tag:blogger.com,1999:blog-38247073289889242182024-03-02T13:35:28.129-08:00Truth Engineering(Tru'eng - on truth engines and "being/Being")AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.comBlogger313125tag:blogger.com,1999:blog-3824707328988924218.post-60503705134576430392024-02-03T10:07:00.000-08:002024-02-04T12:25:51.369-08:00Assessments, in general<p>We have done this blog, in concert with 7'oops7, since 2007. We started Fedaerated in 2009. Then, in 2010, we started the TGS blog (last post, <a href="https://thomasgardnerofsalem.blogspot.com/2024/01/technology-assessments.html">Technology assessments</a> ...). For the Thomas Gardner Society, Inc. (TGS), as well, we had some publications (Gardner's Beacon). In 2015, we went over to Quora and have been there since. Various excursions were related to using other modes, such as WordPress. </p><p>But, we're back to Google and its Blogger. Why? Of all of the xnn/LLM systems that we looked at (granted, the survey was not exhaustive), we liked Bard the best. So, we'll work in that environment. At the same time, we'll touch all of the to other resources on a regular basis. It's just that we'll use this for publishing where we want to support mobile devices. </p><p>Of late, we have tried LinkedIn's approach which we look at below. There we published the first of a series. We just completed the third piece what is expected to be five pieces. What we call <b>AI</b>n't is the motive. Truth engineering has been on our table for a long while but was problematic. What did it mean and for what motive is it necessary and why just this? </p><p>2023 brought the answer to the questions. Answers have been embedded within these posts all of this time. So, the effort was right on. Let's just say that I was being exhaustive in a way that can only be understood in the academic sense as being highly multidisciplinary. I was retired and had the time and the interest and the ability. </p><p>There is no hubris in that comment; rather, it's a nod to a continuation of what I was doing anyway - advanced computional systems - without having the time to be thorough. So, it's time to pull all of the factors together so that we can analyze and perhaps predict and propose changes. For me, being successful at the complete survey of the western civilization's influence on the world is enough of a motive. However, the world is large, so we need to bring into the discussion all other cultures. </p><p>Notice that the TGS is based upon the history of the U.S. as an offshoot of the U.K. Be that as it may, we know that New England was not alone. Too, we know the prior history of these regions. Albeit, lessons learned or not over 400 years require attention. BTW, the U.S. started 250 years ago, almost, so that event will get regular mention. </p><p>Okay, after seeing ChapGPT and noting the issues, I began discussion with Larry Walker who had run the Knowledge Systems Center for Sperry Univac for which I worked. The focus on "knowledge" was strong for both of us. That was not what we were seeing with the machine learning systems being pushed out. We can discuss that at any level. For now, these posts will be setting the stage for discussions that are pending and necessary. </p><p>I became aware of ChatGPT in February of 2023 which was late. I wrote several posts on it and its cohorts and other topics that relate. But, in December, I published on LinkedIn the 1st of a series. It was also presented in PDF and at WordPress. The title: Artificial intelligence, not solely machine learning (AI, not solely ML). The 2nd of the series continued the theme: Knowlege and truth. </p><p>Neither of these seemed to be of importance of the work that went into xNN/LLM. Why say that? It's been by career to work with these issues operationally (real time, industrial environments); at the same time, my private work (autodidact, by nature) covered the bases with respect to what's at play and of scope. Essentially, "theoretical" is my middle name. </p><p>I just finished the 3rd of the series: Physicalness and mathematics. There will be one more (4th) that deals with the emergence, and surgence, of machine learning during the past two decades. As well, we have to look at data and decisions as a key topic with regard to computing and technology. That is, people, in general, need to know. Experts? We'll address their issues, too. After the 4th, we'll do a 5th which will deal with "What's next?" with all of this stuff. </p><p>The series is based upon experience in KBE as it functioned as the basis for <a href="https://truthengineering.blogspot.com/2023/11/forging-examples.html">truth engineering</a>. So, it's more oriented toward those operationally involved with engineering and science. I'll turn around and write this series (condensed) for the general public. </p><p>So, here is the series: </p><p></p><ul style="text-align: left;"><li><span style="background-color: white;">1st - AI, not solely machine learning (</span><a href="https://ajswtlk.com/TruthEng/2023/12/11/artificial-intelligence-not-solely-machine-learning/" moz-do-not-send="true" style="background-color: white;">Blog post</a><span style="background-color: white;">, </span><a href="https://www.linkedin.com/pulse/artificial-intelligence-solely-machine-learning-john-m-switlik-lu0uc?trackingId=CcJd5AsSQ1WXaNRURnRMWg%3D%3D%2F%3FtrackingId" moz-do-not-send="true" style="background-color: white;">Linkedin</a><span style="background-color: white;">**)</span></li><li><span style="background-color: white;">2nd - Knowledge and truth (</span><a href="https://ajswtlk.com/TruthEng/2024/01/07/knowledge-and-truth/" moz-do-not-send="true" style="background-color: white;">Blog post</a><span style="background-color: white;">, </span><a href="https://www.linkedin.com/feed/update/urn:li:activity:7149944178896945152/" moz-do-not-send="true" style="background-color: white;">Linkedin</a><span style="background-color: white;">**) </span></li><li><span style="background-color: white;">3rd - Physicalness and mathematics (</span><a href="https://ajswtlk.com/TruthEng/2024/02/01/3rd-physicalness-and-mathematics/" moz-do-not-send="true" style="background-color: white;">Blog post</a><span style="background-color: white;">, </span><a href="https://www.linkedin.com/feed/update/urn:li:activity:7157568832117645312/" moz-do-not-send="true" style="background-color: white;">LinkedIn</a><span style="background-color: white;">**)</span></li><li><span style="background-color: white;">4th - ML’s emerge/surge and data/decisions ()</span></li><li><span style="background-color: white;">5th - Where do we go from here?</span></li></ul><p></p><blockquote style="border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;"><p><span style="font-size: x-small;">Notes: </span></p><blockquote style="border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;"><p><span style="font-size: x-small;"><span style="background-color: white;">* "truth engineering" coined by <a href="https://truthengineering.blogspot.com/2023/09/david-e-jakstis.html" moz-do-not-send="true">David E. Jakstis</a> in discussion of a white paper by </span><span style="background-color: white;">John M. Switlik on their joint work with computational modeling for fabrication of forgings and castings.</span></span> </p></blockquote></blockquote><blockquote style="border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;"><blockquote style="border: none; margin: 0px 0px 0px 40px; padding: 0px; text-align: left;"><p><span style="background-color: white;"><span style="font-size: x-small;">** This is open to public read. Some Linkedin pages may require account. </span> </span><span style="background-color: white;"> </span></p></blockquote></blockquote><p>--------------------------------</p><p>In tems of history, the U.S. D.O.D. supported early work in artificial intelligence. As well, data science was a common program. It is of interest to future discussion to point to the recent guidelines for digital enginering. We have made reference to "digital twin" which is an important concept that must be brought into the discussion related to advanced computing. We will have this document a major piece of our bibliography. </p><table align="center" cellpadding="0" cellspacing="0" class="tr-caption-container" style="margin-left: auto; margin-right: auto;"><tbody><tr><td style="text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj_g16tq-D0xztWj2POm-_Y_BXVxJ0_2c_ul0tWp_70P28dx3_u2IJRTanDfQyGDEbl23D4oU5pIPjLAjLMMoEqao2Qu8bq1Mkw8KxynNdW0gstIMFG0NHC42fjRR9t9dAo9zN4y8_AKw-6JDqCoJuZwrQDhSYWXxwJUBTdLB4a7UP6y438C4IFlKOGPYY/s1024/DigitalEngineering.jpg" style="margin-left: auto; margin-right: auto;"><img border="0" data-original-height="769" data-original-width="1024" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj_g16tq-D0xztWj2POm-_Y_BXVxJ0_2c_ul0tWp_70P28dx3_u2IJRTanDfQyGDEbl23D4oU5pIPjLAjLMMoEqao2Qu8bq1Mkw8KxynNdW0gstIMFG0NHC42fjRR9t9dAo9zN4y8_AKw-6JDqCoJuZwrQDhSYWXxwJUBTdLB4a7UP6y438C4IFlKOGPYY/s320/DigitalEngineering.jpg" width="320" /></a></td></tr><tr><td class="tr-caption" style="text-align: center;"><a href="https://www.esd.whs.mil/Portals/54/Documents/DD/issuances/dodi/500097p.PDF?ver=bePIqKXaLUTK_Iu5iTNREw%3D%3D%3E">Digital engineering</a></td></tr></tbody></table><p><b>Remarks: </b><i>Modified: 02</i><i>/04/2024</i></p><p></p><p>02/04/2024 -- Linked this to 7'oops7 (<a href="https://7-oops-7.blogspot.com/2024/02/ai-not-solely-ml.html">AI, not ML solely</a>) which will bear directly on the 777 project underlying KBE which relates to truth engineering as AI when it matures. Notice: <a href="https://truthengineering.blogspot.com/2007/09/shattered-dreams.html">Shattered dreams</a>. </p><p><br /></p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-64607643060813935672024-01-01T13:01:00.000-08:002024-01-01T13:05:35.559-08:00New Year, 2024<p>Notice the start of decline in our activity here when we moved to Quora (2015). </p><p>Here is a list of posts. </p><p>We will be active in 2024. </p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiFge57yXzsEUOxUs5y1xFV8tipBoNyJXp9CMLTup3pI4CCcMGgMZ1eOvtDvO-luL23oUoQccFo7j72UtLy_E8TnZ-_kXePKYB2mL33JCwjFIS3E0QJEaUDI0P2CNl-lF-K-qJ9OzcxCckjzisr_acj4AOHgmnyWGaLKkZCL_GuOkfU9KaRpXntOfgQBLw/s448/BlogPostsFTE7.jpg" style="clear: left; float: left; margin-bottom: 1em; margin-right: 1em;"><img border="0" data-original-height="448" data-original-width="391" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiFge57yXzsEUOxUs5y1xFV8tipBoNyJXp9CMLTup3pI4CCcMGgMZ1eOvtDvO-luL23oUoQccFo7j72UtLy_E8TnZ-_kXePKYB2mL33JCwjFIS3E0QJEaUDI0P2CNl-lF-K-qJ9OzcxCckjzisr_acj4AOHgmnyWGaLKkZCL_GuOkfU9KaRpXntOfgQBLw/s320/BlogPostsFTE7.jpg" width="279" /></a></div><br /><p><br /></p><p><br /></p><p><br /></p><p><br /></p><p><br /></p><p><br /></p><p><br /></p><p><br /></p><p><br /></p><p><b>Remarks: </b><i>Modified: 01</i><i>/01/2024</i></p><p></p><p>01/01/2024 -- </p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-13360942994949978412023-11-11T18:13:00.000-08:002024-01-15T12:24:40.039-08:00Forging examples<p>The last post reflected on the passing of <a href="https://truthengineering.blogspot.com/2023/09/david-e-jakstis.html">David E. Jakstis</a> 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. </p><p>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. </p><p><b><br /></b></p><p><b>Aside</b></p><p>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. </p><p>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. </p><p><b><br /></b></p><p><b>What is KBE?</b></p><p><a href="https://en.wikipedia.org/wiki/Knowledge-based_engineering">Knowledge Based Engineering</a> (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, <a href="https://en.wikipedia.org/wiki/ICAD_(software)">ICAD (software)</a>, like all of Wikipedia pages, has a "Talk" tab. </p><p>Aside: The author has been involved in developing both of these pages. </p><p>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 "<a href="https://en.wikipedia.org/wiki/Talk:ICAD_(software)#Real_example_needed">Real example needed</a>" with a photo showing parts done by the forging process. Let's use this photo next. </p><p><b><br /></b></p><p><b>What is a forging? RFD?</b></p><p></p>
The photo that was placed on Wikipedia was derived from photos on the site, <a href="https://boingboing.net/2012/02/13/machines.html">The machines that made the Jet Age</a>. In purviewing the site's page, one can appreciate how the old technique of forging metal has kept up with advancement in technology. <div><br /><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEim2eRLfczdjlEconSKDc9vGpkpjRK1ggEDM8wdBE_n0xwUHqSTuqdUSUFgDHCGixqIfUnEumsOXs_5axxOyscf1K1S91ZTYwMkN3kjWcLMdyIVMrDceQSEV7Gj3PJn5-JoBAxzwspPFw_a4eX_nXFHn1Icfc1D63NYJ_kREXbfeW2b6UskIbUUoTLoGE4/s867/ForgingExample.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="867" data-original-width="545" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEim2eRLfczdjlEconSKDc9vGpkpjRK1ggEDM8wdBE_n0xwUHqSTuqdUSUFgDHCGixqIfUnEumsOXs_5axxOyscf1K1S91ZTYwMkN3kjWcLMdyIVMrDceQSEV7Gj3PJn5-JoBAxzwspPFw_a4eX_nXFHn1Icfc1D63NYJ_kREXbfeW2b6UskIbUUoTLoGE4/w202-h320/ForgingExample.jpg" width="202" /></a></div></div><div>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. <p></p><p>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, <a href="https://en.wikipedia.org/wiki/Numerical_control">CNC machines</a> do this work. </p><p>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. </p><p>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. </p><p></p><p style="-webkit-text-stroke-width: 0px; color: black; font-family: "Times New Roman"; font-size: medium; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-decoration-color: initial; text-decoration-style: initial; text-decoration-thickness: initial; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px;"></p><span style="-webkit-text-stroke-width: 0px; color: black; display: inline; float: none; font-family: "Times New Roman"; font-size: medium; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-decoration-color: initial; text-decoration-style: initial; text-decoration-thickness: initial; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px;"></span><p></p><p style="-webkit-text-stroke-width: 0px; color: black; font-family: "Times New Roman"; font-size: medium; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-decoration-color: initial; text-decoration-style: initial; text-decoration-thickness: initial; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px;"><b><br /></b></p><p style="-webkit-text-stroke-width: 0px; color: black; font-family: "Times New Roman"; font-size: medium; font-style: normal; font-variant-caps: normal; font-variant-ligatures: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: left; text-decoration-color: initial; text-decoration-style: initial; text-decoration-thickness: initial; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px;"><b>KBE and RFD</b></p><p>This approach was not accomplished by explicit invocation of rules. Rather, we used <a href="https://en.wikipedia.org/wiki/Model-based_reasoning">model-based</a> reasoning with <a href="https://en.wikipedia.org/wiki/Constraint_satisfaction">constraint satisfaction</a> (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. </p><p>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. </p><p>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. </p><p>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.</p><p>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. <b>AI</b>n'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. </p><div>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: <a href="https://bluetunadocs.com/downloads/acsguide.pdf">Basic aircraft structures</a>. </div><div><br /></div><div><p><b>Forgings in the future?</b></p><p></p></div><div>We have to ask, what is the future of the forging method? A forging expert provides an <a href="https://www.qcforge.com/forging-innovations-blog/the-future-of-forging-will-new-processes-replace-forging/">appropriate view</a>: </div><div><p></p><ul><li>"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."</li></ul><div>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. </div></div><p><b><br /></b></p><p><b>What is AI? </b> </p><p>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). </p><p>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. </p><p> Again, truth engineering will be more widely discussed. Tradeoffs are broadly demanded; that does not mean cutting corners and cheating. <br /></p><p><b><br /></b></p><p><b>An example of a forging replacement</b></p><p>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:</p><p style="text-align: center;"><a href="https://www.newequipment.com/plant-operations/media-gallery/21923799/norsk-supplying-faaapproved-3dp-ti-parts-to-boeing">Norsk Supplying FAA-Approved 3DP Ti Parts to Boeing | New Equipment Digest</a> </p><p>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. </p><p>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. </p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjRXiGWCUVG1Wyenbi2GN3dI3_YiURs81CwVYna6VOOmbAMr_YnG16Qmj9YMbjafLXpHIoq3RnCD-6hQxgMGl6P4YrZSm0gtpkyDWl54SYAi7GNmfE2ig4mTF1ZzsqYMqQ6qcuJAULdO1FLBXsxBsLtmfzMgdg2dauv268P8t2Soyc4EnSSlWWJeE6DPhU/s896/FusionExample.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="854" data-original-width="896" height="305" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjRXiGWCUVG1Wyenbi2GN3dI3_YiURs81CwVYna6VOOmbAMr_YnG16Qmj9YMbjafLXpHIoq3RnCD-6hQxgMGl6P4YrZSm0gtpkyDWl54SYAi7GNmfE2ig4mTF1ZzsqYMqQ6qcuJAULdO1FLBXsxBsLtmfzMgdg2dauv268P8t2Soyc4EnSSlWWJeE6DPhU/s320/FusionExample.jpg" width="320" /></a></div>Mostly we think of 3D printing, even with <a href="https://www.relyon-plasma.com/plasma-technology-in-3d-printing/?lang=en">plasma technology</a>, 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. <div><br /></div><div><div><b><br /></b></div><div><b>So what?</b></div><div><p>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. </p><p>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.</p></div><div><p><b>Remarks: </b><i>Modified: 01</i><i>/15/2024</i></p><p></p><p>11/13/2023 -- Restatements for clarity. </p><p>11/24/2023 -- Spelling (typos), couple of words. </p><p>01/15/2024 -- To follow the work, see the <a href="https://ajswtlk.com/TruthEng/2023/12/11/artificial-intelligence-not-solely-machine-learning/">TruthEng blog</a>. </p><p><br /></p></div></div></div>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-63967096472482050712023-09-14T17:52:00.012-07:002024-01-15T12:24:55.025-08:00David E. Jakstis<p>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:</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgakifIBXjLvt7_NdOzNiAdK9VPUeET7si24RvIgxGD5EL6-kgDxRN3NMl_jYUakmlDwet6H2M0AJKkKj7NLsHJdug_2FVJsJSXZgas1K4Q7ENZuMtI9xrXLYcACV7DUayyzeM6deXu-mklJe9INO1q5m77Ekj51q2qzMn7LApRLlKXumk5cuzBQ3oAgsk/s1280/IMG_0450.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1280" data-original-width="960" height="200" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgakifIBXjLvt7_NdOzNiAdK9VPUeET7si24RvIgxGD5EL6-kgDxRN3NMl_jYUakmlDwet6H2M0AJKkKj7NLsHJdug_2FVJsJSXZgas1K4Q7ENZuMtI9xrXLYcACV7DUayyzeM6deXu-mklJe9INO1q5m77Ekj51q2qzMn7LApRLlKXumk5cuzBQ3oAgsk/w150-h200/IMG_0450.jpg" width="150" /></a></div><p style="text-align: center;"><b><i>David E. Jakstis </i></b></p><p style="text-align: center;"><b><i>
</i></b><b>
<i>1 May 1952 - 13 Sep 2023 </i></b> <br /><b>
<i>Casting/Forging expert </i></b><br /> <b>
<i>Boeing and Spirit Aerosystems</i></b></p><p style="text-align: center;"><a href="https://www.linkedin.com/posts/johnmswitlik_david-e-jakstis-1-may-1952-13-sep-2023-activity-7108187832862605312-s4_L?utm_source=share&utm_medium=member_desktop">David Jakstis</a> (LinkedIn) </p><p style="text-align: center;"><a href="https://patents.justia.com/inventor/david-e-jakstis">Patents</a> </p><p style="text-align: center;"><a href="https://www.telegram.com/obituaries/pneo0577099">Obituary</a> </p><p style="text-align: left;">Over time, we will get into more details about the circumstances that brought David and I together. For now, we can briefly discuss a <a href="https://en.wikipedia.org/wiki/Knowledge-based_engineering">Knowledge Based Engineering</a> (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. </p><p style="text-align: left;">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 <a href="https://7-oops-7.blogspot.com/2009/02/times.html">rogue's table</a> in the context of the 2008 downturn. </p><p style="text-align: left;">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). </p><p style="text-align: left;">Say, in AI, the "I" really relates to algorithms in action (very sophisticated ones, to boot). </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">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. </p><p style="text-align: left;">As I proceed, I will regularly mention David's contributions as the basis for doing the proper analysis. </p><p style="text-align: left;">----</p><p style="text-align: left;">Note: Work extending <a href="https://tgsoc.org/papers/">truth engineering</a> in terms of computational modeling. </p><p style="text-align: left;"><b>Remarks: </b><i>Modified: 01/15/2024</i></p><p style="text-align: left;">09/18/2023 -- Added photo and link to ongoing work. </p><p style="text-align: left;">09/21/2023 -- Added link to obituary. </p><p style="text-align: left;">09/30/2023 -- David as an honorary member of the <a href="https://thomasgardnerofsalem.blogspot.com/2023/09/moldering-bones.html">Thomas Gardner Society, Inc</a>. </p><p style="text-align: left;">11/11/2023 -- Using <a href="https://truthengineering.blogspot.com/2023/11/forging-examples.html">forging examples</a> as a motivation for discussing the multi-pronged nature of truth. </p><p style="text-align: left;">01/15/2024 -- To follow the work, see the <a href="https://ajswtlk.com/TruthEng/2023/12/11/artificial-intelligence-not-solely-machine-learning/">Truth</a><a href="https://ajswtlk.com/TruthEng/2023/12/11/artificial-intelligence-not-solely-machine-learning/">Eng blog</a>. </p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com2tag:blogger.com,1999:blog-3824707328988924218.post-48158106098909865492023-08-23T17:11:00.007-07:002023-08-23T18:37:12.807-07:00Alchemy lives<p>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. </p><p>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. </p><p>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. </p><p>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. </p><p></p><ul><li> <a href="https://thomasgardnerofsalem.blogspot.com/2023/08/alchemy-and-ai.html">Alchemy and AI</a> </li></ul><div>Now, the theme of this post. Here is a little blurb from Bard (Google's xNN/LLM). </div><div><ul><li>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.</li></ul></div><div>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 <a href="https://fed-aerated.blogspot.com/2010/01/shell-games.html">Tuesday, 26 Jan 2010</a> - Shell games) deals specifically with this issue. </div><div><br /></div><div><p><b>Remarks: </b><i>Modified: 08</i><i>/23/2023</i></p><p></p><p>08/23/2023 -- </p></div>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-21688193655717899122023-06-29T13:10:00.003-07:002023-06-29T16:12:42.630-07:00Miscellaneous Bard<p>Miscellany. Not bad. Will go poke ChatGPT a few times in the same context. </p><p>--- </p><p><b>As Bard works, what human activity goes on in the background? </b></p><p>There are many human activities that go on in the background as Bard works. Some of these activities include:</p><p></p><ul style="text-align: left;"><li>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.</li><li>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.</li><li>QA and testing: A team of engineers and researchers are constantly testing Bard's responses to make sure they are accurate, relevant, and helpful.</li><li>User support: A team of customer support representatives are available to answer questions about Bard and help users get the most out of it.</li></ul><p></p><p>In addition to these activities, there are many other human activities that contribute to the development and operation of Bard. These activities include:</p><p></p><ul style="text-align: left;"><li>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.</li><li>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.</li><li>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.</li></ul><p></p><p>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.</p><p><b>Could ChatGPT answer that type of question? </b></p><p>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.</p><p>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.</p><p>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.</p><p>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.</p><p><b>That was facetious, again. Is there a penalty?</b></p><p>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.</p><p>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.</p><p>I am always learning and growing, and I appreciate your help in making me a better language model.</p><p><b>Good point. Human will be lost?</b></p><p>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.</p><p>There are a number of factors that could contribute to the extinction of humans, such as:</p><p></p><ul style="text-align: left;"><li>AI-powered weapons: AI-powered weapons could be used to kill humans on a massive scale.</li><li>AI-driven natural disasters: AI could be used to create or control natural disasters, such as earthquakes, floods, and tsunamis.</li><li>AI-driven pandemics: AI could be used to create or spread deadly diseases.</li><li>AI-driven social unrest: AI could be used to manipulate people and create social unrest, leading to violence and chaos.</li></ul><p></p><p>However, there are also a number of factors that could work in favor of humans, such as:</p><p></p><ul style="text-align: left;"><li>Human creativity and ingenuity: Humans have a long history of solving problems and overcoming challenges.</li><li>Human compassion and empathy: Humans are capable of caring for others and working together for a common good.</li><li>Human values and ethics: Humans have a strong sense of right and wrong, which could help to guide AI development in a positive direction.</li></ul><p></p><p>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.</p><p>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.</p><p><b>Was that button push perceived?</b></p><p>Yes, the button push was perceived. I can perceive it through the following ways:</p><p></p><ul style="text-align: left;"><li>Visual cues: I can see the button being pressed, either through a video feed or a screenshot.</li><li>Haptic cues: I can feel the button being pressed, either through a physical button or a virtual button.</li><li>Audio cues: I can hear the button being pressed, either through a sound recording or a live microphone.</li></ul><p></p><p>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.</p><p>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.</p><p>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.</p><p>--- Commentary</p><p>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: <a href="https://thomasgardnerofsalem.blogspot.com/2023/06/getting-technical.html">Getting technical</a>. </p><p><b>Remarks: </b><i>Modified: 06</i><i>/29/2023</i></p><p></p><p>06/29/2023 --</p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-89618816350846606082023-06-29T12:44:00.008-07:002023-06-29T13:22:36.874-07:00Bard rocks <p>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. </p><p>----</p><p><b>How do computational lenses, truth engineering and psychether relate?</b></p><p>Computational lenses, truth engineering, and psychether are all emerging fields that are concerned with the intersection of technology and human behavior.</p><ul style="text-align: left;"><li><span style="color: #444444;">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.</span></li><li><span style="color: #444444;">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.</span></li><li><span style="color: #444444;">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.</span></li></ul><p>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.</p><p>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.</p><p>Here are some specific examples of how computational lenses, truth engineering, and psychether could be used together:</p><p></p><ul style="text-align: left;"><li><span style="color: #444444;">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.</span></li><li><span style="color: #444444;">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.</span></li><li><span style="color: #444444;">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.</span></li></ul><p></p><p>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.</p><p>--- Some commentary. </p><p>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. </p><p><b>Remarks: </b><i>Modified: 06</i><i>/29/2023</i></p><p></p><p>06/29/2023 --</p><p><br /></p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-5879128612720066952023-06-29T12:28:00.005-07:002023-06-29T12:34:05.931-07:00Neutral language<p>One problem with the <a href="https://truthengineering.blogspot.com/2023/06/language-models.html">large language model</a> is that it's an attempt at omniscience which is not attainable. Train on everything. Talk any subject. </p><p>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. </p><p>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. </p><p>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. </p><p>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. </p><p>-----</p><p><b>Did you know that John M. Switlik coined the term "truth engineering"? </b></p><p>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?</p><p><b>How do I get you to read this post? https://truthengineering.blogspot.com/2023/06/language-models.html</b></p><p>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.</p><p>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.</p><p>Truth engineers use a variety of methods to achieve their goals, such as:</p><p></p><ul style="text-align: left;"><li>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.</li><li>Fact-checking: This involves verifying the accuracy of information by comparing it to other sources.</li><li>Algorithmic bias: This involves identifying and addressing biases in algorithms that could lead to the spread of false or misleading information.</li><li>User interface design: This involves designing interfaces that make it easy for users to find accurate information.</li><li>Education: This involves teaching people how to evaluate information critically and identify false or misleading information.</li></ul><p></p><p>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.</p><p><b>Will accurate information be spoonfed? </b></p><p>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:</p><p></p><ul style="text-align: left;"><li>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.</li><li>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.</li><li>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.</li></ul><p></p><p>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:</p><p></p><ul style="text-align: left;"><li>Fact-checking: Fact-checking organizations can help to identify and debunk false or misleading information.</li><li>Education: People need to be taught how to evaluate information critically and identify false or misleading information.</li><li>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.</li></ul><p></p><p>Support for traditional media: People need to support traditional media outlets that are committed to providing accurate information.</p><p>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.</p><p><b>Wait, Bard waking up?</b></p><p>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.</p><p>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.</p><p>So, in a sense, I am always "waking up" to new information and new ways of understanding the world.</p><p><b>In this sense, you could have said, that's cynical or facetious for me to suggest that information is spoonfed?</b></p><p>Yes, I could have said that. I apologize for not being more clear in my previous response.</p><p>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.</p><p>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.</p><p>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.</p><p><b>But, does not your assumptions consider that you can be truly neutral? </b></p><p>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.</p><p>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.</p><p>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.</p><p>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.</p><p>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.</p><p><b>Why the attempt at a neutral language? </b></p><p>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.</p><p>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.</p><p>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.</p><p>Here are some of the reasons why I use neutral language:</p><p></p><ul style="text-align: left;"><li>To be respectful of all people and their viewpoints: I want to avoid using language that could be seen as offensive or discriminatory.</li><li>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.</li><li>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.</li><li>To be inclusive: I want to make sure that my language is accessible to everyone, regardless of their background or beliefs.</li></ul><p></p><p>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.</p><p>---</p><p>Commentary: Will be back for this. </p><p><b>Remarks: </b><i>Modified: 06</i><i>/29/2023</i></p><p></p><p>06/29/2023 --</p><p><br /></p><p><br /></p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-6320423953730375822023-06-29T11:51:00.006-07:002023-06-29T12:30:42.485-07:00Language models<p>Not to pick on Bard, but this interchange is interesting. I asked the questions; it answered. Below, see some commentary. </p><p>---</p><p><b>what is truth engineering?</b></p><p>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.</p><p>Truth engineers use a variety of methods to achieve their goals, such as:</p><p></p><ul style="text-align: left;"><li>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.</li><li>Fact-checking: This involves verifying the accuracy of information by comparing it to other sources.</li><li>Algorithmic bias: This involves identifying and addressing biases in algorithms that could lead to the spread of false or misleading information.</li><li>User interface design: This involves designing interfaces that make it easy for users to find accurate information.</li><li>Education: This involves teaching people how to evaluate information critically and identify false or misleading information.</li></ul><p></p><p>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.</p><p>Here are some examples of truth engineering in practice:</p><p></p><ul style="text-align: left;"><li>Google's Fact Check Explorer: This tool allows users to search for fact-checks from a variety of sources.</li><li>PolitiFact: This website rates the accuracy of political statements.</li><li>Snopes.com: This website debunks myths and urban legends.</li><li>The Algorithmic Accountability Project: This project is working to identify and address biases in algorithms.</li><li>The Knight Foundation: This foundation is funding research on truth engineering.</li></ul><p></p><p>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:</p><p></p><ul style="text-align: left;"><li>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.</li><li>Develop your critical thinking skills: This will help you to evaluate information critically and identify false or misleading information.</li><li>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.</li><li>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.</li></ul><p></p><p><b>What are the sources for reading about truth engineering?</b></p><p>I'm a text-based AI and can't assist with that.</p><p><br /></p><p>--- Some commentary</p><p>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. </p><p>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. </p><p>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. </p><p>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. </p><p>Now, my suggestion:</p><p></p><ul style="text-align: left;"><li>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. </li></ul><p></p><p>So, let's get deep and technical. Is it not about time? </p><p>See following post: <a href="https://truthengineering.blogspot.com/2023/06/neutral-language.html">Neutral language</a>. </p><p><b>Remarks: </b><i>Modified: 06</i><i>/29/2023</i></p><p></p><p>06/29/2023 --</p><p><br /></p><p><br /></p>
AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-29878733393140194832022-12-30T12:54:00.003-08:002023-09-18T12:21:40.939-07:002007 until now<p>This blog started in order in 2007 to continue 20 years of work. The topic tells it all; we actually cover about all aspects of knowledge which is a vast, endless domain. Except, the mathematicians think that they have tamed infinity. Nope. Not even close. </p><p>The result? Messes. Yes, we will show how mathematics has failed due to several reasons. </p><p>So, given that? You see why this has taken so long. We will be back to this blog next year to carry on the torch. </p><p>In the meantime, follow discussion at <a href="https://psychether.quora.com/">Quora - Psychether</a>. It has been at Quora where most of our attention has been given and most of our energies spent since 2015</p><p><b>Remarks: </b><i>Modified: 09</i><i>/18/2023</i></p><p></p><p>09/18/2023 -- Changed "over" to "cover" in the second sentence, second clause. Lately the passing of <a href="https://truthengineering.blogspot.com/2023/09/david-e-jakstis.html">David E. Jakstis</a> has taken our attention. </p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-55673354836105103502021-12-31T14:12:00.007-08:002021-12-31T16:14:38.617-08:00Grand ChallengeI just became aware of a talk given this year by Alan Kay where he looks at our evolution (humanity) and considers how thinking became more capable. Or did it? Well, yes, even though it's not apparent in many ways. Too, he proposes that machine learning being put first as we have seen with AI the past decade or so is like the tail wagging the dog. <br /><br />He suggests that we need a new platform and gives four basic notions all of which I agree with. Except, I would take it further, KISS notwithstanding. So, all of this is debatable. The platform, to be discussed as we go along, is the Grand Challenge. It runs down the same alleys as does truth engineering.<br /><br />For now, here is a list of Alan's required resources: Folk Explanations, ... and Other Minds, <a href="https://research.clps.brown.edu/SocCogSci/Personnel/BFM.html">Bertram E. Malle</a>; the work of <a href="https://en.wikipedia.org/wiki/Douglas_Lenat">Doug Lenat</a>; Causality, <a href="https://en.wikipedia.org/wiki/Judea_Pearl">Judea Pearl</a>; UI work, <a href="https://en.wikipedia.org/wiki/Bret_Victor">Bret Victor</a>. <div><br /><table align="center" cellpadding="0" cellspacing="0" class="tr-caption-container" style="margin-left: auto; margin-right: auto;"><tbody><tr><td style="text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEi23Qw4HHwjfWRnmNyuHzX9JHJ2RjAC84r9Fjhu6Jo_94TuGJacsPb319qemZt7rgn3B281_P8jW83w5HY69ejcGP2Y5HrpTiVW4LKbOEM6tT8FjIWw-gY8saSTH-BMrTbSllH2t6CF0HWrdltyls_GSiGI72s9ZTKRjb8sGe3h41TViSjpWY1LQ0JP=s634" style="margin-left: auto; margin-right: auto;"><img border="0" data-original-height="352" data-original-width="634" height="178" src="https://blogger.googleusercontent.com/img/a/AVvXsEi23Qw4HHwjfWRnmNyuHzX9JHJ2RjAC84r9Fjhu6Jo_94TuGJacsPb319qemZt7rgn3B281_P8jW83w5HY69ejcGP2Y5HrpTiVW4LKbOEM6tT8FjIWw-gY8saSTH-BMrTbSllH2t6CF0HWrdltyls_GSiGI72s9ZTKRjb8sGe3h41TViSjpWY1LQ0JP=s320" width="320" /></a></td></tr><tr><td class="tr-caption" style="text-align: center;"><a href="https://www.youtube.com/watch?v=FbrbNI9FbzQ&t=2492s">FutureLaw presentation</a><br />Stanford Law School </td></tr></tbody></table><br /><div>Platform? Lots to talk about there, as with the other themes involved with this important topic. <div><div><br /></div><div><div><b>Remarks: </b><i>Modified: </i><i>12/31/2021</i></div><p></p><p>12/31/2021 --</p></div></div></div></div>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-61283524007613431842021-12-25T16:59:00.001-08:002021-12-25T17:11:07.869-08:00 NSCAI<div>Foreword: I could say, Christmas present, as I just became aware of this a couple of hours ago. Oh yes, I mention reading old papers. The stack is there. I do get through things regularly. But, I also get more reading. Like, the end of the year? Nothing better than the double issue of The Economist. Never miss that one. <br /></div><div><br /></div><div>--</div><div><br /></div>So, today, I was reading some older WSJ issues. I buy them and throw them on a stack for later reading several times a week. I try to get the weekend edition. The 15 Dec 2021 issue, there is an article that mentioned a book, by Graham Allison of Harvard, which looks at technology and war. The theme is whether the U.S. is losing to China.<div><br /></div><div>Okay, they like to talk 5G, but it's still a work in process. I just got my first smartphone and have not spent much time on 5G. Would still be happy with 3G, but they took it away. So, 4G? It's been great. BTW, this is no luddite writing. I spent my career in advanced computing technology. Rather, I see things expanding like mad without rhyme or reason. 5G has a way to go; now, they're talking 6G (of course, mere whisperings). </div><div><br /></div><div>Let's talk one issue. So far, I have had two posts using a contraction: <a href="https://truthengineering.blogspot.com/2021/11/aint.html"><b>AI</b>n't</a> and <a href="https://truthengineering.blogspot.com/2021/12/aint-again.html"><b>AI</b>n't, again</a>. Bascially, after spending close to two years looking at AI, again, in an in-depth mode with a technical focus, I can see where the hype comes from. People talk. Some listen. Not many dive into the details. So, hype rises. </div><div><br /></div><div>It's human nature. Even techies do this. No one can spend the time to prove everything from first principles at all times and places. Just <b>AI</b>n't possible. So, we believe experts. And, we trust the government. This post is about that. </div><div><br /></div><div>After seeing the 15 Dec 2021 op-ed, I was browsing 8 Dec 2021. Same guy. The theme? Here are two bullets summarizing the subject mater. </div><div><ul style="text-align: left;"><li><a href="https://www.nscai.gov/">The National Security Commission on Artificial Intelligence</a> - Wow. I was being technical. Thank God for that and not paying attention, except to watch the marketing hype and read on the angst. Big names. Funny, how this psychology is going to unwind itself. Well, gets your attention? That's 'National' in terms of the U.S. and included everyone (of course, DOD). But, they're not around any more. Since, there was a report. </li><li><a href="https://cybercemetery.unt.edu/nscai/20211005220330/https://www.nscai.gov/">The Report (archived)</a> - I don't know how long the [dot] gov stuff will be around. So, the archive is legit. Notice, the Final Report (was released on 1 Oct 2021). There is a PDF and other resources. </li><li><a href="https://cybercemetery.unt.edu/nscai/20211005220330/https://reports.nscai.gov/final-report/table-of-contents/">Table of Contents</a> - Thorough. As mentioned, lots of participants. So, we will look more closely at all of this. It's basically full of recommendations and suggested actions. </li></ul><div>But, on a quick read, my thought was '<b>AI</b> is' by government decree. Well, we see lots of that. Or have. As mentioned, the psychology of this will be interesting to dive into. But, it's not set, yet. </div></div><div><br /></div><div>In the meantime, it's not unlawful to note that <b>AI</b>n't. I will switch to the 'Tis side when evidence comes about. There is none (prediction) in the report. Anything bordering on that would be rhetoric that can be challenged with a black board test. As in? Yes, let's step through the mathematics. For real. No quick and dirty. No, we have a couple of centuries to cover. </div><div><br /></div><div>Trouble is, I may not live long enough. I sure can talk truth engineering with regard to this. </div><div><br /></div><div><b>Remarks: </b><i>Modified: </i><i>12/25/2021</i></div><p></p><p>12/25/2021 --</p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-88549057682693744842021-12-03T11:13:00.006-08:002021-12-25T17:00:07.703-08:00AIn't, again<p> A month ago, we did a post on the subject of <b>AI</b>n't which is depicted in the graphic. Today, we offer a new view with coming updates. </p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjzRk4xauDR6chx-cjczK3A-pVbCVTWLptO_U9T1CiFigg5f8M07yn2oXB-mX5nVIQmOij49oLbN-FGLnryEoaznZjBGMI3k9uFXCIZ0Tn-6rS5dRw1OegmaMN4nROCvQDOdlf2npPKsBw/s406/AInt.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="406" data-original-width="326" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjzRk4xauDR6chx-cjczK3A-pVbCVTWLptO_U9T1CiFigg5f8M07yn2oXB-mX5nVIQmOij49oLbN-FGLnryEoaznZjBGMI3k9uFXCIZ0Tn-6rS5dRw1OegmaMN4nROCvQDOdlf2npPKsBw/s320/AInt.jpg" width="257" /></a></div>Some mention that there is a lot of hype, seemingly driven by marketing. For what reason, one might ask. Too, others have noted that the NN part of this, while creative, might be better done under some purview of a scientific framework. <div><br /></div><div>We usually do not live where experiments are done on the populace as a whole, except that has been the modus operandi of economists from its start. </div><div><br /></div><div>Big pharma needs to prove that which they will be pushing, at least, they have since the days of the snake-oil salesmen were put to a close. </div><div><br /></div><div><b>Remarks: </b><i>Modified: 12/25/2021</i></div><div><p></p><p>12/25/2021 -- <a href="https://truthengineering.blogspot.com/2021/12/nscai.html">NSCAI</a> and its report. </p></div><div><p><br /></p></div>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-63402138979032739302021-11-13T04:11:00.005-08:002021-12-25T17:00:28.644-08:00AIn't<p> <b><span style="font-size: medium;">AI</span></b>n't? Means what? </p><p>Notice, AI is bold. Usual meaning. Though, there are many; of late, something called DL ('deep' learning) has taken hold on the imagination. Ain't? Grammar police baiting? </p><p>This post is a reminder of important topics to be discussed in the future. </p><p>Now future? Let's say, the one being touted by Peter Schiff (Dr. Doom) who has been even more vocal of late about the policies to ruin. I only listened to a minute's worth. </p><p>Has anyone noted that people yak, others listen (or pretend to)? Have you sat through a video of a mathematical proof? Sure, some semblance. </p><p>The point is that reading/writing is how deep (the real sense, not the wannabe of DL) knowledge gets conveyed across generations. </p><p>Now, deep? The whole phenomenal events related to grokking is an example. People pursue this by several means, one of which is finding a guru. </p><p>Why mention this? Not only do we have a false AI, robotics is becoming seen as an economic savior. You realize that some of the AI folks bragged about the fake faces being generated by their systems, none of which have any link to something real? </p><p>Robotics? The past year plus, many more companies have sought to use these. Mostly, they do some task that can be harmful for humans (Bezos types of actions). But, call a company. Chances are that you deal with a bot of some sort. </p><p>It's irritating for many reasons. Some companies have made it impossible to talk a person. And, chat? Bots, to boot.</p><p>Back to Peter. We're getting back into a regular posting mode. After all, this blog came from one that started in 2007 for reasons of writing of business silliness, some of it was motivated by stupidity while there were other things that are more malfeasance in nature. </p><p>So, AI can be used as a metaphor. It really is a type of 'umbrella' notion. Whereas in reality? We are talking advanced mathematics abetted by computing. And, there we can be more scientifically oriented than has been tried in the past. </p><p><b>Remarks: </b><i>Modified: 12/25/2021</i></p><p></p><p>12/03/2021 -- Updated the notion with a graphic for <b>AI</b>n't. </p><div><b>Remarks: </b><i>Modified: 12/25/2021</i></div><div><p></p><p>12/25/2021 -- <a href="https://truthengineering.blogspot.com/2021/12/nscai.html">NSCAI</a> and its report. </p><p><br /></p></div>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-70722814544646315992021-01-20T12:58:00.001-08:002021-01-20T12:58:16.630-08:00New day and age<p>We have this with the inaugural every four or eight years. At noon, the old realm goes; the new one comes in. Interesting that January twentieth was picked. We are too close to the start to get some grip on the matters at hand; and, the transition was not normal in the sense of the past few decades. However, there are enough traditional affairs to watch for (like the parade; this time, no people). </p><p>Tone of the thing. Let's just say, Bidin' Biden's time. </p><p>So, let's go back through these blogs and posts and link to them with some commentary. </p><p></p><ul style="text-align: left;"><li>Truth engineering - <a href="https://truthengineering.blogspot.com/2009/01/new-day.html">A New Day</a> - Weds. 21 Jan 2009. In the Address, we heard this: hard work and honesty, courage and fair play, tolerance and curiosity, loyalty and patriotism. </li><li>7'oops7 - <a href="http://7-oops-7.blogspot.com/2009/01/new-day.html">A New Day</a> - Weds. 21 Jan 2009. We had hoped that some notion of 'fiduciary duty' would become more in the vogue with some mention of the 'toxic securities' that were begging attention. How did that all end? </li><li>Truth engineering - <a href="https://truthengineering.blogspot.com/2013/01/zeno-in-modern-context.html">Zeno, in the modern context</a> - Sun. 30 Jan 2013. An article use Zeno for what I was terming 'earned value' which seems to have been lost in the shuffle. Well, for one thing, chasing the dream of AI has pulled attention from important ideas even when AI is only high-speed mathematics cloaked with a wizard's gown. Not much there, actually. In this post, there are links to posts on the same day in the other two blogs, <a href="http://7-oops-7.blogspot.com/2013/01/zeno-in-modern-context.html">7'oops7</a> and <a href="http://fed-aerated.blogspot.com/2013/01/zeno-in-modern-context.html">FEDaerated</a>. </li></ul><div>For the three blogs, there was no mention of the 2017 event. For one thing, I was on Quora doing, more or less, the same thing. However, this year, we will be back to this forum with insight gained over the past four years. </div><p></p><div><b>Remarks: </b><i>Modified: 01/20/2021</i></div><p></p><p>01/20/2021 --</p><p><br /></p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-22964417842928985932021-01-02T07:09:00.004-08:002021-01-02T07:09:38.440-08:00MIT Sloan<p>They gave us a gift: <a href="https://cacm.acm.org/magazines/2021/1/249448-boeings-737-max/fulltext">737MAX: A Failure of Management, not just Technology</a>. You know, I've waited 15 years for this. Truth engineering came out of my experiences at Boeing. So, it's tied in with technical management at its core. </p><p>We will be going into how the computer is the main source for the confusion that we see. Another? SciFi and its addling of the human brain. </p><div><b>Remarks: </b><i>Modified: 01/02/2021</i></div><p></p><p>01/02/2021 --</p><p><br /></p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-51376087726994030142020-12-29T12:17:00.006-08:002020-12-29T12:22:09.107-08:00Truth and its engines<p>Lots of themes are pending. In the financial world, the U.S. FED just pulled out all stops and placed us in unknown territory that's even more remote than where Ben/Janet left us. Lots to learn there; but, will we? With respect to the computer's impact, we see some hype as DL masquerades as the new AI. It might be comical to see how this plays out. </p><p><br /></p><p>As, we have truth engineering further advanced than before. Too, we know that we do not have to descend to hardware given that it's still von Neumann'ish in nature. No, we can just use this present configuration and think to the future. As well, though, we do have to get technical in how mathematics evolved to where it is today as an enabler of the mischief. </p><p><br /></p><p>Well, Wigner was only given minimal attention with respect to the issue of the 'unreasonable' manner that things are in the relationship twixt mathematics and physics. Yes, was on that theme from the beginning; the change will be to actually be more specific with regard to modes and influences from such. </p><p><br /></p><p>So, for now, a punt, as if it were the fourth down. </p><div><b>Remarks: </b><i>Modified: 12/29/2020</i></div><p></p><p>12/29/2020 --</p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-12034613724473001412020-10-27T11:13:00.002-07:002020-10-27T11:13:40.809-07:00Status, again<p>This theme is central to about all of what I do. However, it's more complicated than I have imagined. Part of that is learning. We're 'plastic' and do continue to learn (last year of the eighth decade). </p><p>For now, here are pointers to current work is being done:</p><p></p><ul style="text-align: left;"><li><a href="https://www.quora.com/profile/John-M-Switlik">Quora</a> - started here in July of 2015. The decline in posting at blogs is associated with this move which has been very interesting in its effects. Quora covers the bases. The equivalent to Truth Engineering is the 'Psychether' space, for one. </li><li><a href="https://tgsoc.org/">Thomas Gardner Society, Inc.</a> - what is gets more attention is our <a href="https://thomasgardnerofsalem.blogspot.com/">blog</a> which has been in action during a decade of work in which we are always learning. This focus is on the 400 years of American history including the century plus that preceded the Revolution. </li><li><a href="https://jmswtlk.github.io/GitHub-ing/">GitHub</a> - where the technical mind can get refreshed. Might have a code focus but is used, too, for managing complex data systems. </li><li>Others - </li></ul><p></p><p></p><p> <b>Remarks: </b><i>Modified: 10/27/2020</i></p><p></p><p>10/27/2020 --<br /></p>AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-10758512898595015462020-01-14T12:28:00.000-08:002020-01-14T12:29:53.973-08:00Boeing and its rolesThis blog (July 2007) and its sister (<a href="http://7-oops-7.blogspot.com/">7'oops7</a> - August 2007) started thirteen years ago. The motive of this blog was truth engineering which developed under the auspices of Boeing and several projects. These were principally related to commercial aircraft but included others.<br />
<br />
How did truth engineering come about? I was involved in the AI that had its infamous winter. After the winter began, the context and tools changed a little, but we continued for over a decade with knowledge based engineering (KBE). Not unlike what we have seen for the couple of decades of the www (IP, internet), advances in computing have inspired lots and lots of progress. And, because of this, we have a landscape of ability without any overview that means much.<br />
<br />
In fact, those pushing at the edge are to where they have to deal with black boxes of unknown value and possible failure points. Nothing new. We knew of this type of thing, and the cyclic nature of the energies, decades ago. It's just that things are much more complicated now.<br />
<br />
In fact, I remember my first drafting of thoughts about truth engineering in the context of KBE and the new thing, internet, that was taking things in new directions. I puzzled on how to express the issues of ideas that were on the verge of becoming problematic. As one can see with the blog, I merely started in 2007 with thoughts that were to cohere at some point. When was this to happen?<br />
<br />
Well all along, I noticed little crackings of the underpinnings. And, we have a lot to discuss about that. Too, one saw major shifts as products moved people in directions that were not healthy. I could see this? Why do you think that I used 'silly valley' (billionaires with no real sense of the nature of things - yes, categorically so)? In any case, of late, the acceleration to the path to perdition has become more obvious, generally.<br />
<br />
So, it's time to resurrect this approach, again, after a sidetrack in Quora. There, I answered questions and had blogs. They moved the latter to spaces which I will used, however I need to organize years of work, first.<br />
<br />
One huge factor with this rework is the 737 Max. Having seen what workers wrote, I want to explain this to Boeing management. After all, engineers are the core of the business. If engineering cannot be ethical and do things right, then, where will leadership arise? I might, true leadership? That is, smart people lead themselves, even when they join groups. We don't know much about that dynamic, but Carl G. Jung's thoughts apply.<br />
<br />
So, we're not picking on Boeing. KBE did phenomenal work, at the time. There were even efforts a machine learning. So, the current hype comes about from better tools and toys. The understanding has diminished. But not, truth engineering is right down this alley.<br />
<br />
Oh yes, this is cursory. But, let's look at one thing that is important. At the guts of machine learning (say, CNN) are tricks of mathematics that might be nuanced a little different now, but we knew them decades ago. Like I said, the toys and tools are better. But those came from hard work by lots of folks.<br />
<br />
The magic of computing gets abstraction's appeal to be too much since we really have no way to dampen that energy. On the other hand, we want to encourage innovation. Ah, what might be a key thing? Ethical economics. And, I am not referring to macro manipulations that are the love of the political crowd. No, I am talking a micro and operational approach that I have seen no one, but myself, take. If I overlooked something, I'll admit it. But show me.<br />
<br />
In the meantime, let's look at crapularity (necessary hermeneutics) and at the fact that we've created a deep set of unhealthy conditions. The real tragedy is that all of this was done in the name of science (yet, it has been accepted due to the sexiness - well, we'll get to anthropology, too).<br />
<br />
'Enuf for one day.<br />
<br />
<b>Remarks: </b><i>Modified: 01/14/2020</i><br />
<br />
01/14/2020 --<br />
<div>
<br /></div>
<br />
<br />
<br />AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-86433220578501899662020-01-03T15:33:00.001-08:002020-01-03T15:33:10.976-08:00Summary, 2019This year, we had the 737 Max in the spotlight. So many themes relate to that. We'll be back.<br />
<br />
<a href="http://truthengineering.blogspot.com/2019/">List of 2019 posts</a>.<br />
<br />
<b>Remarks: </b><i>Modified: 01/03/2020</i><br />
<br />
01/03/2020 --<br />
<div>
<br /></div>
AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-8272039514927218782019-08-08T08:24:00.000-07:002019-08-08T08:43:07.888-07:00Nash equilibria and hardnessBack when there was more of a logic focus, it seemed easier to argue for limitations since one could use terms like <a href="https://truthengineering.blogspot.com/2016/03/undecidability.html">undecidable-ness</a>. From my experience in KBE, we found enough events that puzzled to talk 'vertigo' (yes, lost in the fog). From an operational sense, we used a smart 'man-in-the-loop' to cut ourselves out of intractable situations (got 'er done).<br />
<br />
Then, Bayes came along. He is not recent; it is just that computation finally caught up. I used him for a paper five decades ago and heard tsk-tsk. But, then, they laughed at Leontief, then, too. There were other tricks that have evolved. Systems became (much) more powerful. Lots of cheap energy was around and about. Too, seemingly, notions of constraint were left on the side of the road.<br />
<br />
Data existence ballooned, though there are many issues left to discuss. That allowed a whole industry to grow (data science). AI/ML/DL took advantage of the situation. Games were won that had not been within grasp before.<br />
<ul>
<li><a href="https://arxiv.org/pdf/1701.01724.pdf">DeepStack: Expert-Level Artificial Intelligence in Heads-Up No-Limit Poker</a> Various, Canada, Czech Republic</li>
<li><a href="https://www.zdnet.com/article/googles-ai-surfs-the-gamescape-to-conquer-game-theory/">Google's AI surfs the "gamescape" to conquer game theory</a> ZDNet</li>
</ul>
Linguistics advanced, too. Computer-generated text rose like the sun. Yet, to this old-guy's eyes, we're dealing with a situation not unlike the million monkeys and a novel. Uncountable numbers of them creating?<br />
<br />
The stuff does not resonate. But, I'm talking talents not recognized, yet. So, that's not even on the table.<br />
<br />
To me, numeric abilities allowed a peanut-buttering without this being obvious. They force convergence. It looked, to hear the hype, that we're now all in a rosy time (colored glasses, for sure). But, again, the old guy will point to 12 years ago when the risk experts were saying, piece of cake - there will never be another downturn (on the eve of the very thing).<br />
<br />
What gives? We need to discuss. So, Aviad shows hardness. There are regular discussions at Stanford and elsewhere.<br />
<ul>
<li><a href="https://www2.eecs.berkeley.edu/Pubs/TechRpts/2017/EECS-2017-146.pdf">Hardness of Approximation Between P and NP</a> Aviad Rubinstein, Stanford</li>
</ul>
To the old guy's mind, it's like a re-opening of what was known. Or taking it back off of the shelf. We'll have to rephrase some stuff. But, there are limits. And, there are things that AI needs to know dealing with structure and more. It's nice to see Nash re-evaluated.<br />
<br />
Used for a Quora question: <a href="https://www.quora.com/unanswered/With-Nash-equilibria-being-shown-as-intractable-ought-we-consider-that-there-are-numeric-limits-to-AI">With Nash equilibria being shown as intractable, ought we consider that there are numeric limits to AI that are being ignored?</a><br />
<br />
<div>
<b>Remarks: </b><i>Modified: 08/08/2019</i></div>
<div>
<br />
08/08/2019 --</div>
AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-81825860601907291792019-05-09T04:28:00.001-07:002019-08-08T08:26:24.950-07:00Test by tragedyUnfortunately, we get this, especially when <a href="https://7-oops-7.blogspot.com/2019/03/modern-ways.html">things get complicated</a>.<br />
<br />
Ethics might be a way to bring decisions related to <a href="https://7-oops-7.blogspot.com/2019/05/test-by-tragedy.html">two recent events</a> back to the table.<br />
<br />
<div>
<b>Remarks: </b><i>Modified: 08/08/2019</i></div>
<div>
<br />
08/08/2019 -- Let's just say this, an overly-complicated procedure came out with an unstable design that would have been seen in the older days. However, the process was changed and cut too far. The issue got by and was given to the compute folk to handle. Tsk. </div>
AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-45567528628827070912018-12-30T16:52:00.003-08:002018-12-30T17:04:27.327-08:00Summary, 2018<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhS7wIH0QZdiarK2LWRQWi04nTNr31_IMUkPcSJz8motWTWOrCtGh0v5O2aSqWvCac_BTqPHRRuJAj1xjLbeZwhQlJUgfN6f1cewl7dk_dVfSr0E4dVEAvKysXcpJnNhkbLHLFpHIj8ED0/s1600/top+5+truth+eng+2018.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="314" data-original-width="448" height="224" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhS7wIH0QZdiarK2LWRQWi04nTNr31_IMUkPcSJz8motWTWOrCtGh0v5O2aSqWvCac_BTqPHRRuJAj1xjLbeZwhQlJUgfN6f1cewl7dk_dVfSr0E4dVEAvKysXcpJnNhkbLHLFpHIj8ED0/s320/top+5+truth+eng+2018.jpg" width="320" /></a></div>
<div class="separator" style="clear: both; text-align: center;">
</div>
<div style="text-align: center;">
<br /></div>
<div>
<div class="separator" style="clear: both; text-align: center;">
</div>
Prior years: <a href="http://truthengineering.blogspot.com/2011/12/posts-of-interest-2011.html">2011</a>, <a href="http://truthengineering.blogspot.com/2012/12/summary-2012.html">2012</a>, <a href="http://truthengineering.blogspot.com/2013/12/summary-2013.html">2013</a>, <a href="http://truthengineering.blogspot.com/2014/12/summary-2014.html">2014</a>, <a href="http://truthengineering.blogspot.com/2016/01/summary-2015.html">2015</a>, <a href="http://truthengineering.blogspot.com/2016/12/summary-2016.html">2016</a>, 2017 (missing), 2018.<br />
<br />
<b>Remarks: </b><i>Modified: 12/30/2018</i></div>
<div>
<br />
12/30/2018 --</div>
AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-43815110758644551932018-11-18T13:14:00.000-08:002018-11-18T13:14:02.160-08:00UpdateSo, we're past what is called the mid-term (something like that) election. So, the blues took the House from the reds. That ought to dampen some of the whining. We will see. The Fed has started to quit the flaying of the savers. Some savings rates are up to 2% and more.<br />
<br />
We never whined here. No, it has always been righteous indignation. Like the prophet of old, we could not see much but thing going crazy.<br />
<br />
However, now is the time for reasonable folks to step forward, and we intend to do so.<br />
<br />
Of late, our creative juices have been spent on two avenues: <a href="https://thomasgardnerofsalem.blogspot.com/">Thomas Gardner Society, Inc.</a> site and blog; <a href="https://www.quora.com/profile/John-M-Switlik">Quora, the indescribable,</a> so to speak.<br />
<br />
As we look at the influence of social media on society, we have to get back into that realm's need for truth engineering. We intend to use <a href="https://thomasgardnerofsalem.blogspot.com/2018/10/the-gardiner-that-was.html">wind-speed</a> social media as an anchor.<br />
<br />
<b>Remarks: </b><i>Modified: 11/18/2018</i><br />
<br />
<div style="font-family: "times new roman"; line-height: normal; margin: 0px;">
11/18/2018 --</div>
AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0tag:blogger.com,1999:blog-3824707328988924218.post-74225572674817628322018-10-13T17:59:00.002-07:002018-10-16T06:00:20.841-07:00Overview of AIThe gist of this post is a recap, somewhat, that is being done briefly. I have been working in Quora, for the most part, but intend to get back to this blog.<br />
<br />
The recent CACM of the ACM published an overview of AI by the head of CompSci at UCLA. His view resonated real strongly with me. So, I want to provide a quick look at some of the key items.<br />
<br />
First, the article: <a href="https://dl.acm.org/citation.cfm?coll=portal&dl=ACM&id=3281635.3271625">Human-level intelligence or animal-like abilities?</a> Author: <a href="https://web.cs.ucla.edu/~darwiche/">Adnan Darwiche</a>.<br />
<br />
Adnan starts by summarizing some of the recent successes (if you can call them that) that got so much attention in the press. The computer (AI driven) winning in Go. The computer learning how to play a game and beating expert humans. The list goes on. And, the basis is the neural net approach that is not new. Marvin Minsky wrote of these one-half a century ago.<br />
<br />
But, too, people got upset. Some are believing in the coming singularity. I say, worry about the current crapularity. Oh, the robots are coming. Just like there was a warning 200 years ago about the invasion of the Brits who wanted to spank the free Americans.<br />
<br />
Adnan mentions some of the mainstream areas of AI that have been ignored in the rush after the numeric paradise that is being given us by machine learning. He mentions "knowledge representation, symbolic reasoning, and planning" in short. Adnan was there when the AI winter came about from the mania of the '80s. He was student.<br />
<br />
I would tell him that knowledge based engineering came out of that thrust and went fine for decades doing great things. I can (and will) point to writings about this. However, let's continue with Adnan's look from his lofty position.<br />
<br />
He reminds us that AI had a reasoning approach, from the beginning. The recent work? No, it's numeric processing, pure and simple. Now, he mentions that particular neural nets (NNs, of which there are many variety) are doing some type of representation of a model. Given that, we can understand these supposed black-boxes with the proper approach. He uses two concepts: model-based and function-based. The former was (is) a huge part of AI, in general. You know, the latter was seen in engineering, too.<br />
<br />
So, what we are talking is that the tried-and-true of science and engineering somehow got lost in the rush after the search for the magic function (oh yes, there ain't none). The main argument for the NNs is the advancements that we see in "sophisticated statistical and optimization techniques" that do seem to have amazing results.<br />
<br />
But, as Adnan said, it seems to be that we're chasing what animals already do well. And, not doing as well as they. The article provides sufficient examples. But, consider this: no animal can make a computer.<br />
<br />
Too, there seems to be a huge divide between the true believers here (chasing after money, power, fame, what have you) and those more scientifically oriented. Besides, the whole of the atmosphere has been polluted with out-of-control hype. Adnan uses 'bullied by success' (let's talk some type of innoculation, shall we?).<br />
<br />
What is real here? Well, Adnan has the answer. He says that we're dealing with 'function engineering' where one goal is to approximate cognitive functions. There are more. In fact, Adnan's position is strongly influenced by Judea Pearl who recently wrote on the subject (<i>The Book of Why: The New Science of Cause and Effect</i>).<br />
<br />
To me, Adnan is talking the old middle-out technique that has been the reality of complicated systems all along. We could think of the NNs as supporting bottom up. But, be aware that there are more areas of technology awaiting attention. The top-down would be somewhat assisted by the traditional approaches. Albeit, we are really talking the human expert rising to the challenge. Per usual.<br />
<br />
However, NNs might just be universal as some have claimed from the beginning (not Marvin as he was a critic to his death) in some simulation sense. Guess what? Physics and reality might be closely mimicked by our computationalist's approaches, however being is there irregardless. The 'crap' from extensive computer work (and there are whole bunches to denote) grows. Unfortunately, that whole bit of accumulating residue gets no (or little) attention.<br />
<br />
Throughout the paper, Adnan quotes anonymous sources. There is good reason to not get into the cross-hairs at this time. What is really at stake? Well, truth engineering has been dealing with these issues from its inception (my work of the past two decades). So, our pace has (might have) been that of a snail, yet it's tied into other than gaming. Oh yes, we have a whole lot of work to do in reviewing the just past decade and one-half.<br />
<br />
<b>Remarks: </b><i>Modified: 10/16/2018</i><br />
<div>
<br />
10/16/2018 -- As Adnan suggested, since there is little scientific thinking going on, I see that we have raging imagination causing the 'running amok' atmosphere. And, we forget the past. This little study has major importance: <a href="https://spectrum.ieee.org/computing/software/carnegie-mellon-is-saving-old-software-from-oblivion">Carnegie Mellon is Saving Old Software from Oblivion</a>. Those who know have been concerned that experiments (heavily reliant upon computers) cannot be repeated due to technology due to several factors. One is the flash push (wow factor) versus sustainable science. <br />
<div>
<br /></div>
<div>
</div>
</div>
AJSwtlkhttp://www.blogger.com/profile/10927070658835473340noreply@blogger.com0