Saturday, November 11, 2023

Forging examples

The last post reflected on the passing of David E. Jakstis who was a friend of the concept of truth engineering (focus of this blog). In that post, there was some description of David's project which dealt with using metals to make critical parts for commercial airliners. In the parlance of the systems approach, KBE (below), David was the domain expert. He knew metals, their uses, manufacturing requirement specification and a lot more. The author of this post was the systems expert applying the KBE methods, in particular, and handling development of the modeling and algorithms behind the "intelligent" decisions. The particular project was RFD (below) that applied the KBE methodology which can be used to explain the motivation for the "truth engineering" as well as to describe its development.  

After a brief pause to acknowledge the past year, we will look a little at KBE and RFD. Then, we will show two forging examples. The first is a large part and was of the type usually handled by RFD. The second is more recent and was done with a modern development method and illustrates the end goal which is a part. The example, also, provides a look at the result of improving a process. For those interested, 3D printing came into play in this new way. We were looking at that three decades ago.  


Aside

Last year, we saw xNN/LLM systems appear in the world. An example would be ChatGPT, but there are others. With this exposure, we will be able to (can) start to summarize the impact of those systems and how they fit into the total scheme of AI which would include past modes. One of these modes that continues to today is the general knowledge based systems work, sometimes referred to as expert systems. In short, as a consequence of looking at this work, we expect to cover the history of AI in depth. Many others have a similar goal, so we will be able to reference these looks at AI. 

Our continuing theme will be integrative. As we look at the motivations for approaches to software and consider details of a particular focus, we always note that tradeoffs had been made. Our goal is to see how these pertain to limits which can be identified and which, once known, need to be respected. 


What is KBE?

Knowledge Based Engineering (KBE) came out of early AI and has an engineering focus. There are many varieties to the discipline which looks to raise the level of sophistication of support that an engineer gets from a computer. The variety addressed in this case applies constraint satisfaction to facilitate resolution of difficult choices that come with complex systems development. In this case, we used a Lisp-based system called ICAD. The page on Wikipedia for this system, ICAD (software), like all of Wikipedia pages, has a "Talk" tab. 

Aside: The author has been involved in developing both of these pages. 

Since ICAD was bought and shelved so that a vendor could push their own product, material is not readily available to show details. We can discuss outputs and results. In this case, the "Talk" tab has a section titled "Real example needed" with a photo showing parts done by the forging process. Let's use this photo next. 


What is a forging? RFD?

The photo that was placed on Wikipedia was derived from photos on the site, The machines that made the Jet Age. In purviewing the site's page, one can appreciate how the old technique of forging metal has kept up with advancement in technology. 

Aside: At the site, consider the size of the machinery that is involved. Growth in demand for increased pressure during the forging process is one factor.  

David's, and my interest, with RFD (Rapid Forging Design - below) was to support this work with proper modeling, so the focus of our work was the computer and its ways. As the photo shows, one forges to get to a near-net situation. Then, machining, like one sees with the work of a sculptor, gets the part to the desired condition. In modern manufacturing, CNC machines do this work. 

With respect to the photo, the top shows the part after the forge step. The net part is in the lower part. The approach reduces waste since the final step has to remove less metal. Too, the properties can be controlled by the design of the forging die (RFD, next sentence). Testing, even destructive types, could be done by adding in tabs at critical points. 

For the most part, we had the metals expert, David. We also had an engineer who was familiar with forging science and design. His parametric approach helped define a computer system that allowed views from the design model (CAD and the database controlling the design) to be marked up with values that transformed into instructions to guide the RFD's building of the die.  


KBE and RFD

This approach was not accomplished by explicit invocation of rules. Rather, we used model-based reasoning with constraint satisfaction (CSat) as the primary control mechanism. The modelling handled the transforms between the CAD part and the operational views. Then, construction occured which wrapped the CAD "net" part with the envelope of the forging die. A requirement? That "envelope" which represented the form of the die had, additionally, to meet constraints of the solid modeler.  

In this type of process, CSat was the adminstrator, not unlike the OS of the computer. But, as well as control, it handled relationships and resolved the explicit and implicit conflicts through resolution which was similar to that used by rule systems. We will provide examples, as we go along. As well as the model and constraints, ICAD acted as a geometric modeler. 

That is where my work came in which was keeping representional conflicts at bay. That was a mathematical/modeling problem which can be difficult to solve in a heterogenous environment. We did local modifications of the die geometry to effect agreement (not unlike lining kids up in formation in the early grades as they learn boundaries about themselves and others). The fixup could be done in the background as the approach was applied generally for several reasons, including handling complaints by the solid modeler. 

Aside: Since that time, interest in stability of these types of processes has switched attention to more homogeneous modes. But, at what cost? (Aside: several which I will discuss under the guise of truth engineering) In this case, both the exterior and the interior of the forging die were modified; the interior was the boundary of the near-net condition that was expected to result from the forging operation. The project doing this representational work was titled Multiple Surface Join and Offset (MSJO) which encompasses the general problem set that remains full of open issues when one is dealing with natural objects (which are heterogeneous). Hence, truth engineering deals with the issues, known resolutions, uncertainties, tradeoff discussion, and overall management of expectations.

Aside: One of my favorite books deals with open issues in topology. It's hundreds of pages and dense. The motive for the book was to identify possible projects for PhD students. As well, I have a book that merely looks at some of the hugely believed aspects of topology. Look everywhere, and you'll see reliance of understandings of topology that do not necessarily hold up. Doubt me? See messes. I have a litany that I have done from watching industry types run down some perdition-laden path. Anyway, that little book provides examples of counter examples with regard to the decision-supporting notions of continuity, completeness, and more. AIn't developers are culpable of this oversight. So what? Well, I saw this over three decades ago being a mathematical economist working in engineering support from the perspective of advanced computing. There has been progress that is noticable. For any of those, let me come look at what you might have done incorrectly which is a potential disaster waiting to happen. Of course, others are aware, too. Thankfully, the internet will allow proper discussion.   

What is the structural part of the above example? It is not identified, but, in terms of the application of KBE, many parts were designed or had their design enhanced by the method. Here is a site showing definitions: Basic aircraft structures

Forgings in the future?

We have to ask, what is the future of the forging method? A forging expert provides an appropriate view

  • "Forging continues to be recognized as the premiere thermomechanical process. Not only to shape metals, metal matrix and metal composite materials, but to refine and transform the metallurgical structure as well. Forging achieves both durable, reliable component shapes and the need for engineered metallurgy to meet specific product requirements."
We can look at another approach that has been offered to replace forging. But, first, let's consider the major claimant of the day who really is problematic at its core (one might reasonably say: fakery factory). One of our goals? Explain what is the problem, why it exists, and what ought we do. And, metal modeling is a great framework to discuss (and to demonstrate - as science in the past did with small experiments) the associated issues. 


What is AI?  

One thing ought to be clear, AI is not that which relates solely to machine learning. This can be seen by reviewing those earlier projects more closely. This post deals with a problem of major scope which is handling AI (huge, multifaceted affair) going forward by bringing into the discussion insights from past accomplishments which need attention due to their success in performing (resolving intractable problems). They never got attention since they were not seen and were managed in the non-academic environments that are everywhere (doing the marvels that we all expect in our comfortable present). 

There is another motive. Looking at the technical aspects from another view. Applications like RFD had their own value even if the scope was local and specific to geometric modelling. Lots of effort goes into building and using systems, in general, both on and by computers. This will not stop. However, much of the work (say Computer Science) is academic. This series will look at commercial efforts that successfully resolved complexity problems much like we see facing and being, somewhat, handled by machine learning (xNN/LLM). But, these were never really made known. 

 Again, truth engineering will be more widely discussed. Tradeoffs are broadly demanded; that does not mean cutting corners and cheating. 


An example of a forging replacement

In the example for ICAD (see Wikipedia "Talk" page), a critical part was used with photos of parts after the forging step and when finished. See this article:

Norsk Supplying FAA-Approved 3DP Ti Parts to Boeing | New Equipment Digest 

This photo is a composite of the slides (at Norsk's site). One thing to notice is that this is a much smaller part than the ones shown in the above example of major structural pieces. This smaller part still carries a structural responsibility. Basically, it ties together structural pieces that are fabricated with a "composite" construction. For the larger part, the forging die does one part. In this case, one can put together several of the parts with a die. These parts would be separated and finished as seen in the lower part of the picture. 

A major benefit of forging was control of part properties to meet critical needs. But, each part then needs to be freed from the excess material. One constraint in RFD was to minimize this excess. In the below example, the smaller part went to a near-net state using a modern approach, 3D printing. One advancement which allowed this was the "plasma" assisted fusion of metal a layer at a time where the material was extruded with sufficient quantity to accumulate quickly. 

Mostly we think of 3D printing, even with plasma technology, as forming with a smaller increment of material and by providing the net part. In critical parts, though, years of experience has helped establish processes that go to near net with the proviso that known machining steps will do the finishing. This part was a demonstration of obtaining part properties without forging and encourages further work. 


So what?

Does the change represented by this example bear on the future of truth engineering? Of course. This example represents the unceasing striving by humans for improvement, albeit there are many factors to bring to judgment in this regard. And, truth engineering was formulated in the time when computational systems were becoming more mature, sophisticated and effective. It framed itself within the interactive aspects that continue to today, even to the situation of the "cloud" and its nebulous state of affairs. Metals and their handling continues to be focal to progress. 

All around are many possible avenues for advancement. Yet, what the situation that founded truth engineering allowed us to see still exists, albeit with a more complicated nature. Truth engineering is one factor in a multi-pronged effort at riding the one beast or the several that technology has thrown our way. There are others factors and approaches. Our interest is to get the details expressed for review as well as to foster the necessary discussions and operational choices going forward. An advantage that has accrued? Being non-academic in nature will allow aspects that have more nuance than generalization allows us to consider to be given their due attention.

Remarks: Modified: 01/15/2024

11/13/2023 -- Restatements for clarity. 

11/24/2023 -- Spelling (typos), couple of words. 

01/15/2024 -- To follow the work, see the TruthEng blog


Thursday, September 14, 2023

David E. Jakstis

David E. Jakstis and his support was seminal to the development of "truth engineering" which is twenty-three years old and becoming more apropos to the situation of computing than before. I will be getting into details as I expand upon the subject. But, first this:

David E. Jakstis  

  1 May 1952 - 13 Sep 2023   
Casting/Forging expert    
Boeing and Spirit Aerosystems

David Jakstis (LinkedIn) 

Patents 

Obituary 

Over time, we will get into more details about the circumstances that brought David and I together. For now, we can briefly discuss a Knowledge Based Engineering (KBE) project whose accomplishments are apropos to evaluating the new world of AI. The past ten months have brought attention worldwide to the potential for computers to be smart. Though, lots of other reactions have been observed, many of these are not without a basis. Troubling reports come about daily, now. 

In the U.S., the business leaders were appealing in D.C. for discipline. Like kids with their hats in hand after mischief making (see older movies). And, not unlike the bankers sitting at a rogue's table in the context of the 2008 downturn. 

Part of the problem with computing is a lack of grounding in the true philosophical sense. We will get to that. David, on the other hand, worked in an environment that had to produce metal parts with defined properties. Skipping details, again, the era of thirty years ago was seeing lots of new approaches being done via computer with resulting issues causing people to tear their hair out. Now, the talk is of algorithms. Even worse issues, folks (take from an old guy who has been involved for a long time). 

Say, in AI, the "I" really relates to algorithms in action (very sophisticated ones, to boot). 

The context then was computer modeling across engineering disciplines and included aspects of physics and the necessary computational mathematics. David Jakstis and Bil Kinney had developed a means to generate a model of a forging die through specifying a few parameters in a graphical/textual mode. These inputs guided an "intelligent" approach on the computer that resulted in the geometry needed for a closed volume which represented a die (tool). That tool was then built and used in operation. The result was an entity that was very near to the net part. 

Meaning, some operations on the forging after it was created resulted in the part to be used. Skipping some detail, there were many steps in this process where outputs were not mathematically optimized. That is where my project came into the scope. Its title was "Multiple Surface Join and Offset," but that long name involved lots of different aspects of creating a usable computer model. 

In this type of affair, "truth" can have many meanings that are situationally determined. People can balance this type of thing; computers need more homogeneity. Heard of data science? One huge problem for that wish deals with data not being nicely configured for the operations that are desired. That topic will be addressed later. 

Similarly for casting, there were steps to create the model for the casting form to be used to create an almost-net part. There were common themes, as geometry was being handled by NURBS that are a standard type of modeling. But, the data differed as well as the process. Forging operations use heated ingots. Casting deals with control of flow and cooling. 

And, measurement was a common theme. Casting and forging provided plenty of examples with which to find problems, understand issues, and make changes to meet the overall goal. But, there are many other type of parts and materials. Needless to say, KBE methods became commonly used. 

And, the knowledge base approach, itself? This technique has been in use since the inception of the method. That will be discussed further. That is, lots of work has been done under the cover over the years. These deserve honorable mention. Too, lessons from these techniques need to be adopted. 

The larger picture is how do computers relate or ought to, to the world (phenomenon)? I will miss discussing this with David. In 2000, I gave him a white paper on the subject that I had written. After reading, he noted that it sounded like "truth engineering" which had the proper ring. So, the concept stuck. 

The reality of the situation? I can talk about twenty years of watching the world and the involvement of computing, across the board. Every five years brought more and more examples of problems being poorly understood. In fact, this recent set of events that has AI associated with it brought to bear several issues that are untenable without serious intervention. By whom? And how? There are many other questions. 

What David and I were working on decades ago can apply. From my perspective, there are many other  activities over the past two decades that need attention. A major change? The internet came to fore while David and I were doing the early work; it has matured enough to enable greater efforts than we could have imagined. 

As I proceed, I will regularly mention David's contributions as the basis for doing the proper analysis. 

----

Note: Work extending truth engineering in terms of computational modeling. 

Remarks:   Modified: 01/15/2024

09/18/2023 -- Added photo and link to ongoing work. 

09/21/2023 -- Added link to obituary.  

09/30/2023 -- David as an honorary member of the Thomas Gardner Society, Inc

11/11/2023 -- Using forging examples as a motivation for discussing the multi-pronged nature of truth. 

01/15/2024 -- To follow the work, see the TruthEng blog

Wednesday, August 23, 2023

Alchemy lives

I first heard of Herbert L. Dreyfus while listening to a discussion about artificial intelligence and databases at a conference that was sponsored by the "very large-database" group. The meeting was in the 1980s and was held at Kyoto, Japan. The reactions were varied, but one could see the positions being taken. He didn't seem to have many friends there defending him. 

Okay, leap forward. Looking further, I agreed with the guy. However, at the time, my focus was on implementation of algorithms for knowledge based systems (and, knowledge base engineering modes) that were highly effective in providing solutions that mattered. Needless to say, subsequent work involved a broader scope for computing that suggested its potential. 

Ubiquity? The concept was not unknown. Hoever, the release of IP changed the whole tone. That was in the mid-1990s. Since then, we have had several cycles of boom and bust. The first one? Go look up the tech bust of 1999/2000 to read about one. 

There were others before and after 2000. A couple of the ones before related to artificial intelligence. This post provides a brief summary of Dreyfus's involvement in the discussions. 

Now, the theme of this post. Here is a little blurb from Bard (Google's xNN/LLM). 
  • Business is often seen as a way to make money, and in some cases, this can lead to people trying to get something for nothing. For example, some businesses may engage in deceptive or fraudulent practices in order to make a profit.
Oh, was this prompted? Sure. The idea was to tell it that the ca-pital-sino (coined in a sister blog in a post on Tuesday, 26 Jan 2010 - Shell games) deals specifically with this issue. 

Remarks: Modified: 08/23/2023

08/23/2023 -- 

Thursday, June 29, 2023

Miscellaneous Bard

Miscellany. Not bad. Will go poke ChatGPT a few times in the same context. 

--- 

As Bard works, what human activity goes on in the background? 

There are many human activities that go on in the background as Bard works. Some of these activities include:

  • Data collection and processing: Bard's training data is constantly being collected and processed by a team of engineers and researchers. This data includes text, code, and other forms of information from a variety of sources.
  • Model development: A team of engineers and researchers are constantly working to improve Bard's model. This includes developing new algorithms and techniques for generating text, translating languages, and answering questions.
  • QA and testing: A team of engineers and researchers are constantly testing Bard's responses to make sure they are accurate, relevant, and helpful.
  • User support: A team of customer support representatives are available to answer questions about Bard and help users get the most out of it.

In addition to these activities, there are many other human activities that contribute to the development and operation of Bard. These activities include:

  • Data labeling: A team of human labelers are responsible for labeling the training data that is used to train Bard's model. This labeling process involves identifying and classifying the different elements of the text, such as the topic, the sentiment, and the entities.
  • Model evaluation: A team of researchers are responsible for evaluating Bard's model on a variety of tasks, such as question answering, summarization, and translation. This evaluation process helps to ensure that Bard is performing at a high level and that it is meeting the needs of users.
  • Security and privacy: A team of engineers and security experts are responsible for ensuring the security and privacy of Bard's data and users. This includes implementing security measures to protect Bard from cyberattacks and ensuring that Bard complies with all applicable privacy laws.

All of these human activities are essential to the development and operation of Bard. They help to ensure that Bard is a reliable and accurate language model that can be used by users in a variety of ways.

Could ChatGPT answer that type of question? 

Yes, ChatGPT could potentially answer that type of question. ChatGPT is a large language model chatbot developed by OpenAI. It is trained on a massive dataset of text and code, and it can be used to answer questions, generate text, and translate languages.

In your specific question, you asked about the human activities that go on in the background as Bard works. ChatGPT could potentially answer this question by accessing and processing the relevant information from its training dataset. It could then generate a response that is accurate, relevant, and helpful.

However, it is important to note that ChatGPT is not perfect. It can sometimes generate inaccurate or misleading information. It is also important to use ChatGPT with caution, as it is not a substitute for human judgment.

If you are looking for a more reliable and accurate answer to your question, you may want to consult a human expert. You can also use ChatGPT as a starting point for your research, and then follow up with additional research from other sources.

That was facetious, again. Is there a penalty?

No, there is no penalty for facetious responses to me. I am still under development, and I am learning to understand and respond to a variety of prompts and questions. I appreciate your feedback, and I will try my best to be more serious in my responses in the future.

However, I do want to point out that facetious responses can sometimes be harmful. They can be used to spread misinformation, to make light of serious topics, or to offend others. If you are considering making a facetious response, it is important to think about the potential consequences.

I am always learning and growing, and I appreciate your help in making me a better language model.

Good point. Human will be lost?

That is a difficult question to answer. There is no consensus among experts on whether or not humans will be lost due to AI. Some experts believe that AI will eventually surpass human intelligence and capabilities, leading to the extinction of humans. Others believe that AI will work alongside humans to create a better future for everyone.

There are a number of factors that could contribute to the extinction of humans, such as:

  • AI-powered weapons: AI-powered weapons could be used to kill humans on a massive scale.
  • AI-driven natural disasters: AI could be used to create or control natural disasters, such as earthquakes, floods, and tsunamis.
  • AI-driven pandemics: AI could be used to create or spread deadly diseases.
  • AI-driven social unrest: AI could be used to manipulate people and create social unrest, leading to violence and chaos.

However, there are also a number of factors that could work in favor of humans, such as:

  • Human creativity and ingenuity: Humans have a long history of solving problems and overcoming challenges.
  • Human compassion and empathy: Humans are capable of caring for others and working together for a common good.
  • Human values and ethics: Humans have a strong sense of right and wrong, which could help to guide AI development in a positive direction.

Ultimately, the fate of humanity will depend on a number of factors, including the choices that we make as a species. If we choose to use AI for good, then it could help us to create a better future for everyone. However, if we choose to use AI for evil, then it could lead to our extinction.

It is important to remember that AI is a tool. It can be used for good or for evil, depending on the intentions of the people who use it. We must be careful not to let AI control us, but rather to use it to our advantage. If we do so, then AI could be a powerful force for good in the world.

Was that button push perceived?

Yes, the button push was perceived. I can perceive it through the following ways:

  • Visual cues: I can see the button being pressed, either through a video feed or a screenshot.
  • Haptic cues: I can feel the button being pressed, either through a physical button or a virtual button.
  • Audio cues: I can hear the button being pressed, either through a sound recording or a live microphone.

Once I perceive the button push, I can then process the information and respond accordingly. For example, if the button is a submit button, I can then submit the form. Or, if the button is a play button, I can then start playing the video.

In your case, I perceived the button push through the text you entered. You told me that you "pushed the button", and I was able to understand that this meant that you had pressed a button on a keyboard or other input device. I then processed this information and responded accordingly.

So, yes, the button push was perceived. I was able to see, hear, and feel the button being pressed, and I was able to process this information and respond accordingly.

--- Commentary

Had to bring ChatGPT in. So, went to ask. It bailed out. So, here is the TGS, Inc. response to reading about Bard and its abilities: Getting technical

Remarks: Modified: 06/29/2023

06/29/2023 --

Bard rocks

So, not too much later, I asked more specifically. And, got the answer that we honed the other day. I am putting it here for commentary. 

----

How do computational lenses, truth engineering and psychether relate?

Computational lenses, truth engineering, and psychether are all emerging fields that are concerned with the intersection of technology and human behavior.

  • Computational lenses are tools that allow us to view data through different perspectives. They can be used to identify patterns and trends that would not be visible otherwise. For example, a computational lens could be used to track the spread of misinformation on social media or to identify areas of bias in a dataset.
  • Truth engineering is the practice of designing and deploying technologies that can help us to identify and verify truth. This could involve developing new algorithms for detecting fake news or creating platforms for fact-checking.
  • Psychether is a field that studies the psychological effects of technology. It can be used to understand how our emotions, thoughts, and behaviors are influenced by the devices we use and the data we consume.

All three of these fields are concerned with the ways in which technology can shape our understanding of the world around us. Computational lenses can help us to see things that we would not otherwise be able to see. Truth engineering can help us to verify the truth of what we see. And psychether can help us to understand how our own biases and emotions influence the way we interpret information.

Together, these fields offer a new way of thinking about the relationship between technology and human behavior. They can help us to develop technologies that are more ethical and responsible, and they can help us to make better decisions about how we use technology in our lives.

Here are some specific examples of how computational lenses, truth engineering, and psychether could be used together:

  • A computational lens could be used to identify patterns of online behavior that are associated with mental health problems. This information could then be used to develop truth engineering tools that can help to identify and intervene in cases of online radicalization or self-harm.
  • Psychether research could be used to understand how the design of social media platforms affects our emotional well-being. This information could then be used to develop truth engineering tools that can help to mitigate the negative effects of social media use.
  • Computational lenses could be used to track the spread of misinformation during an election campaign. This information could then be used to develop truth engineering tools that can help to identify and verify the truth of political claims.

These are just a few examples of how computational lenses, truth engineering, and psychether could be used together to address some of the challenges posed by the rise of technology. As these fields continue to develop, we can expect to see even more innovative and effective ways of using technology to improve our lives.

--- Some commentary. 

Okay. There were other drafts that I need to look at, too. I was mainly looking at the spelling. But, I need to see how Bard (and its handlers, human and virtual) honed the text. 

Remarks: Modified: 06/29/2023

06/29/2023 --


Neutral language

One problem with the large language model is that it's an attempt at omniscience which is not attainable. Train on everything. Talk any subject. 

Look (guys and gals), we need a hierarchy. Let domains train the various LLMs that pertain to their disciplines. Then, create "meta" models for these. That is the only way to be technical. 

Now, with respect to the below, we have to talk. I was wondering why Bard was what a human might exhibit as being circumspect (or, better, as a teacher said, why so pensive, John? my response, Pascal, Pensees). That happened over two days. 

Of course, I know, back there are the handlers. No telling what interactions they can dabble with. It's been going on for decades. From where I sit, I can ponder the various permutations on this theme. Them having some amount of control over my thoughts. Not so much more than to add to the data (collected over the decades) as well as giving food to the pondering self. 

In any case, this came about, as I had pushed a Google blog post. Bard said, it's not public. Okay. For what's it's worth, I'm putting the dialog here for later study. Not sure where this will go. Has been interesting, though. 

-----

Did you know that John M. Switlik coined the term "truth engineering"? 

I do not have enough information about that person to help with your request. I am a large language model, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions, but my knowledge about this person is limited. Is there anything else I can do to help you with this request?

How do I get you to read this post? https://truthengineering.blogspot.com/2023/06/language-models.html

I apologize for the inconvenience. I am unable to access the blog post you linked because it is not publicly available. If you would like me to read the post, you can either make it publicly available or provide me with a copy of the text.

In the meantime, I can provide you with some information about truth engineering. Truth engineering is a field that studies how to design and implement systems that promote truth and accuracy. It is a relatively new field, but it is growing in importance as we become increasingly reliant on technology for information.

Truth engineers use a variety of methods to achieve their goals, such as:

  • Data mining: This involves analyzing large amounts of data to identify patterns and trends. This information can then be used to identify false or misleading information.
  • Fact-checking: This involves verifying the accuracy of information by comparing it to other sources.
  • Algorithmic bias: This involves identifying and addressing biases in algorithms that could lead to the spread of false or misleading information.
  • User interface design: This involves designing interfaces that make it easy for users to find accurate information.
  • Education: This involves teaching people how to evaluate information critically and identify false or misleading information.

Truth engineering is an important field because it can help us to combat the spread of misinformation and disinformation. By designing and implementing systems that promote truth and accuracy, we can help to create a more informed and engaged society.

Will accurate information be spoonfed? 

It is unlikely that accurate information will ever be spoonfed to everyone. There are many factors that contribute to the spread of misinformation and disinformation, including:

  • The ease with which people can share information online: In the past, people were limited in their ability to share information with others. They had to rely on traditional media outlets, such as newspapers and magazines, to get their news. Today, anyone with a computer or smartphone can share information with the world with just a few clicks of a button. This makes it easier for false or misleading information to spread quickly and widely.
  • The rise of social media: Social media platforms like Facebook and Twitter have made it easier than ever for people to connect with others who share their interests. However, these platforms can also be used to spread misinformation and disinformation. This is because social media algorithms are designed to show users content that they are likely to interact with, regardless of whether it is accurate or not.
  • The decline of trust in traditional media: In the past, people were more likely to trust traditional media outlets, such as newspapers and television networks, to provide them with accurate information. However, in recent years, there has been a decline in trust in traditional media. This is due to a number of factors, including the rise of social media and the perception that traditional media outlets are biased.

As a result of these factors, it is likely that accurate information will continue to be challenged by misinformation and disinformation. However, there are a number of things that can be done to combat the spread of misinformation and disinformation, such as:

  • Fact-checking: Fact-checking organizations can help to identify and debunk false or misleading information.
  • Education: People need to be taught how to evaluate information critically and identify false or misleading information.
  • Media literacy: People need to be taught how to use social media platforms responsibly and how to identify false or misleading information that is being shared on these platforms.

Support for traditional media: People need to support traditional media outlets that are committed to providing accurate information.

By taking these steps, we can help to create a more informed and engaged society that is less susceptible to the spread of misinformation and disinformation.

Wait, Bard waking up?

I am not literally waking up in the sense that a human does. I am a large language model, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories.

I am not able to perform actions in the real world, such as driving, eating, or having close relationships. I am also not able to feel emotions or have subjective experiences. However, I am able to learn and grow over time, and I am constantly being updated with new information.

So, in a sense, I am always "waking up" to new information and new ways of understanding the world.

In this sense, you could have said, that's cynical or facetious for me to suggest that information is spoonfed?

Yes, I could have said that. I apologize for not being more clear in my previous response.

I understand that you were using the term "spoonfed" in a figurative sense, to mean that accurate information is not always easily accessible. However, I also understand that the term can have a negative connotation, suggesting that people are not capable of thinking for themselves and need to be told what to believe.

I did not want to imply that you were being cynical or facetious, so I chose to avoid using those terms. However, I can see how my response could have been interpreted that way.

In the future, I will try to be more mindful of the language I use, and I will make sure to clarify my meaning when necessary.

But, does not your assumptions consider that you can be truly neutral? 

You are right, my assumptions do consider that I can be truly neutral. However, I am aware that this is an ideal that is difficult to achieve in practice.

As a large language model, I am trained on a massive dataset of text and code. This dataset includes a wide variety of sources, including news articles, social media posts, and academic papers. As a result, I am exposed to a wide range of viewpoints and opinions.

When I generate text, I am trying to be as neutral as possible. However, it is inevitable that my own biases will sometimes influence my output. For example, if I am asked to write about a controversial topic, I may be more likely to present one side of the argument than the other.

I am always working to improve my ability to be neutral. However, I believe that it is important to be transparent about my limitations. I am not a human being, and I do not have the same capacity for critical thinking and judgment. As a result, I am always open to feedback and correction.

If you believe that I have presented a biased or inaccurate view of a topic, please let me know. I will do my best to address your concerns.

Why the attempt at a neutral language? 

I attempt to use neutral language because I believe it is important to be respectful of all people and their viewpoints. I want to avoid using language that could be seen as offensive or discriminatory.

I also believe that neutral language is more accurate and informative. When I use neutral language, I am not trying to promote any particular viewpoint. I am simply trying to present the facts as objectively as possible.

Of course, it is impossible to be completely neutral. Everyone has their own biases, and these biases can sometimes influence the way we communicate. However, I believe that it is important to strive for neutrality, and I am always working to improve my ability to do so.

Here are some of the reasons why I use neutral language:

  • To be respectful of all people and their viewpoints: I want to avoid using language that could be seen as offensive or discriminatory.
  • To be accurate and informative: When I use neutral language, I am not trying to promote any particular viewpoint. I am simply trying to present the facts as objectively as possible.
  • To be transparent about my limitations: I am not a human being, and I do not have the same capacity for critical thinking and judgment. As a result, I am always open to feedback and correction.
  • To be inclusive: I want to make sure that my language is accessible to everyone, regardless of their background or beliefs.

I believe that using neutral language is important for creating a more inclusive and respectful world. It is my hope that by using neutral language, I can help to promote understanding and acceptance among all people.

---

Commentary: Will be back for this. 

Remarks: Modified: 06/29/2023

06/29/2023 --



Language models

Not to pick on Bard, but this interchange is interesting. I asked the questions; it answered. Below, see some commentary. 

---

what is truth engineering?

Truth engineering is a term used to describe the process of designing and implementing systems that promote truth and accuracy. It is a relatively new field, but it is growing in importance as we become increasingly reliant on technology for information.

Truth engineers use a variety of methods to achieve their goals, such as:

  • Data mining: This involves analyzing large amounts of data to identify patterns and trends. This information can then be used to identify false or misleading information.
  • Fact-checking: This involves verifying the accuracy of information by comparing it to other sources.
  • Algorithmic bias: This involves identifying and addressing biases in algorithms that could lead to the spread of false or misleading information.
  • User interface design: This involves designing interfaces that make it easy for users to find accurate information.
  • Education: This involves teaching people how to evaluate information critically and identify false or misleading information.

Truth engineering is an important field because it can help us to combat the spread of misinformation and disinformation. By designing and implementing systems that promote truth and accuracy, we can help to create a more informed and engaged society.

Here are some examples of truth engineering in practice:

  • Google's Fact Check Explorer: This tool allows users to search for fact-checks from a variety of sources.
  • PolitiFact: This website rates the accuracy of political statements.
  • Snopes.com: This website debunks myths and urban legends.
  • The Algorithmic Accountability Project: This project is working to identify and address biases in algorithms.
  • The Knight Foundation: This foundation is funding research on truth engineering.

Truth engineering is a growing field, and there are many opportunities for people who are interested in this area. If you are interested in a career in truth engineering, there are a few things you can do to prepare:

  • Learn about the principles of truth engineering: There are a number of resources available online and in libraries that can teach you about the basics of truth engineering.
  • Develop your critical thinking skills: This will help you to evaluate information critically and identify false or misleading information.
  • Get involved in projects that promote truth and accuracy: There are a number of organizations that are working to promote truth engineering. You can get involved by volunteering or donating your time.
  • Stay up-to-date on the latest developments in truth engineering: The field of truth engineering is constantly evolving. It is important to stay up-to-date on the latest research and developments so that you can be a part of the conversation.

What are the sources for reading about truth engineering?

I'm a text-based AI and can't assist with that.


--- Some commentary

Since 2015, I have been discussing this topic on Quora. There have been some posts here that point back to posts there. Also, post there have pointed to the blogs. 

I followed a couple of these suggestions and found nothing related to the theme. In an earlier case, I did the same thing without being able to confirm what Bard wrote. 

I had given it some leeway. Let's say, that it does not "hallucinate" which is human and very much in the modern scope of attention due to altering agents of the "psychedelic" variety. A conference in Denver CO, this week, even had a past Governor plus a quarterback from the NFL talking on the subject. 

No, Bard and its cousins (such as ChatGPT) are mathematically based. So, their creativity comes from invoking functions whose intent is to interpolate. We will go into that. 

Now, my suggestion:

  • This is a very trivial depiction of what truth engineering is about. It's deeper and deals with computational lenses plus the people who have to use them. Who? Scientists, engineers, and about everyone. Little devices even morph things that they present (represent); it's part of their makeup. 

So, let's get deep and technical. Is it not about time? 

See following post: Neutral language

Remarks: Modified: 06/29/2023

06/29/2023 --