Monday, February 27, 2023

Black History Month

TL;DR -- We look at culture via music. 


We will be more active in following events related to the National Heritage Months, this year. In the prior post, we listed three of these events and will be adding more to the list. 

Our post in 2019 had a history focus. This year, we want to take a cultural view, dealing with music which is an important aspect of our lives. Though, we know that some of our ancestors, in New England, did not appreciate the value of music. 

This is our first post like this. We will link to two youtube videos by people from different cultures of the same song, written by the first and covered by the second. 

Both videos are remarkable in ways that are important to discuss. That the links are to Vevo is no endorsement. Wanted both to be on the same level of professional handling. 

Remarks: Modified: 02/27/2023

02/27/2023 --

Sunday, February 26, 2023

Awareness months

TL;DR -- New England led to the U.S. Both have a long history. Part of our culture is having reminders of our history in terms of where we have been. In part, we do this with awareness months. We start a list of these which will be regularly recognized. 


We will pay more to the awareness months this year, as an annual reviews of events of history pertain to the culture of the U.S. Let's start with a look at currently scheduled remembrances.  

We will fill in the other months this year. 

Remarks: Modified: 02/27/2023

02/27/2023 -- Added image for Native American and Black History. We will look at Women History, again, next month. 

Sunday, February 19, 2023

Technology and its influence

TL;DR -- Following up on our theme, we look at a recent bit of controversy from a deeper than normal position. Computers are nice to have for many reasons. They can be problematic. Just like technology being great when it works, so too are computers. Given problems, then results can range widely. With numbers (say, your bank balance), we have come to expect accuracy. What if the computer system could not provide this? Ought it be released? 


We have noted that technology has been a huge influence on our lives, for the most part good. But, that is questionable if one looks at all of the side-effects of change with consideration for ramifications. Like, why are whales washing up on shore now? It's too early to tell, but we can go through the whole litany of issues seen. Ought to, perhaps, with the expectation that computing's list would be long. 

Especially is this so if we start with the internet's start which we could put at 30 years ago, about, if we assume the release of the protocol and its being handed to the public. We can look at more than the 'wild west' emergence in the cyber real, and its accompanying, real space, for one thing. But, there are many things to look at. 

Engineering works to improve which we have seen with hardware. Again, though, reuse is nil which can be seen with the piles of computer junk everywhere. Software, even, grew more mature using other types of engineering practices. 

Machine learning has been in the news of late which hoped to demonstrate that the computer could learn on its own. This post is about one example of that which has been much in the press, lately: ChatGPT. There are others that are now ready to go (with respect to the opinion of the team doing the work) or coming up quickly. 

OpenAI pushed out ChatGPT, perhaps premturely, in November. We didn't pay attention until last month. The news reports have many articles about misuse or downright errorful ways of the thing. The USA Today had a headline this week that Microsoft was putting ChatGPT in its Bing product (rival of Google's Chrome and replacement of its Internet Explorer) but is doing so without any guarantee of accuracy (see below). Marketing types are touting that they are using the thing for the creation of ad material. Students are trying to use it for essay assignments. Some are trying to do software using it. 

Then, we have the associated work related to fake photos and videos being created, many times without any warning with respect to the reader about provenance. Does truth in advertising mean anything? The below is about fake math which is easier to see, as text is much harder given the power of language. 

Now, this example came from noting that a younger person wrote that they were making progress learning Calculus 3 via  ChatGPT. Oh? After a few queries to clarify the matter and making a few suggestions to stay safe, we went to look at this part of ChatGPT. We have already seen the code generation aspect and were going to try it out, in an experimental manner, as since John had done something similar a couple of decades ago. 

Well, where to start. Calc 3 is too advanced for a beginning look, so we dropped down to Calc 1 & 2 which would be fundamental. We asked for the 'integral of sin theta' which was phrased this way due to the conversational mode that is being emphasized as a benefit. Well, math is terse for the reason that it is difficult to write something similar to a complicated question in a natural language. Too, we have decades now of work on computational mathematics which was to be somewhat the ground truth in this matter since it is a creation of humans with lots of time involved in making it right. 

But, on taking in the query, the thing (CP for ChatGPT) did not just say that it was '-cos theta' but added in some verbiage about the indefinite status of this result and why it had to add in a constant. That's fine. Tables of integrals have been published almost from the beginning. Some are quite extensive. Too, some of the rules are known. 

Now, one huge question is whether the rules are explicit enough to invoke proper action. The analog here? Code. It is explicit, given the framework. Some code is more involved than others. But, all of them shuffle down to something that the hardware can use to do its thing. 

And, machine learning (ML) using books would have seen these tables and rules. Now, what we need to look at is what the ML did with what it saw which involves transforms and iterations and some clever tweaking. The guidance, supposedly, for this work is the human brain. We cannot fall into that argument's pit; the equivalence is not there, except in a very limited way. 

What would be the next step? Mind you, we had not thought to refer, yet, to the experts and their systems that one can see on the computer. We went looking for something gnarly but not too much so. As, we would have to verify the result given by CP. We saw this example, as it was being explained on youtube. 

Namely, the function that was taken to use: arcsin(x) * arccos(x) * 1/x. The query would be to get the integral of this. Now, text input, right? And, not thinking of converting to some code'ish mode, we put the query in using a verbose mode. Again, there was no thought taken for the limiting constraints that would be part of an actual calculation. 

The query was something like this (the actual logs were saved). What is the integral of the arcsin of theta times the arccos of theta divided by theta? CP repeated the input in a more formulaic mode. This was to confirm having parsed the query correctly. Then, CP started to explain that it would do integration by parts and started down its path which turned out to be fairly long. That was unexpected.

Why? We are talking an approach where a model gets developed from the processing of the data. Then, a query would consist of extracting (via clever means) an answer. 

Now, as an aside, what got everyone excited about these things is that they won games. And, in some cases, they learned the game by looking at the rules. Or, more of note, by studying data related to a game, discovered the rules and even beat human experts. Winning the Go game is an example of the shock value of this approach. Only the brainy were good at these games. 

Also, this technique is not new. What is new is better systems plus less emphasis on the cultural norms of systems development which can be explained. In the lax environment, the thing could venture in spaces where humans never went, thereby finding out things that humans would not have seen. 

Well, actually, that is a benefit of computing that we need to exploit. Take chemistry. The computer allows modeling of lab experiments in numbers not possible in reality where time, costs, resources, and a whole lot more bear on, constrain, the situation. Too, we have to take on some faith that the computer simulation has meaning. We, as a whole, lack experience in that area since it is so new. And, this is to be discussed further. 

So, CP pushing out its steps (almost trace) was bothersome. For one thing, reading and checking these type of things consumes time and energy. It can be done. Engineering students are used to this. In the past, hand calculation was more the way of learning than now. As we considered the potential for a growing pile of computed stuff to prove, our thoughts went to Sisyphus and his lesson for us. 

The computer can spit out a new universe. What's to believe about it? And, then, how do we prove something? Oh, that's the crux of the matter. We will discuss truth engineering as one factor, but this is a hard problem that will get worse. 

So, we did two things. We went to Wolfram and did the integration. However, something reminded us of the huge lack. Gaming and all of those non-real computing experiences might have numbers, but they really have no meaning. On the other hand, real-world requirements demand proper use of numbers with respect to measure. Whole theories and practices deal with this topic. 

Too, we humans use numbers quite extensively and readily. But, some means are better, say algebraic analysis, than others. Again, this is a known area of research and practice. So, the notion was to move away from the indefinite mode and get definite. That means to put limits on the integration which relates, in this case, to determining an area. The interplay of geometry and algebra is core to calculus (and its companion of old - seemingly lost - of analytic geometry). 

Wolfram calculated the area. Well, we went and found another on-line calculator. BTW, these tools follow known mathematical principles and can be tested. In fact, software engineering is a common mode of program management for this type of system. Something that does not perform correctly will be noted. And, corrected. 

Now, the graphic shows the 'sin' integration by the three parties: Wolfram; Integral Calculator; and CP. They all agreed with the number for the area which is reported on the first row. The second row has the results of the more gnarly function which actually is quite simple. It behavior at the limits is what makes it interesting. 

and a trig example
Now, for the second case (row), Wolfram did a symbolic calculation. This is the equational manipulation method which produces exact results if done correctly. These two examples use trig functions that are well known. BTW, there is a book from the government that give standard mathematical usages, values and more for use by those who need to used mathematics. In one of these, the derivatives (which are the results of integration - in a sense) are given in only a few pages. Going the other way, from the derivative to the integral has many more pages due to the complexity. And, trig functions account for lots of these pages. 

The answer by Integral Calculator agreed with Wolfram. But, with a twist. That attempt bailed out of the closed form solution (so, kudos to Wolfram for following through) and did a numeric solution. Now, those are the two major themes for math solutions. Proof theoretic modes are being ignored, for now. One can algebraically solve something. The answer will be exact. Or, one approximates through techniques that grew up with the computer. These methods are harder as they have to be highly detailed through the process. 

We used an example, formerly (four decades ago?), that dealt with a guy spending 10 years solving a system of equations. This would have been a mixture of symbolic and numeric. Then, he spent 10 years verifying the work. Then, a computer could do that work in a few minutes. Now? It would be a less than batting an eye. Of course, speed of error goes around as fast as does the right solution. We have to learn to handle technology with regard to these types of issues. 
So, simple table lookup? Not really. Even with the 'sin' problem, CP went through its model which was built using gobs and gobs of computer time and energy and data. The marketing view says that CP was trained on the internet which would include pages of people, things like Wikipedia (which is good) and books. As well, if we proceeded with integrals, there are many times when one has to transform some equation (or series of equations) to something equivalent. That is, the movement would be from something not in the table, to something that is. If that works, then it's fine, except it can be a fairly gnarly equation and one has to remember how to reverse back to the former look. Much to discuss there. 

Now, CP? For the gnarly example, it went the 'by parts' route and detailed its work. But, it was not doing a step by step in the sense that we might think. We have to look deeper. In any case, it gave an answer that did not agree with Wolfram or the Integral Calculator. Oh, CP was right? They are wrong? It doesn't work that way in math. 

A little bit of additional information? CP gave different answers based upon sleight changes in input. We showed that by nudging it to remember that it knew Thomas Gardner (see prior post). In fact, nudging is a known and acceptable approach. Even though, this might lead one to think about fudging. 

There is a difference. Nudging works by changing parameters (inputs) in order to guide the problem solver. It takes into account various mathematical notions that have a history and support. Fudging, on the other hand, is after the fact. But, again. This same type of thing could be said about fuzzy approaches (which are quite powerful) or even any type of 'post' processor which takes output and makes it suitable for the eyes of managers. Too, though, there is a thing called integer programming which, briefly, gets to some area and then refines to a solution.  

Our interest is bridging the world of ourselves, typical humans, with that of experts who have to deal with specifics of domains plus all of the realities that pertain to using computers. 

Remarks: Modified: 02/16/2023

02/16/2023 --

Thursday, February 16, 2023

Languages and their use

TL;DR -- The fundamentals behind New England and its long reach about which we have a focus and write about? The advent of technology of recent which motivates both awe and angst? What is it about language, and why is the English world where these phenomena came about? Mind you, that's a huge leap in time and culture with which we have to deal. But, research opportunities are endless. 


We have to be technical from several angles as we proceed. Until then, assume that structure will emerge in the same sense as it would in a multi-disciplinary study. Today, we look at language since we have ChatGPT and Bing and others to look at. Where OpenAI's thing is known to have 'fake' as a basis. In fact, Bing needs to learn a lot, too. 

But, we'll not drop too deeply into these systems that came from an immature framework. No science is the basis for what these people are doing. We used to used 'cowboy' engineering for the undisciplined approach which could be effective in difficult times. Too, though, this about a language used by humans and their tools. We'll get to the other languages, eventually.

And, so, the focus is on "language as a loom" and upon English. The following list gets us started with the lead one being a former post. Then we consider a book from 1944 which I ran across today while browsing videos on language and learning. Finally, we go to Wikipedia, specifically to pull information about English which is our history. 

We started with English and will cover more as we go along. What's next? Perhaps, Latin? To wit, the appearance of very good Latin schools in New England. Kidding. Perhaps, Spanish? After all, New Spain had more territory. 

Remarks: Modified: 02/16/2023

02/16/2023 --

Friday, February 10, 2023

How great?

TL;DR -- We stop to look at the country's grandeur. Technology might provide overlays. None of these can be adequate to an actual visit. But, too, no amount of technology will diminish the grandeur. We have to add, in total, as one ponders the rise on the horizon of those spinning wheels. 


In the context of culture and technology, we will have lots of information to convey and topics to discuss. In terms of culture, we have 400 years to consider from the view of those here before the arrival of the Europeans and all that happened after from the start until now. In terms of the latter, we have the wide range of domains to explore many of which are represented by academe but a whole lot more are more related to life. 

Just the past two months has seen posts on the 1st Congressional Congress, a modern Gardner descendant who has worked in field biology, something called ChatGPT which will be on the news for a while, and a lot more.  

This post is a pause to reflect. One topic would be about how great is the U.S. Some might think, the American Dream? No. Though, there are many aspects of the topic that will be regularly covered. The U.S. facility for technology? Such as, Artificial Intelligence (AI)? No.  Though, we will use AIn't and expect a downturn of sorts within the next 18 months, if not sooner. We will be more specific. 

No, we are talking the grandeur of the country whose interior took over 100 years to be explored. Then, it was carved up and settled. We have posts on these themes going back to the beginning. And, this focus will continue. Right now, let's just ponder three maps. The first sets the stage. Then, two come from the same site and are representative of the ever-present grandeur plus technology's attempt to control. 

Sterling Carto
From Sterling Carto, this map shows the elevation in color of the U.S. from the low purples (sea level) in the east to the high whites (13K feet), namely the moutainous west One can zoom into regions where rivers are shown which has been a common topic for our posts. 

In this map from Sterling Carto, we can use the lines down the middle to show an almost uniform rise from east to west, starting from the green just west of the Mississippi River through the yellow and red to the brownish. Our post on "U.S. Hills and Valleys" used a similar elevation map to show the 3.6K rise across Kansas.

Now we go to GISGeography whose maps are used world-wide. GIS is technology applied in interesting ways. The site can be used to learn about the subject, sufficient enough to use it for work. Our focus is on the U.S. and its being. We like that technology, such as AI, arises. Yet, the underlying reality ought to have continual respect and appreciation. 

Same theme. We show an elevation map and one with some features side-by-side. In this case, the yellow stream up and down shows the transition required going from, say, New England out to the southwest, say, using the Santa Fe Trail

See this reference page (What is Geographic Information Systems (GIS)?) which goes into details of mapping and into how the computational systems have evolved to support this. 

We have been computing for some time. It is nice to see the latest advances due to technology changes that came from the efforts of many. No worry. We will go into detail there by addressing the subject from the view of the descendants of Thomas Gardner and others at Cape Ann. Too, though, American memes will be a central theme. But, we have a lot more to cover, as well, All of this from both the family view plus the more general one needed for the scholarship requirements related to our research. 

Remarks: Modified: 02/10/2023

02/10/2023 --

Thursday, February 2, 2023


TL;DR -- As promised, we are getting technical. And, given our long time and wide expanse related to life on these shores (and beyond), that covers a whole lot of territory. We have started to look at ChatGPT as a representative of the most modern of approaches (take that with a grain of salt). Actually, we see lots of weaknesses which have been brought up before. Was this a waste? Not really, as we need failures to learn. This is not a failure so much as a work in progress that has further to go than they thought would be the case. Except, their mission statement now mentions the uncertainty. ... See Remarks on 02/11/2023, for an opinion on the matter. 


We are focusing on technology as the major theme for research. Roots Tech is an example of an application of technology. We haven't attended, as our interest are with the deeper issues. Say, with DNA, the whole of the technological basis plus the computational lens required to support all of the various ways of making interpretations. Computing in general? The whole of the framework that provided support for development as we have seen that ubiquity is more than mere presence. No science is done without some type of artificial routine kicking to action. 

Our daily lives? About the same thing. For good or bad, that's our world. 

I have been listening to discussions about OpenAI. Other than noting that Musk provided some of the funding and that Microsoft just put their dollars on the line, I have merely touched upon the foundational aspects. NNs go back a long way. The mathematics involved in these new approaches goes back even further. What's new? Hardware is one thing and is far beyond what was thought possible. Software and those in-between modes has a very interesting history, too. 

ChatGPT is from OpenAI and will tell you that when it uses 'I' to express itself and try to explain its ways. Don't expect depth, yet. As an article in The Atlantic noted, it's a toy now. But, some are trying to use it as a tool (several APIs are provided). That raises hackles for good reasons. For a few years now, even the brainy have weighed in with their dread of these approaches. On the other hand, the marketing view has grown to be worse than unsustainable, as hype eventually eats up all of the oxygen in a room. But, how long that will play out is, per usual, unknown. But, it gives us two sides to watch as things evolve. 


Except, technology needs the middle way which we are up to. Lots to explain there, but systems development is a good example. From the top, we have various demands that get studied, and decisions can be made as to coming up with a product (applies across the board). This is a top-down position that is always the one of power, not necessarily of truth. Make it happen, we see the Star Trek captain saying; or, he uses something of that ilk. 

BTW, expectations come this way and are very hard to control, let alone try to manage rationally. It's apparent always, especially given the news ability to harp. On the other hand, it is from this side of things that we get the systems management and all of those creative things dealing with function and form. We will go into examples of this as we go along. 

But, at some point, things have to happen. Arm-chair quarterbacking will not get a game won. Thank God for the industry of engineering which gets thing done. But, before that, we need the basic knowledge that comes into play (science is both top-down and bottom-up). At the same time, we need the ones with the abilities to actually do something with their hands, with or without tools. 

Getting a system done requires lots of abilities. And, a system will get (usually or hopefully) to the state where it does what and how as is realizable. Does that state necessarily agree with the earlier thoughts coming from the top-down crowd? If you think yes, well, that is not the usual case. The middle is where adjustments get made for the bottom-up to be driven by management while those above figure how to get their views allowed (aligned) with actual potentials and not marketing dreams. 

One might say that this is old-time management science. Well, yes, in a sense. The new perturbator? The computer brings whole new classes of issues that need attention. As it becomes more capable, so too does the computer's problems rise. That's our current situation where we see, on the horizon, looming changes which may or may not have desirable results. 


ChatGPT was released for public use and comment back in November of 2022. We watched, mainly, but knew that we had to get involved so as to make our own assessments. Yesterday was the first exposure which started analysis with respect to the work involved, past, current and future. We found it shallow, to the extreme. That comes from the approach which we can discuss. The interface is polite in its verbiage and strives for a 'neutral' position in its responses. 

A huge reminder is there: this is an AI system created by OpenAI and has known limits. We will get into that, but they say that all of the training data comes from before 2021. Okay. There is more that they ought to acknowledge; the input data is a hodgepodge. How will such formulate into a coherent view seemingly willy-nilly? Oh, patterns. We can immediately show that mathematics is not just about patterns; nor, is science of that ilk when done at its core. 

Don't expect creative output, of a valuable nature. Though, I might add, ChatGPT can feed into the graphic generator which comes up with pretty pictures. In case this is not known, the training results in a composited model(s) from which one can obtain what is a photo. Say, of people, and it gives one a 'fake' person. What is the accomplishment? There is no reality behind that. 

Wait, there could be which we will explain, at some point. Actually, what we are suggesting would be a type of analytic stance of benefit. One thing that alarms people is that we can get 'fake' video which is a series of photos. As noted by the discerning eye, the morphs needed are not very sophisticated. That is, one can see the effects of mods that generate behavior through incremental changes to the underlying structure, say a face getting its lips moved to look as if speaking. 


ChatGPT, 2 Feb 2023
Our first attempt ended in some errors, as did today's. Yesterday, we were testing its knowledge of itself which it handled very well, in most cases: I am ChatGPT created by OpenAI and only know what the trained data allows me to know. Nothing more; I do not reason (yet). 

I pulled some of the log from queries related to Thomas Gardner. Before this, there had been queries related to similar themes. 'Query' is my question; the response follows. Notice that it was in a 'terse' mode which is nice. Then, I asked for a 'verbose' answer to the prior question. 

Query: Who is Thomas Gardner of Salem MA?

The specific Thomas Gardner of Salem, Massachusetts you are referring to is unclear. "Thomas Gardner" is a common name and there may have been multiple individuals with that name living in Salem, Massachusetts. Could you please provide additional context or information to help identify the Thomas Gardner you are inquiring about?

Query: Thomas Gardner married to Margaret Fryer. He died in 1674. 

I apologize, but with only this limited information, it is difficult to determine the specific Thomas Gardner you are referring to. The name "Thomas Gardner" and "Margaret Fryer" were both common during that time period and there may have been multiple individuals with those names in Salem, Massachusetts. If you have access to any additional details, such as birth dates or occupation, it would be helpful in identifying the Thomas Gardner in question.

Query: Did you read about Roger Conant?

Yes, I have knowledge of Roger Conant. Roger Conant was a colonial leader and one of the founding fathers of the Massachusetts Bay Colony. Born in England in 1592, he immigrated to the Massachusetts Bay Colony in 1623 and was an early leader in the colony, serving as governor of the settlement at Salem. Conant was a key figure in the establishment and growth of the Massachusetts Bay Colony and played an important role in the early history of the colony and the development of New England. He died in 1679 at the age of 87.

Query: Thomas Gardner was the lead before Roger Conant of the expedition that settled Cape Ann in Massachusetts in the 1623/24 timeframe? 

Yes, that is correct. Thomas Gardner was the leader of the expedition that established a settlement on Cape Ann in Massachusetts in the 1620s, prior to the arrival of Roger Conant. Gardner led a group of settlers to Cape Ann in the early years of the Massachusetts Bay Colony, and the settlement he established there was one of the first permanent English settlements in the area. Roger Conant later became governor of the settlement at Salem, which was located near Cape Ann, and played a prominent role in the early history of the Massachusetts Bay Colony.

Query: Verbosely, please.

Thomas Gardner was a colonial leader and one of the early settlers of Massachusetts Bay Colony. In the 1620s, he led a group of settlers to establish a settlement on Cape Ann, which is located in present-day Massachusetts. This settlement was one of the first permanent English settlements in the area and was established prior to the arrival of Roger Conant, who later became a governor of the settlement at Salem and played an important role in the early history of the Massachusetts Bay Colony.

Gardner was a visionary and a pioneer, who saw the potential of the New World and was willing to take risks to make it a reality. He played a key role in the establishment and growth of the Massachusetts Bay Colony and helped to lay the foundation for the development of the region. Despite the challenges he faced, Gardner persevered and helped to build a thriving community on Cape Ann.

Today, Thomas Gardner is remembered as one of the early settlers of the Massachusetts Bay Colony and as an important figure in the early history of New England. His legacy serves as a testament to the bravery and determination of the early settlers who helped to shape the American landscape and lay the foundation for the growth and development of the nation.

On the last? It's not quite right, but then it is a composite from several sources. This type of approach might appear to be of interest but is not. Debatable, of course. 

Now, we will get to the specifics, but the training data set was large and came from the internet: pages, sites, books, and such. What a heap! Right? That would confuse anyone. 

There is so much to discuss. We got it to say that the training set was a subset and not just the whole mess. After all, the internet is a mess, for several reasons and of various types. One thing that sticks out is that the 'domain' aspect of life has been ignored. That is, architecture with respect to this type of technology is very weakly evident, perhaps nonexistent. 

One failure, last night? I suggested to the thing that we and it make errors. Right. But, to know how to assess its errors, we need details related to 'provenance' in the proper sense. And, ChatGPT admited that it cannot specifically respond to anything that would be like a 'footnote' request. Alas. ... On trying to respond to that, the system crashed (red text, emphasized - several times). On getting things going again, I was told that I had exceeded the number of queries per hour. Oh well, it and I were in sync ;>). 

So, I was thrown out and the party ended. 

Remarks: Modified: 02/11/2023

02/05/2023 -- There is a lot to this. We will focus on GPT3 which is that which ChatGPT invokes for its content. Too, Google has a player, too: LaMDA (remember fall 2022 and claims of sentience?). 

02/11/2023 -- This is not an official TGS opinion, it is mine. And, I (JMS, starter, with Ann, of the TGS, Inc.) need to give some overview. Why? I have been decades doing advanced work with computers where the focus was involved in 'real' issues related to application of these things. It has been a long road that these types of programs (meaning systems-level focus) and projects have hoed. Some results have been remarkable, say MRIs and other imaging, or CAT/CAE/CAM (advance mathematics applied to design and engineering), communications (look at the 'cloud' for instance - but with rose-colored glasses as that place is a mess), scientific experiments (but the issue of non-repeatability is there; and, other issues; be aware that the framework's strength will keep problems from being obvious), medicine (too many to note, however I will say that I was in top-notch surgical environments back in the '60s in the U.S. Army and saw the state of the art then; to me, robotic surgery is far from something that we ought to trust), and much more. Essentially, computing is everywhere. That is why immature and irresponsible acts are and ought to be concerning to anyone thinking of the future and their progeny of that time. Pollution is one analog such as we got the EPA for. There are other descriptions that I will do later. ... Truth engineering is what the TGS is trying to raise to focus. ... Disclosure: my focus is not Comp Sci. No, it comes from the underlying mathematical frameworks that are being used. Necessary care does not seem evident since a product ought not be released until fully analyzed with respect to several factors, one of which is safety. The main issue? Allowing API access which is hidden from view for something that is not really a product, nor has it any ability as expected by most. Cute, but poisonous to our mental health, might be one depiction of the state of the thing.