#AI #OpenAI #ChatGPT: Does it behoove us citizens to, as 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.

 

 

#AI #OpenAI # ChatGPT: When referring to productivity what's really measured? Can it be influenced to provide a specific message/result?

I asked ChatGPT: 

"When referring to productivity what is really measured? Is it a precise or very vague term? Can it be influenced by those wanting it to provide a specific message/result?"

ChatGPT answered:

Productivity is a widely used economic term, but its meaning and precision can vary based on context. Let's break it down:

What is Measured?

1. Labor Productivity: Often measured as output per hour worked. It gauges the efficiency of labor in producing goods and services.

2. Multifactor Productivity (MFP): Includes inputs beyond labor, like capital and technology, measuring overall efficiency in the use of resources.

3. Specific Sector/Productivity Metrics: Tailored measures for industries, such as agricultural productivity (yield per acre) or manufacturing efficiency (units produced per machine hour).

Precision or Vagueness?

Precise in Theory: Productivity has a clear definition and mathematical basis. For example:Labor Productivity=Total OutputTotal Hours WorkedLabor Productivity=Total Hours WorkedTotal Output​ In principle, it provides a straightforward measure of efficiency.

Vague in Practice: The term becomes less clear when you consider:

   Measurement Challenges: Determining "output" can be tricky, especially for services or knowledge-based industries. How do you measure the productivity of a teacher, artist, or software developer?

    Data Quality: Variations in data collection methods across regions or industries can introduce imprecision.

   External Factors: Economic cycles, regulations, or changes in technology can affect productivity in ways that are difficult to disentangle.

Can it Be Influenced?

Yes, the interpretation and presentation of productivity data can be influenced to serve particular narratives:

   Selective Metrics: Focusing on labor productivity while ignoring MFP can exaggerate labor efficiency gains while overlooking other contributing factors.

   Context Omission: Presenting raw productivity growth figures without considering changes in workforce demographics, automation, or economic structure can mislead.

   Policy Implications: Governments or organizations might highlight or downplay productivity trends to justify economic policies, like tax reforms or labor market changes.

Examples of Influence

   Boosting Confidence: Highlighting rising productivity as a sign of a strong economy.

   Worker Criticism: Using low productivity growth to argue that workers are underperforming, sometimes ignoring structural issues.

   Tech Advocacy: Overstating productivity gains from new technologies to justify investment or adoption.

In short, productivity is a valuable economic measure but not immune to manipulation. Understanding its context, methodology, and limitations is key to interpreting what it really means.

I said: Thanks!

It responded: You're welcome! 😊 Let me know if you have more questions—happy to help!

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

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

ChatGPT - OpenAI: Getting to know you!

Before going after the “filthy-rich”, it behooves us all to consider how they got their wealth and what they have done with it.

The plutocrats can have obtained their wealth in many forms ranging from highly licit and commendable ways that have even enriched many others, to odiously having used criminal means leaving many impoverished in their wake. But, once that wealth exists, what can the wealthy do with it?

They can invest their wealth in bonds and shares, which mean these assets, if well invested, will be productive.

They can freeze their purchasing power, by a sort of voluntary tax, on walls or in storage rooms, like for instance the $450 million Leonardo da Vinci “Salvator Mundi” (What those who got the $450 million fresh purchase power do with it, is what then becomes relevant to the economy) 

They can spend their wealth on things that no normal human being could spend on, which helps to create jobs than would otherwise not exist.

They can put some cash, on which they earn 0%, under the mattress... a couple of $100 bills?

They can engage in philanthropy, hopefully efficiently in worthy causes, otherwise that's a loss.

They can use their wealth to manipulate and exert undue influence.

That should primarily make us go after that wealth that has been obtained through illicit or immoral means; and that wealth that is used to manipulate and obtain more influence than what its owner should rightly have; and keep an eye out for useless and even bad philanthropy.

I argue all this because, when redistribution profiteers try to increase their franchise value by instigating envy and hate, it behooves the rest of us to make a clear distinction between the good and the bad among the astronomically wealthy; and to much better understand what has already been "redistributed" by the wealthy themselves, so as to avoid unexpected consequences.

What is absolutely certain though is that any redistribution of wealth will yield only a minuscule fraction of the benefits so loudly promised.

PS. There are though many market inefficiencies that allow wealth to be accumulated in legal and moral ways but that should anyhow be combated. This includes monopolies or excessive rent extraction from intellectual property rights.