Apps and truth

The rage now is 'apps' which can be used to describe truth engineering further with the hopes of 'app'lying the concepts to firm up computation, as it is presented to the common folks.

Yes, this applies, as well, to the open issue of the rolling labs (autos, ...) upon which, and into which, we put ourselves daily; the idea would be to lessen the experimental aspect (we want existential).

...

Ah, where is the old DOD where any computation required e-m shielding plus special handling of OS, and resource, issues? Gone with the Internet which is open to mis-'app'lication.

...

Many talk algorithms when they discuss apps. What? Algorithms are strong; but, they have severe pre-conditions. Even if you had an infinite set of powerful algorithms, there is still the hard problem of matching the algorithm with the problem (assuming that the problem can be defined 'app'ropriately) and then even interpreting results.

Ontology and epistemology are a couple of important issues here.

Now, heuristics (rule of thumb, even if support by Bayesian, and other, methods) can be strong, too, if they are founded on learned frameworks. In fact, we probably have more use for these.

Unfortunately, a lot of the software behind 'apps' is ad hoc. We'll go more into that.

...

By the way, none of this stuff is as easy as the youngsters try to make it (ah, MS, how many failings are under your paradigmatic responsibility?).

CEO apps? Well, we could have computational voting (at some point - consider the DOD issues that relate to security and stability and truthfulness). People, some, will still need their hands held.

As said before, we have three problems that are not yet resolved: qualification, frame, and ramification. That is, we have to deal with pre-conditions, closure, and then use of any (and in almost all) computational events.

Some pushed data base (static view - behind the numeracy craze (consider: numeracy leads to hubris, hence we need quasi-empiricism; innumeracy is not idiocy (..., as the commercial says -- ..., priceless ... (as in, numberless))) which even if it has operational behavior does not get outside of the 'apps' problems. Then, behavior (which includes those things related to dynamical systems - of which we, of course, are the epitome) analysis comes along with a whole set of age-old problems.

Some modern techniques try to cut to the quick (thanks, Occam - or, are you sorry for all of this modern mis-use?). Such reductions, as these are wont to apply, to the sufficient can throw out the necessary.

That, folks, is probably the most basic cause for a lot of mis-apps and their dire consequences.

...

Two important concepts, to look at more closely, will that we need to have man-in-the-loop (woman, too), including borgs (yes) and that humans have the uniquely held talent for truth evaluation (computation has an in-laid bit of vertigo that is impossible (yep) to overcome). The latter is trainable; the former is much more than augmented reality.

Remarks:

01/23/2015 -- Software? Well, we are talking more than apps (latest craze). We are dealing with fundamental questions which, then, gives rise to normative issues in mathematics (and, by extension, to the computational).

11/21/2010 -- Three years ago, it was said: Computational foci raise miraculous need. Still applies.

07/25/2010 -- That some have been allowed to misuse the situational uncertainties associated with modern technology, and its use, needs to be discussed. The ca-pital-sino result (the basis that we see for daily gaming a near-zero reality) was, almost, inevitable. How to extricate ourselves reasonably to a more sound foundational framework is of prime importance.

07/02/2010 -- Stunned? Hubris or stupidity (or, are they the same?). Meaning what? Well, this is a simple little thing, of no real consequence. How many problems lurk amongst all of those computational elements that have been spread around the economic world? Who cares?

Modified: 01/23/2015

Hint, heuristic, algorithm

Context: See Tru'eng anew, focus going forward, mathematics.

---

We were wallowing in the muck (it's an election year, so give us a break) wondering what could pull us out of the morass (we do need to get our tops up and spinning). Well, those with oodles of bucks, unless they are extremely careless (read: stupid), find it easier to remove themselves (not exactly, but that's a big T 'truth' issue) from the mess (they leave the crap to others). And, big bucks now are wandering after 'apps' which are oriented, for the most part, toward personal devices (mobile ubiquity).

Aside: Most don't enjoy that opportunity. Someone used baseball to characterize those with large pockets, in the following sense. They categorized the person's success by their starting position. Ellison, of the relational thing, was from the batter's box. Some start from first base. Others already had a home run at birth. You know, most are not even in the ball park. Z of FB was on one of the bases.

So, big bucks HOPE to make more by chasing after dreams (illusions -- as in, chimera). There may be technical aspects to the process that brings things forth, yet one would think that appealing features are more the focus than outright computational prowess. Calling something an algorithm does not make it so (below).

Sidebar: another issues that we'll discuss: A. 3 years with Vista and no BSOD -- only 2 weeks with this newer thing - Windows 7 - and I already have one; B. using the recent version of a program from a famous company, I kept seeing the thing go back to the initial screen. Well, it turns out that this is the default error mode (more friendly than the BSOD?), but it does the unwind without leaving any hint (see below) of what was wrong. It's like going back to square one and starting over (ever heard of Sisyphus?). But, getting a top to spin is not trivial. C. ...

---

So, let's look at this by using the three concepts from the subject line. They can be thought to have a progressive association somewhat like the following describes.

• hint -- We can view this several ways but consider a math problem. Many times, there may be a hint about how to approach a solution. One could say that a hint is sufficient to the wise. Unfortunately, computers are not wise and need explicit instructions. That, folks, is both the boon and the bane. It's the former since we can (try to) know what went into some computation (only under certain restrictive assumptions dealing with things like side-effects, black-boxes, etc.). Another way to think of a hint is that it lays down markers, within a landscape, whose presence helps keep things moving toward an end. Let's face it. Smart folks do not like to follow explicit instructions more than once (why then do we put people into the position where they are, for the most part, automatons? --- stupid, from several sides). You know what? We cannot give a hint to a computer in the same way that we can smart folks (forget the so-called smart devices - dumb-ass'd things, people). Except, if a person is in-the-loop during a computational event of complicated nature, the person can nudge the system away from divergent tendencies (yes, we'll expand at large about this being one way out of the quagmire -- suggesting, of course, human talents not yet developed).  
• heuristic - We could say rule-of-thumb, but it's to mean more than that limiting view. A heuristic view can be fairly powerful approaching, somewhat, the 'nudge' mentioned in the prior bullet. Why don't we hear people talking this, rather than the loud pronouncements about their algorithms? If anything, any decision logic would need to be heuristically based (using real data and analysis thereof) in a real world situation. Developments after Hilbert's question about a program to do all mathematics (Mathematica, and its ilk, notwithstanding) suggest such. 
• algorithm -- There is no agreed-upon definition. But, one strong notion is that an algorithm has (ought to have) more rigor behind it than not. Now, looking at the various characterizations (thanks to Wikipedia editors) can be interesting. Knuth's view probably best fits my experience. Namely, we have this: finiteness, definiteness, input, output, effectiveness. Let's look at those. Finiteness. Some argue that we have this by the vary nature of our domains. Not so. I've seen too many things loop (everyday, operators get lost, for various reasons on the web, which requires redo). Combinations of non-finite spaces can look extremely large from certain viewpoints. Definiteness. Unless there are explicit user requirements, there'll always be a problem here. Convergence, through interest and use, may be the modus operandi, yet it approximates only. Input: thankfully, menu interfaces inhibit problem emergence. But, just a few days ago, someone was trying to show off his new device. And, he started his dialog as if a 'smart' person was on the other side of his Shannon experience. Hah! The thing barf'd. I've seen this too many times, folks. Output: Crap, just look at mangled messages out of supposed smart fixup and fat fingering. It's almost epochal. I've seen too much effort by people to demonstrate that their smart device is such. We dumb ourselves down, folks, in order for this to happen (many, many ways). Effectiveness: As measured by what? Showing off to others? I'll be impressed when we see some type of verification process in places (no, not just testing). However, this is a hard thing to do. 

---

Reminder. See my remarks about Mr. Jobs' little demos from the earlier days. My thought still stands, despite IBM's success on Jeopardy. 

Aside: Don't get me wrong. I love that the software frameworks have evolved immensely. It's nice to open the covers and see the progressive build upon what one hopes is a sound foundation. But, it took oodles of time, effort, and caring work to get here. How do we try to show the extreme tedium, and angst, that has been the case from the beginning? You know what happened, folks? The tide was turned so that computation can be faulty without any user kickback except for not buying. Or complaining? And, the vendor saying: sorry. HOW many millions (billions) of dollars of work has been lost through errors that might be of an egregious type if we could get under the kimono to know for sure? Well, losses are not finite for several reasons (cannot be counted, or accounted for, and the secondary effects are not measurable). 

---

Oh, who with money (yeah, venture people, you) is even interested in the longer term problems? 

Remarks:

01/23/2015 -- Software? Well, we are talking more than apps (latest craze). We are dealing with fundamental questions which, then, gives rise to normative issues in mathematics (and, by extension, to the computational).

01/05/2015 -- See header.

03/23/2014 -- SAT solvers as an example of large class of heuristics.

02/25/2014 -- Put in a context link, up top.

07/20/2013 -- So, today, found out that a new handle for algorithms is algos. Okay.

06/14/2013 -- Moshe's editorial at the Communications of the ACM discusses algorithms. Comments, and subsequent letters responding, to Moshe's thoughts indicate the wide range of opinion in the matter.

05/02/2013 -- This has been a popular post (second most popular), of late. Perhaps, it's the growing awareness of the ever-increasing gap between what we think that we know and what we actually know. Well, the theme of the blog is to look at these types of problems. Perhaps, we can bring something forward from the past (such as, we not learning Anselm's message). I mentioned it somewhere (I'll track it down), but the motivation for this post was in part hearing young guys brag about their algorithms in a public place (of course, weekend situation, so some latitude is allowed). That concept is bandied about these days without people giving the notion its proper respect.

10/05/2012 -- Related posts: Zen of computing (in part), Avoiding oops.

10/05/2012 -- IJCAI has a newer flavor. It, at one time, had a theoretic thrust, mainly. Need to re-acquaint myself with the conference (attended 1987 Milan, Italy 1991 Sydney, Australia 1993 Chambery, France 1995 Montreal, Canada). This talk from IJCAI-2011 relates to the theme of this post: Homo heuristicus.

Modified: 01/23/2015

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. 

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 --

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 --

Can of worms

Well, who are we to believe? It's turning out that the answer to this question is less certain through time than we would like, in many situations.

In a recent one, the past couple of days has us seeing Toyota trying to disprove one professor by using another. Nothing new about that; science is supposed work via a type of dialectic. But, gamemanship, and such, as the main focus? (A third professor's view)

That people have experienced, and suffered the consequences of, some type of failure of auto control systems is the one fact not to be forgotten.

And, one would hope that the illustrious car company, whose reputation has always been associated with value and quality, will take the high road and do the right thing. Which is? (Note: 03/12/10 -- ah, they are, here is their web site related to recalls)

Well, Congress' panels ought to take the thing to its full extent, or at least as far as their monied selves will let them (definition of the politico set, of late, is characterized by a salivation response to the stimulus of money under the nose).

The Administration needs to live up to its responsibility. Which is? Act as mediator for disparate views (see below) and be an advocate for us, the wee people.

Now, for some of the other roles and views. Engineers need (and ought to be allowed) to work out the technical issues as they may. However, that we're talking hardware (operational and computational - with software for the latter) means that it's a new game. Perhaps, this dilemma might be an opportunity to learn some necessary lessons.

Lawyers? Well, several things here. But, one of these ought not be suppressing the truth by manipulating fear. That counsel goes for both sides. Whose first principles apply?

People, and drivers? Wake the heck up to the growing presence of little hidden 'bots' (general use of a term which is meant to imply that the genie has been let out of the bottle) that can play havoc with us if we don't pay attention. But what are we to do?

Evidently, for awhile, there has been a growing computational framework for the driving platform due to our technical progress of the last few decades. Surprise! Of course, this has been obvious, but we've let ourselves trust too much.

Too, some of us seem to have gone to a total zombie state (you know who you are), in this sense: mind warped by, and wrapped around, an abstracted, thereby virtual, cloud via thumb and eye, in the driving mode, to the extent that the vehicle has become a mindless WMD with no one in control.

Such behavior, on the part of the reckless, has allowed the potentials for devastation, for the driver and for those unlucky souls in the presence of the driver, to increase inordinately.

Of course, we might use that last condition as evidence of the influence that the 'gaming' generation's upbringing (computation in their blood, almost) has had some insidious repercussions that seriously need our attention.

That comment is not being negative; it is more this: the issues related to truth engineering need to be at the forefront (more below) of both an analytic and corrective (in the sense of control theory) stance.

Does failsafe mean anything to the people? Well, we could think of several connotations that are general, but that any of these might pertain to some type of increased certainty needs to be lifted to view for some serious scrutiny.

Why? For a computational system to be risk minimal, there are several things that need to happen. For one, all domains need to be decidable. Okay, sub-domains will be decidable. Any arbitrary collection of these will not, by default, be decidable. It (that is, the order and stability that we all desire) has to be imposed.

By the way, for now, just think of decidable as subsuming stability, convergence, and other numerically behaved properties (technical geeks, be patient, we'll get there - quasi-empiricism).

Too, even if we attain the desired, decidable, state, it may have been due to some type of cleverness and accomplished by a man-in-the-loop. Yet, that 'man' is not everyman but is someone who needs to be cognizant of the decisional issues, to be awake (aware, see above, zombie reference (state of mindless flow (apologies to Buddha) which is insensitive to subtle changes in the related sensors)), and to be experienced (one impetus for the growing use of simulation/visualization in the modern world).

What is decidable? Well, it is not something to assume. Some designers will argue that they've accomplished the necessary assumption set for closure. Ah! In an open framework, such as we see with driving, there is no proof of this. Why do you think that new products require so much testing? Even those with mathematical, and modeling, support need some type of empirical workout (an airplane, for example).

You see, there is really no basic mathematical foundation for these types of decisions that alleviates us of the need for caution. Why do you think that managers and lawyers get involved? Too, the required, onerous, aspects are costly both in time and resources (money, people) so we get the bean counters involved.

Engineers know these things, but they are human and can err.

Who to believe? Well, this is solvable, folks, but requires some effort. We'll use the situation to explore some of the issues and propose possible outcomes.

Leaping ahead: how can we get the proper stable computational bases for these operational entities without some serious cooperation across the industry to the extent, even, of having common platforms?

What? Yes, any creative, and competitive advantage, aspect probably ought to be limited to a small region of performance that could easily be tested.

So, let's bring the concepts of failsafe to fore. This will take a few posts, but here is a short list, for starters.

• Failsafe - acknowledges the possibility of failure and attempts some type of prevention (and lessening) of consequences
• Failure mode - recognition of these is necessary to know how to manage the failures even if they are to occur with minuscule probability
• Who to believe? - yes, in the small world of a system, there will be sensors, decisioners (bow to the great GWB), connectors, and more which at any time can be in conflict (computational sense - constraint satisfaction, NP, meaning hard) about what they know and what to do; too, there will be need some type of rectification (we might say, auto programmers, like quants, ignore complexity) even if the situation is undecidable (that's one reason for overrides, folks - yet, a mere brake override is not sufficient)

In terms of the last item, yes, the macro issues very much parallel those of the micro view. Or, we can look at it the other way.

We all learn conflict resolution in kindergarten or earlier. As we know, conflicts are real, some may even say essential (think ca-pital-sino). And, we know that power from the top-down (hammering down the opposition, for the politocos) can suppress the truth, thereby causing easy (or so it seems) resolution (which usually is a partial solution).

That this situation exists can allow a more complete discussion of some important issues (subsequent posts).

Remarks:

01/22/2013 -- USA Today story on settlements. From three years ago, lest we forget.

02/26/2011 -- Another go.

02/08/2011 -- There was a report today concerning a study on the SUA problem that has been going on quietly. More news will be coming later when the report is technically analyzed.

10/07/2010 -- Several principles need to be explored, such as the ergodic one.

09/28/2010 -- It nice to see the IEEE weigh in. Notice: sensors galore, drive in the loop, ...

04/19/2010 -- Genies, no not genius, indeed!

03/15/2010 -- Response to Toyota by Safety Research & Strategies, Inc. Did Toyota really use 'infallible' in describing their systems? One professor seems to think so.

03/12/2010 -- Of course, some media may be better than others. Popular Mechanics has a good article about the Toyota issue. Notice the comments: a wide range, some seemingly coherent and well expressed. However, that the overall tone of the article suggests user error as the chief problem is something that ought to be analyzed itself. For instance, if the accelerator and the brake pedals are being confused by the foot and mind of the driver, is that not indicative that someone didn't think to cause sufficient means to differentiate the two? Ah, ought there not to have been some studies to 'optimize' such selection? One problem with the modern world, folks, is that we apply set discriminators (in general, separation algorithms) without regard to some of the nuances that apply. Oh yes. One criticism of Lean (and Toyota's system) is that is cuts to the quick in a very efficient manner; at the same time, these actions leave a state in which it is very hard to recover traces sufficient for analysis, many times. That is one thing the NHTSA ought to look at in terms of what might be necessary to perform ex-post-facto diagnosis.

03/12/2010 -- Forgot to mention one player, namely the media, especially TV. Guys/gals, don't monkey with reports in order to emphasize some viewpoint, such as ABC is accused of doing. Oh, it's just editing, they claim. Wait, aren't media businesses just like the car makers driven by market share and profit? ... The question was asked: doesn't the public know that Toyota, with all its resources, hasn't looked at the underlying issues? Well, we also know that Toyota publicly admitted moving negatively on a quality line in order to put resources toward expansion of the market share. How to attain balance? Good question in that even the best-and-brightest fail regularly.

Modified: 01/22/2013

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 --

Albert and his boys

As in, Albert Einstein and the guys (and gals) of Physics. His ideas were central to the development of truth engineering. The trouble is, what are his ideas? He, himself, complained that once the mathematicians got hold of his model, he didn't understand it. Too, he covered a lot of bases over his time. So, in truth, we will have to track through all of that, over time. 

And space? Look at GenAI (which is really is AIn't as I have mentioned many times since 2021) and how it represents unwarranted "search" through hyper/multi-dimensional spaces. We will look at that closely. This recent work is dabbling with heterogenous stuff and assuming that transforms will bring in homogeneity. But, the work of Einstein dealt with things that were more amenable to being handled in the "canonical" fashion that homogeneity brings. 

Note: That last paragraph points to the essence of the main issue of the cloud which we can (and will) go into in detail (over time and space). However, when we look at the foundational issues being addressed by Einstein, we will see a close stepping forth (dance like) of mathematics and the operational so as to become problematic to the extreme. GenAI is a mere symptom of a huge problem. Time to start to grapple with that. 

All of this plus more is on the table as we bring truth engineering to bear using knowledge based engineering as an initial framework. Let's look at one book that will be of use for this work. It's his book with Infeld (so, E&I) with the title of The Evolution of Physics using archive.org's copy. The authors briefly start with the briefs and come through the usual trek of Galileo and Newton on down the pike. They look at the rise and fall of the mechanical view after which, of course, we get the introduction of "field and matter" that comes from the advent of relativity. They go through the ideas of (and which contributed to) special and general and finally end with a view of the quantum work that somewhat merges (interlaces) with relativity. 

Okay, we all know of the visual arguments that Einstein used (train, elevator, and others). The book has no mathematics, so the authors grunge out explanations using words. It works. On the other hand, there is something to what Feynemann mentioned with respect to not being able to understand quantumness without mathematics. 

I say, mathematics drove the development of the thoughts. We will spend a lot of time there. BTW, if there seems to be a different tone to these posts, that's quite observant. If not, that's okay, too. But, the work to date was mostly surveying all of the thoughts, as expressed over the past few centuries that relate to the themes associated with deciding what's true. That issue became imperative as the computer evolved, but we did not. 

Want an opinion? We have bent over backwards over the past few decades to make the computer look good. Oh yes. The biggest argument for this? The descent brought by misguided development of the web and its muddy cloud which was then fed into ML (machine learning) in order to become some sort of omni presence or know-it-all or what have you. How about overall jerk (3rd derivative, if you're an engineer)? 

But, back to E&I. I have been through the book several times. Why? I had it for some time and mostly dabbled (as Koestler mentioned with respect to library angels). Of late (blame GenAI's rise and verge toward a fall), I took the time to step through E&I's logic. Plus, having used GenAI to probe somewhat into the workings that were hidden, the imperative nature became apparent. So, we'll get through the whole of it. 

For now, I just realized that E&I mentioned television. The book is about 1938 in emergence to public access. E died in the 1950s. The book was republished. I said that he looked to make changes to bring it up to date and only did a few. So, the book stands as a point in time reference to needed discussion. 

See pgs 189 and 190 for the discussion of an inertial frame and its clock. E&I lay out how to pick some central position and try to synchronize. Remember, this was from the 1930s. But, there were rudimentary sets which showed the concept. Now, jump ahead. We have the internet with its cloud and more. Too, we have sophisticated clocks that can sync across the country. When we watch a game in the U.S., everyone seems to consider that the variability is minor with respect to delays and such. After all, consider the work put into supporting real-time streaming. 

It was good enough for on-line (say Zoom) meetings during the pandemic. People walk with phones to their ears (some drive, too) and seem to think that they're having a real conversation with little delay in the signals. Oh yes, for those who may want to know, we'll include some technical sidelines. 

For instance, the cloud? It's a bunch of services that are provided via distributed (some very much far apart) servers running synchronized  algorithms using high-speed connections. Oh wait? Everyone knows of Nvidia and its $trillions evaluation according to the ca-pital-sino (my neologism - see Fedareated). Right? That whole affair handles the relativity issue quite well, at least ostensibly. You know, we could be picky (and might due to the importance of the topic) and point out issues.  

But, that's later. People need their games even if it's like gambling and pulls money from the pocket and one's family needs. Same goes for GenAI which was done without due concern for things that are important. Don't worry, we'll get there. 

No, remember, E&I are not the only players in truth engineering. We're targeting that due to the interest in things quantum on the part of the computer people who like the ca-pital-sino and seem to want to have control more than is necessary. 

People's rights are being trampled with insidious algorithms. But, then, it's early yet. Will there be improvement or further decline. 

So, with that digress, let's put this off until tomorrow or after. 

Remarks: Modified: 03/21/2024

03/21/2024 -- 

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. 

•  Alchemy and AI  

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 -- 

Tribe as Truth

To follow a group’s view or one’s own mind may be the question in many situations. Hence, truth engineering must consider any interpretative viewpoint and its basis, since truth views can be held by a group or by an individual.

In a look at the group, it would not be pejorative (no such intent is meant) to use tribalism as its ethnocentrism (mean-centric tendency) pertains to truth. Considering the individual and truth would require a deeper look at cognitive issues and the fact that creativeness is more an attribute of the individual than the group.

In an example from where we have the most modern of thinking, any individual, who follows an independent path, say in pushing for a Kuhnian type of event in any discipline (a group), or for any non-mainstream idea, can end up being seen as crank or genius or even in-between.

That the balance may very well be resolved with a subsequent generation is immaterial for the moment.

Further complications can be brought forth by introducing computational issues, especially artificial intelligence and some types of applied mathematics. Generation, in this context, may include the shorter-term type related to improvements in computing, modeling, and algorithms.

In the modern world, most people are members (or adopt the view) of several tribes and have to balance, perhaps, conflicting positions.

For instance, any business can be thought of as a tribal entity which attempts to overlays cognitively those who are employees. How well this is done contributes to success. One might even say that if a CEO is a leader, rather than a pirate, this will help in the integration.

Yet, that tribe of the business does not supersede the many other tribal influences of the employee, except for the time of the work day. But, even in the work-day period, it is easy to see the different tribal views (is it not a characteristic of diversity to allow this?) in operation. In subsequent posts, we'll see how this might influence operations, such as in crucial areas like earned-value analysis.

Remarks:

05/09/2013 -- Eric Hoffer, longshoreman philosopher and autodidact, and his views apply here. 

04/25/2009 -- People matter.

01/27/2009 -- Now a new day and way to consider some of these matters.

Modified: 05/09/2013

JFN, Jr.

John Nash died this past weekend. He and his wife were in a taxi that crashed. Both, unfortunately, were fatally injured.

John is famous for several things. In terms of game theory, one of these is the notion of equilibrium in a multi-person, non-cooperative game. To that end, he proved existence.

For a long while, in this blog, we have mentioned that the modern "game" focus is not good (in many ways) for us. Yet, the whole of the intellectual set has run off in that direction. Now, that turn of fate has taken a long time to come about. John von Neumann did his part; John Nash gave it more of a push.

Along with the interest in applying this type of mathematics, we have seen an increase in computational power which then has kept the movement going. One could say, if there were no computer, it would be no big deal with game theory. But, they go hand in hand (just like bilking the markets are enabled by algorithms and by the general lack of understanding).

The net effect of these changes has been a cutting free of the human mind from the proper tethers. What? Yes. What might these be? Ah, much to discuss there. But, I did say a little earlier that I would be taking a different direction.

John's passing opens the door for me to revisit this whole deal; at the same time, I'll be able to argue more coherently. You see, the fumble-butt mode comes from seeing idiocy all around. How did this come to be?

However, I have seen, too, that there are islands of sanity here and there. Thank God for that. Oops, that type of thing was alluded to earlier.

Somewhere, recently, I mentioned that we need a "sucker" (sucker quoted since the connotationswill be other than used so far) game. Actually, to rephrase, a lot of games are incompletely described, even the prisoner dilemma. Why (just look at the abstract'd accumulation on that one theme)? I don't know why the intellectual bigots have allowed themselves to devolve to such a low level. Say what? Yes.

That mathematics (which is discovered more than not) has been the enabler for the emergence of stupidity is very sad. The big-mind-set, if they were only impacting themselves, would not be such a problem; however, these jerks, collectively, get themselves into the way of power and thereby get, in their minds, carte blanche to spoil the earth and its little chilluns (meaning, of course, all of those who are not of the power set). Gosh, so much to do to get the situation properly described.

So, "sucker" brought in (in other than the so-long sucker idiocy, and such)? Yes, if you would, please, conscience (a reality, from the proper point of consideration) as a part of the puzzle. Where the hell has that virtue (or, any of the other virtues) gone in the flim-flam modernity that we stumble under now?

Remarks:   Modified: 05/28/2015

05/28/2015 -- Again, again. There are a whole (larger?) bit of phenomena (however you want to characterize the wider scope) that is not brought into game theory (that I can see - I'll continue looking). Assuming that I have time, I will attempt to define some (perhaps, using situational means).

SAT Solvers

SAT? No, not the scholastic test. Rather, this deals with Boolean satisfiability which is a hard problem. A comment of Moshe of ACM Communications motivated this post. He was at a workshop this year that looked at a couple of things. One was whether were new theoretical insights from practice of late. The other was a sampling of techniques that solves these types of problems, albeit by rule of thumb.

We earlier mentioned algorithms as having a firmer basis than heuristics. There are a lot of SAT approaches. Let's pause here for a couple of pointers: Understanding SAT solvers, Flow Control Analysis for SAT Solvers. We could find a lot more.

From his observing the state of the art at the workshop, Moshe says that the methods are mostly heuristic. We might say that there are two issues to consider. One is that the hardness of a problem relates to the difficulty of finding its solution in an effective (time, resource, money) manner. The other is that solutions, if found, can be verified quite easily (compared to the search).

What does this mean for truth engineering? Firstly, assessing truth is a hard problem, computationally. We know this. But, truth is hard in general, too. Efforts at determining truth need to be reasonably constrained, if possible.

So, it is nice that we see motivation to define and explore the efficacy of a solution approach. However, we must, too, remember that maintaining the truthful state is not a given. In some cases, the trouble related to maintenance may be even worse than the original determination.

Catch-22? Somewhat. But, not.

Remarks:   Modified: 05/30/2014

04/24/2014 -- For a recent discussion on the other SAT, see Rick's post (he mentions big data and analytics, thereof).

05/30/2014 -- The May CACM (Vol. 57, No. 5) had an interesting article title "Understanding the Empirical Hardness of NP-Complete Problems" in which the authors talk about helping resolve hardness, somewhat (taming the beast), via statistical means. Makes one almost thing that these issues are of no concern going forward (throw computational power at the problem). But, it cannot be as easy as that (to wit, at the end of the 18th century, the Illuminati was claiming that everything was known about physics - so everyone go home and twiddle your thumbs). As the authors say, has to do with whether you can get solutions and whether you can do so in a reasonable time. Yet, there is more (still to be characterized). If the spaces quake, solutions become more difficult. Say what? Yes, we'll be getting back to this.

Analytics

As we said in an earlier post, Big Daddy Data, everyone is hot after analytics. These are framed computationally, you all know, bringing out little gremlins from the tracings that we leave of ourselves. Okay?

Much ado about nothing, to boot. The commercial analytics are the clearest way to perdition, people.

---

So, the other day, in a conversation, on a Sunday, so that gives me the right to be philosophical (actually, I don't need any permission, motivation, or whatever - it's always there), a conversant makes note that it's interesting how I can relate "analytics" (of course, IT milieu) to philosophy. Now, in the guy's favor, I was broaching upon the topic of truth engineering.

Say what? I thought. Then, I said, you know, philosophy was into analysis way before the latest craze which is the result of oodles of years of work by many people all culminating now with idiots misusing knowledge (say it isn't so - MBAs are the worst of the bunch).

---

Earlier, I wrote about algorithms in the context of apps (a big load of stuff to weed through and potentially a big source of errancy - in terms of opening one self up to manipulation). The term is used loosely now. Of course, if it's in the analytics framework, it does have a mathematical basis.

But, and it's a big butt, tell me analytic'ers, what say you about the quasi-empirical (to be discussed) issues? Well, that will be one focus henceforth. Firstly, bring up the topic in this discussion so that there is recognition of its reality. Then, look at the issues and at how they're important to our computational future.

Lord knows that the term was used continuously since the beginning here (44 of 200 posts) and in other blogs (FED-aerated - 25 of 211, 7oops7 - 38 of 248). Mind you, it was my oversight to not go into it further, just as I assumed too much about near-zero's recognition (still need to address that in depth). At least, these topics are sufficiently complicated to keep me busy for awhile.

Remarks:   Modified: 02/10/2014

01/16/2014 -- The recent Communications of the ACM had several stories on big data. Their claim is that the loads of data collected within the past five years or so is a sufficient set to make claims. Well, actually, the idea is to generate predictions, thereby getting a slap on the back from science. However, all sorts of things come to mind which I'll get into. First of all, that parallel universe of data that comes along with internet trafficking and just plain use tells us what? No matter its size, and the duration in which it is collected, the stuff, by no means, describes a person except for some small aspect of themselves. It does not subsume the being. And, even if someone is wrapped by the collection and analysis of this secondary data, it's not real. But, more on this. ... And, mathematics does come into play, misused (ah, the worldview of the MBAs gone mad).

01/16/2014 -- After starting the above example, complications started to lurk that we could ignore for awhile, but, at some point, these would have to be addressed. Say, after a few items were sold by the one who had them first (arbitrary boundary situation, here), those who bought would look at how they could, perhaps, make more than illusory money by selling at a higher price. The value determination then would become some type of functional problem bringing in difficulties that have been long the domain of the mathematicians (the ultimate abstraction'ists, somewhat, but, analytics would be involved). While looking at pedagogic material that would be of interest, I ran across this web site (Intuitive guide to exponential functions). I have not read this yet, but the fact of the amount of comments that have ensued, plus those who commented, got attention. Too, John von Neumann said that we don't understand mathematics (higher-order types); no, we get used to it. However, there must be an intuitive aspect if we are going to appeal to truth and people's place in its determination. So, that usage resonated with my thinking. Too, though, we have a class'ist split that is happening under our noses. In one sense, it relates to numeracy. But, the more insidious part deals with overlays (computationally enhanced) becoming more real than the reality itself (we'll get into that ad infinitum).

02/10/2014 -- Put a comment at this post: brane-space.blogspot.com of-g-o-d-and-god-concepts.html We said that we would raise meta issues (as in, big T), at some point. It's been two years since we had the first of a sibling collection depart.

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 --

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.