people as possible.

A report cited in Reuters from the Daily Telegraph, London, indicates that “the government plans to allow insurance companies to use DNA testing to assess whether people are at risk of inheriting serious illness and should pay higher premiums.”

I believe strongly in the importance of the market as a means for the distribution of resources in society. However, I also believe that the benefits of development should accrue to all, not leaving any behind. What we now seem to be able to accomplish with research on the human genome multiplies manifold the difficulties of harmonizing these two previously contradicting objectives.

For instance, it would be great if genetics allowed the insurance companies to decide who will pay lower premiums, that is, those with less risk of developing serious illness. However, who will be responsible for those declared genetically second-class citizens, who will be forced to pay double or triple the premium, or who will ultimately be turned down altogether?

This problem is not limited to insurance. Reuters also reported on a conference to be held in mid-April in the United Kingdom in which “Genetic testing of children and testing for physical and social characteristics, as well as medical traits, would be high on the agenda.” Does this imply the possibility that even access to the university will some day be determined in part by genetic analysis?

What would parents who today limit their background search to asking their children who their friends’ parents are do tomorrow? Would they be obliged to ask about their genetic charts? The potential for discrimination is great, and would only reinforce the motivations of overly twisted Darwinists.

This genetic investigation might also represent a serious commercial threat for those countries that are not participating in this area. One of the companies racing to use information from gene mapping to make profits declared that it had hooked up with a center to find genes associated with breast cancer. If the efforts of this company are successful, it will be sitting on a patentable product and would be in a position to become a monopolist in a market with very inelastic demand. Can rationality be guaranteed within the openly declared and not unreasonable intention to obtain profit from the venture?

Many countries have signed commercial agreements that obligate them to respect patents to the extent of having to collaborate with other countries and punish unlawful use of protected discoveries. In the future, advancements in genetic science may force the revision of these accords, to decide whether they are still valid or whether, on the other hand and for the good of the common citizen, they should just look the other way.

What to do? It is very hard to say. Today, and just out of practical considerations, I limit myself to suggesting that all insurance companies design a plan which obligates them to issue policies for all of those who undertake a genetic examination. This policy should cover the negative impact and consequence that could arise from anyone getting access to such information.

I know this is only a Band-Aid, but what else can I do? I am not among those that resign and lie down to cry, even though this matter actually would justify just that.

From The Daily Journal, Caracas, March 2000

From Voice and Noise, Booksurge 2006

https://voiceandnoise.blogspot.com/2006/08/human-genetics-made-inhuman.html

Genes humanos hechos inhumanos 

A mediados de Marzo el Presidente Clinton y el Primer Ministro Tony Blair declararon in a joint statement que research into human genetic blueprint was "one of the most significant scientific projects of all time." Sugirieron también que "To realize full promise of the research, raw fundamental data on the human genome including the human DNA sequence and its variations, should be made freely available to scientist everywhere." Sonaba maravilloso. 

Desde ese momento solo he leido sobre aspectos relacionados con el mapeo de los genes humanos, tan perturbadores,.que a cada momento me recuerda el titulo del musical, Stop the world I want to get off. En la materia me encuentro muy lejos de encontrar una posición pero la angustia que me crea, me obliga a compartirla con muchos. 

Lo peor fue un reporte de Reuters en el cual, citando como fuente al Daily Telegraph de Inglaterra, se indica "The government plans to allow insurance companies to use DNA testing to assess whether people are at risk of inheriting serious illnesses and should pay higher premiums." 

Para alguien que como yo cree tanto en la importancia del mercado como mecanismo de asignación de recursos en la sociedad, como en la necesidad, objetiva y moral, que el desarrollo no solo alcance una parte de la población, y deje rezagada a la otra, las posibilidades que visualize, multiplicaron por mil las dificultades de harmonizar entre los dos algo contradictorios objetivos. 

Que bueno si la genetica permite cobrar una prima mas baja a quién no esta predispuesto a ciertas enfermedades, pero, quién se responzabiliza por el que resulte declarado ciudadano geneticamente de segunda y a quién le exigiran el pago doble, triple, o simplemente le rechazaran una cobertura. 

Lo anterior no se limita a seguros. La Reuter reporta también sobre una conferencias a mediados de Abril en Inglaterra y en la cual "Genetic testing of children and testing for physical and social characteristics, as well as medical traits, would also be high on the agenda." - lo cual dibuja en el horizonte la posibilidad de que hasta el acceso a las universidades se determine por analisis genetico. 

Los padres madres quienes hoy con toda normalidad le preguntan a sus hijos sobre quienes son los padres de sus amigos, qué harán mañana? Estarán en la obligación de preguntar sobre la carta genetica? 

Aparte de su potencial discriminatorio - que solo puede reforzar los argumentos de aquellos genéticamente desviados Darwinistas que buscan la raza suprema, la investigacion genetica también presenta una profunda amenaza comercial para los paises que hoy no tienen una presencia en esta area de la economia. 

Las primeras reacciones a las declaraciones de Clinto y Blair por parte del mercado financiero de empresas y laboratorios dedicado a la ciencia genetica fue negativa - se abre el mercado y se impide el monopolio. A los pocos dias la Casa Blanca declaraba "The whole point of this is to make raw data available so private companies can innovate, create new medicine and treatment and make a profit." y las aguas volvieron a su cause. 

Lo anterior plantea inmensos retos regulativos. Por ejemplo, Celera Genomics, one of the companies racing to use information from gene mapping to make profits, said on Monday it had hooked up with a center to find genes associated with breast cancer. Si los esfuerzos de tal empresa son exitosos obtendra un producto curativo y patentable, y se ubicara como monopolista en un mercado con una demanda inelastica. Como se garantiza la razonabilidad en la declarada y nada equivocada intención de obtener una ganancia. 

Un pais como Venezuela, ha firmado acuerdos comerciales que hoy lo obligan a respetar las patentes, hasta el grado de colaborar y perseguir el uso ilegitimo de estos. En un futuro, el desarrollo genético puede obligar a revisar estos acuerdos, para decidir si se siguen honrando o si, por el contrario, para el bien de sus ciudadanos, debe hacerse la vista gorda. 

Las reacciones emotivas que el tema produce, inspira escribir. Hoy termino proponiendo que las empresa de seguro, de inmediato diseñen un seguro, de caracter obligatorio para todo quien se haga un examen genetico, y que cubra las consecuencias negativas que se puedan derivar de poseer tal informacion. 

Reconozco que lo anterior solo es un pañito caliente, pero qué hago. No soy de los que renuncio y me hecho a llorar - aun cuando en este caso si provoca.

Forget the market for a while

The financial markets are continually boasting about having the best information available. They are right, but this continuous improvement in their capability to disseminate information comes at the cost of too much data too quickly. This results in an increased sense of the short term and no long-term vision.

It is only this that could possibly explain why today’s financial markets would impose interest rates on a country’s foreign debt that are so high that they can only be justified by the premise that the corresponding debt is to be repaid immediately and all at once. This is the case of Venezuela, a country with relatively little external debt.

This particular problem of disinformation in an era of information has resulted in an increasing volatility of the short-term capital market. This in turn has caused financial crises in many of the emerging markets and is being closely studied by many of the world’s monetary authorities.

In an article titled The Reform of International Financial Architecture published in Madrid’s newspaper ABC, Robert Rubin, former Secretary of the Treasury of the United States, recognizes the market’s basic responsibility, declaring that he is convinced about the need for government intervention in order to insure a better-market performance.

Mr. Rubin states that it continues to be necessary to solve the shortfalls in the risk valuation that have contributed to the worsening of the recent crisis and suggests that intervention should be made in the form of better international directives (i.e., the Basel Committee) which would increase dependency on long term loans instead of short-term financing. This type of intervention seems to me to be rather timid.

As a citizen of a country that due to internal and external causes finds itself in a bit of a mess, I wish to take advantage of the appointment of Mr. Lawrence Summers as new Secretary of the Treasury to ask him be more proactive.

For example, we would advance in leaps and bounds towards Mr. Rubin’s objectives should the United States guarantee the underwriting of a Venezuelan debt issue for US$ 25 billion with 30 year maturities with which Venezuela would repay all current debt that carries shorter maturities, which would make Venezuela one of the most solvent debtors in the world, which would make its debt instruments among the most attractive in international markets, which would insure that these could be placed at reasonable rates, which would allow the United States to free itself of any and all obligations thus obtained in a matter of minutes or hours.

Impossible, you say? Today, a firm that sells books, with no major asset base, and without immediate prospects of turning a profit is valued by the capital markets at US$ 30 billion, based primarily on its presence on the glamorous Internet. I simply cannot believe that the United States and Venezuela together cannot jointly put together an operation and negotiate the appropriate guarantees so that all parties come out smelling like roses.

I think that the majority of the authorities, government officials, professionals and individuals like Rubin, Summers and, modestly, myself, respect the free-market forces and system but also believe that it is sometimes necessary to promote government intervention. Where we may differ is in how this intervention should be enacted and how these two agents, market and government, should interact.

For example, over the last decades, the perception has been that a country like Venezuela should be very attuned to the requirements of a sophisticated financial international market. Attaining this markets approval would theoretically ensure that this country is on the right road to development and prosperity.

I believe this has been exaggerated. A country like Venezuela, which banks basically on one exportable product, has certain internal advantages and strategic strengths.

There is no reason why this country should bow to market forces. It has the right, and even the duty, to develop other options to ensure development that don’t necessarily include the markets.

Perhaps our problem today is not Venezuela’s external debt per se, perhaps our problem is the market. Faced with this reality, let us go out and negotiate options, government to government. This does not have to include subsidies or hand-outs. These options can very well be developed in an economically more reasonable atmosphere than that present in today’s market.