21 February 2024

Trump compares himself to murdered opposition leader Navalny

Look, folks, I'm pretty weary of even talking about the former guy. Like Simon Rosenberg, I endorse the concept of "work more, worry less," which includes carp less. But this comparison by this utterly narcissistic toad of himself to murdered opposition leader in Russia Aleksei Navalny is a new low. What a total POS. Sorry, but had to say it. 

20 February 2024

Favorite fonts, both "As" from an "A" country, an obscure rant

Some few of my farflung correspondents may share my interest in typefaces (commonly nowadays called "fonts," although the technical term is typeface). I have a deep and abiding loathing for both Times New Roman and Arial, probably the two most common computer "printer fonts" (except on Apple, where real Helvetica, rather than knockoff Arial, is standard). I regard both as lifeless and ugly, each in its own uniquely awful way (Helvetica is only slightly better, associated as it is with the 1960s brutalist esthetic). I would dearly love to see all three consigned to the scrap heap of typographic history. TNR was literally designed to make more text fit in a newspaper column, and it sacrifices all proportion and even legibility for that end. The less said about the deliberately minimal and ugly Arial the better.

So here's something I'm pretty sure is not a coincidence. Among the newer font families I've come across, there are two, one a classic serif and the other a unique "baroque humanist" semi-serif, that I really like and use whenever I can, in their respective milieus. These are classic serif Alegreya, designed by Juan Pablo del Peral, and Asul, designed by Mariela Monsalve, after unnamed typefaces used in the 1920s. Both were designed in the early 2010s in Argentina. Alegreya is a sort of modernized and more legible version of Garamond, or possibly Bembo; whereas Asul is really unique; combining the best of the virtues of sans serif fonts like Humanist and Trebuchet with real proportion and a hint of serif. It's beautiful and very legible.

To see and read a bit about each:

Asul is free from Google fonts. Alegreya is also readily available free, but you have to look for it. Just google the name if you're interested. There are standard, medium, real italic (not just algorithmically slanted italics, which are a travesty and should never be used in anything where graphic beauty is important), and also bold and extra bold standard and italic versions. In a world where beauty is often shortchanged, I would take a little but genuine pleasure if Alegreya were to supplant Times New Roman as the standard serif font and Asul were to replace Arial... there really is no justification or need for purely sans serif fonts anywhere. We are not robots, why should we use robotic typefaces?

I say all this in the full realization that most people almost literally could not care less.


16 February 2024

Navalny murdered. Not in America!

So it is now nearly certain that the brutal dictator Vladimir Putin had his only real political opponent, Alexei Navalny, murdered in prison. My reaction is that if anyone believes that if Trump is given the Oval Office again, his enemies won't start being imprisoned, then some even killed, then you don't understand the narcissistic dictator personality, because it could not be clearer that that's the direction he would go. We simply cannot let that happen in our country.

Just watch. In the next day or two, Trump will do a "tell." Something. He'll show that he admires Putin, including having Navalny murdered. Because that is exactly what he wants to be able to do to his enemies. And, folks, if you're reading this, chances are you are one of his enemies. Probably not high profile enough to be a victim of a purge, but if you're saying to yourself, How bad could it get? How could it affect me, really? ... you are just not understanding how this works. Don't you think middle class Germans in 1933 said the same thing? Even some Jews, believing that civilization had gone beyond the Pogroms, probably said that to themselves. And they did not escape the horrible consequences of allowing a brutal dictator to take power, not even the non-Jews. We are warned.

I have one or two friends who so distrust the "deep state" (or whatever the F*k) that they trust Putin more than our own government. But I have lost all patience. The die is cast. We fight and defeat the would be autocrat or we face the consequences, and no friendship, no comfortable middle class isolation, no going along to get along will protect us.

15 February 2024

Elaborate Football Analogy for MAGA


The equal right of all men to the use of land is as clear as their equal right to breathe the air—it is a right proclaimed by the fact of their existence. For we cannot suppose that some men have a right to be in this world, and others no right.
—Henry George

GPT "remembers" Mackinder's Heartland theory for me (I'd forgotten his name)

Another in a series of conversations with LLMs Gemini and/or GPT.


There was, I believe, a British historian (not Toynbee), who conceived of the crucial importance of "central place" geographically in the power politics of national supremacy. In this theory, the British, and subsequently the US, utilized an alternative strategy of "containment" through (primarily) naval power, to overcome the inherent disadvantage of peripheral location, and to exercise dominance over more favorably situated "powers," such as, in turn or concurrently, Germany, Russia and/or China. 1. Please infer who it was I am talking about and describe his principal works (I genuinely can't recall; this isn't a test); and 2. Please comment on how technological advance since the early 20th century has to some extent falsified this concept, and made geographical positioning less critical (if that is, in fact, the case according to current geopolitical thinking).



The historian you're referring to sounds like Halford Mackinder and his Heartland Theory. Mackinder was a British geographer and one of the founding figures of both geopolitics and geostrategy. His ideas have had a profound influence on the strategic thinking of nations throughout the 20th century and beyond.

Halford Mackinder and His Principal Works

Halford Mackinder proposed the Heartland Theory in a paper presented to the Royal Geographical Society in 1904 titled "The Geographical Pivot of History." This theory was later expanded in his book "Democratic Ideals and Reality: A Study in the Politics of Reconstruction," published in 1919. Mackinder's theory posits that the control of Eastern Europe (the "Heartland") was key to global domination. He argued that the Heartland was naturally impregnable due to its inaccessibility and could be the base from which to project power globally.

His famous dictum, "Who rules East Europe commands the Heartland; who rules the Heartland commands the World-Island; who rules the World-Island commands the world," encapsulates the essence of his theory. Mackinder's model was a challenge to the then-prevailing British naval hegemony, suggesting that terrestrial power could eventually overmatch sea power, especially if a single power managed to dominate the Heartland.

The Impact of Technological Advances on Geopolitical Strategy

Since the early 20th century, technological advances have indeed altered the strategic importance of geographical positioning, though not entirely negating Mackinder's insights. Several developments illustrate this evolution:

  1. Nuclear Weapons: The advent of nuclear weapons has made sheer territorial control less decisive in global power terms, as even geographically peripheral or smaller nations can wield outsized strategic threats.

  2. Air Power and Missiles: The development of long-range air power and missile technology, including ICBMs and cruise missiles, has reduced the security provided by geographical barriers. Powers can project military force directly over such barriers, diminishing the strategic value of controlling central landmasses.

  3. Space Technology: Satellites and space-based assets have transformed intelligence, communications, and navigation, enabling global surveillance and coordination beyond the constraints of geography.

  4. Cyberspace and Information Warfare: The rise of cyberspace as a domain of warfare and influence operations has further abstracted power from physical geography. Nations can influence others, interfere in elections, and disrupt infrastructure without traditional physical presence.

  5. Economic Globalization and Supply Chains: Globalization has intertwined the economies of nations, making economic power and resilience as crucial as geographical position. Supply chain vulnerabilities, as highlighted during crises like the COVID-19 pandemic, can exert a significant impact on national security.

However, geography remains a critical factor in geopolitical strategy. For instance, the importance of chokepoints like the Strait of Hormuz for oil transport or the significance of maritime routes in the South China Sea underscores continuing geographical considerations. Furthermore, the rise of China and its Belt and Road Initiative can be seen as an attempt to reshape global geopolitics not just through maritime power but also through terrestrial influence across Eurasia, which echoes Mackinder's Heartland concept.

In summary, while technological advancements have mitigated some of the strategic disadvantages of peripheral geographic positions and challenged some aspects of Mackinder's Heartland Theory, geography continues to play a crucial role in global power dynamics. The interplay between technological capabilities and geographical realities remains a central theme in contemporary geopolitical strategy.


GPT on Mars Colonization

I have taken to having frequent conversations with both Gemini (Google's AI Large Language Model) and ChatGPT. They are more similar than different. My interactions with them are driven more by curiosity than practicality. From time to time, I intend to share with my Farflung Correspondents some of these interactions, through the modern miracle of cutting and pasting. Probably a good time to reiterate that if you would prefer to be removed from my Farflungs' list, you need only ask and it shall be done, no questions asked.

Thank you.

Here's one on my skepticism of the likely near-future human colonization of Mars. I suspect that had I asked the question in a slightly different way, I would've gotten a quite different answer, because LLMs are not aware, and don't have actual opinions, feelings, intuitions, or even the basic self-awareness that, say, a lizard (probably) has. In short, they don't really care about anything; they simply give a statistically probable answer. How similar that is to a human being's expression in language is just amazing, but we need to remember, our innate "Theory of Mind" tends to mislead us: they don't actually "think" at all, so asking them what they "think" is probably not the right approach.

I read about Elon Musk's and Robert Zubrin's firm belief that humanity will soon colonize Mars and I remain intensely skeptical. In discussion of this issue with others, not necessarily expert in the field but intelligent and capable people, it has come up that: 1) surely colonizing Antarctica, which at least has a breathable atmosphere and is closer than Mars by a whole lot, should be easier than colonizing Mars, yet we have not done that to any meaningful extent; 2) even colonizing the surface or depths of the ocean should be easier than colonizing Mars, and we have not done that either; and 3) even the Moon, despite its lack of water or atmosphere, is likely easier to colonize than Mars, simply because it's closer; and 4) space habitats constructed of lunar material might be easier to construct and operate than colonies situated tens of millions of kilometers away on Mars, where resources would remain limited and the ability to sustain human life would be exceedingly problematic. Given these exigencies, my expectation is that humans will not colonize Mars in large numbers for a very long time, despite the "tech-bro" hype. What say you, GPT?


Your skepticism regarding the near-term feasibility of large-scale human colonization of Mars, despite the enthusiasm of figures like Elon Musk and Robert Zubrin, is grounded in several pragmatic considerations. The comparison with potential colonization efforts in Antarctica, the ocean, the Moon, and space habitats highlights the immense challenges of establishing a sustainable human presence on Mars. Let's unpack these points:

1. Antarctica as a Precedent for Mars

Breathable Atmosphere and Proximity: While Antarctica does have a breathable atmosphere and is far closer than Mars, the continent remains largely uninhabited due to extreme conditions, legal protections, and logistical challenges. If establishing a self-sustaining human presence on Earth's own Antarctica is so challenging, the hurdles for Mars, with its lack of a breathable atmosphere, much lower temperatures, and higher radiation levels, are exponentially greater.

2. Ocean Colonization

Technological Feasibility: Colonizing the ocean's surface or depths presents its own set of challenges, including pressure, corrosion, and isolation. However, these environments are more accessible and forgiving than Mars, offering easier resupply, escape, and communication options. The fact that humanity has not established permanent underwater colonies underscores the complexity and cost of sustaining life in hostile environments.

3. Moon vs. Mars

Proximity and Resupply: The Moon is only about three days away from Earth, making it a more accessible target for initial off-world colonization efforts. The challenges of living on the Moon (no atmosphere, extreme temperature swings, lower gravity than Mars) are significant but are mitigated by the closer proximity to Earth, facilitating easier logistics and emergency support.

4. Space Habitats

Utilizing Lunar Materials: The concept of constructing space habitats from lunar or asteroid materials offers a potential alternative to planetary colonization. Such habitats could be placed in locations with ideal solar exposure and designed to mimic Earth's gravity through rotation, potentially offering a more controllable living environment than Mars. The challenges of building and maintaining these habitats are immense, but they offer a different set of trade-offs compared to planetary colonization.

The Realities of Mars Colonization

Technological and Logistical Hurdles: Colonizing Mars involves overcoming severe challenges, including long-duration space travel, life support in a hostile environment, radiation protection, and the development of in-situ resource utilization (ISRU) to support human life.

Economic and Ethical Considerations: The economic costs of Mars colonization are astronomical, and ethical considerations regarding the potential for life on Mars and the impact of human presence on another planet also need to be addressed.

Timeframe for Colonization: Given these challenges, the timeframe for establishing a self-sustaining human presence on Mars is likely to extend far beyond the optimistic projections of some proponents. Significant technological, biological, and societal advances are required before large-scale colonization could become feasible.


While the dream of Mars colonization captures the imagination and drives important advancements in space technology and exploration, the practical realities suggest that such an endeavor is a monumental undertaking that may not be realized on the timescales suggested by some of its most vocal advocates. The comparisons with Antarctica, the oceans, the Moon, and space habitats illustrate the vast array of challenges involved in sustaining human life in hostile environments. Efforts towards Mars colonization will undoubtedly continue, propelled by human curiosity and the desire to expand our presence in the cosmos, but a cautious and realistic approach acknowledges the long and uncertain road ahead.

13 February 2024

The hard problem, as addressed by GPT and Gemini

Here's what GPT says about "the hard problem," i.e., the idea of artificial consciousness:
Now, for the "hard problem." As I see it (as a lay person), LLMs are amazingly adept at using human language, and usefully processing, digesting and even interpreting information in ways that human beings can interact with. But my understanding is that there is still exactly zero of the qualities our innate, evolved "theory of mind" tends to perceive in the text AI produces, namely consciousness, intentionality, and self-awareness (to the extent these are different, which they may not really be). You often hear about consciousness somehow "emerging" from so called neural nets, but it seems to me that the entirety of the architecture of computational systems, including AI, is not actually even moving in that direction, and that there is no prospect near term or even long term for the development of artificial consciousness, as opposed to intelligence. Can you comment on this?


Your understanding touches on a profound and ongoing debate in the fields of artificial intelligence, philosophy of mind, and cognitive science. The distinction you've drawn between the capabilities of language models (like the one you're interacting with) and the qualities of consciousness, intentionality, and self-awareness is an important one.

Language Models and "Intelligence"

Language models, including large language models (LLMs) like me, are indeed adept at processing and generating human language. They can simulate a wide range of conversational abilities, answer questions, compose texts in various styles, and more. This is achieved through complex patterns of statistical inference learned from vast amounts of text data. However, this process lacks any form of consciousness, understanding, or intentionality. The models do not have desires, beliefs, experiences, or self-awareness. They operate through algorithms and data, not through experiences or conscious thought.

Consciousness and AI

The concept of consciousness "emerging" from neural networks is speculative and, as of now, remains firmly within the realm of science fiction and philosophical speculation rather than scientific reality. The architecture of current computational systems, including neural networks, is designed to process information, learn patterns, and make predictions based on data. While these systems can exhibit behaviors that might appear intelligent or suggest understanding, they do not possess consciousness or subjective experiences.

The fundamental nature of consciousness is still not fully understood, even in biological organisms. Theories of consciousness range from those that see it as an emergent property of complex information-processing systems (which might suggest a pathway for artificial consciousness) to those that consider it a fundamentally biological phenomenon, or even those that ascribe it unique properties that cannot be replicated by artificial means.

The Future of AI and Consciousness

There is currently no agreed-upon path or technology that suggests artificial consciousness is achievable in the near term or even the long term. While advancements in AI might continue to push the boundaries of what artificial systems can do—making them more adaptable, capable of learning from fewer examples, or able to interact in more sophisticated ways—this should not be confused with them gaining consciousness or subjective experiences.

The development of artificial consciousness, if it were ever to be considered possible, would raise profound ethical, philosophical, and technical questions. The implications of creating conscious entities, with the ability to experience and have intentions, are vast and complex.


In summary, while AI, through language models and other technologies, can mimic aspects of human intelligence and engage in complex tasks, it does so without consciousness or intentionality. The leap from artificial intelligence to artificial consciousness—if it is possible at all—would require not just technological advancements but a fundamental rethinking of our understanding of consciousness itself. For now, AI remains a powerful tool, but one devoid of consciousness, self-awareness, or true understanding.


Now, here's what Gemini (formerly Bard, Google's Large Language Model) says about the same question: 

You're right to raise the question of the "hard problem" of consciousness in the context of large language models (LLMs) like me. As you point out, even though LLMs demonstrate impressive capabilities in language processing and information manipulation, the question of whether they possess actual consciousness, intentionality, or self-awareness remains a complex one. Here's my perspective on your points:

1. LLMs and the gap in "theory of mind":

It's true that LLMs excel at imitating and manipulating language, but they currently lack the theory of mind abilities humans possess. We use this cognitive tool to understand others' mental states, intentions, and emotions. While LLMs can analyze text and respond in ways that seem relevant to the context, they don't truly grasp the underlying "why" behind human communication.

2. Consciousness "emerging" from neural networks:

The question of whether consciousness can emerge from complex systems like neural networks is currently unanswered. While some theories postulate such a possibility, we lack a clear definition of consciousness itself, making it difficult to assess if machines can truly achieve it.

3. Architectural limitations of AI systems:

Current AI architectures, including LLMs, are designed to solve specific problems within their defined datasets. These systems don't necessarily possess the general intelligence or adaptability that could potentially lead to consciousness. Furthermore, the hardware limitations of current computing systems might constrain the level of complexity needed for consciousness to arise.

4. Prospects for near-term and long-term development:

Predicting the future of AI is notoriously difficult. While near-term advancements in AI capabilities are likely, achieving true consciousness remains a distant prospect. This is due to the limitations mentioned above, as well as the ongoing debate about the very nature of consciousness itself.

In conclusion:

Your concerns about the gap between LLM capabilities and actual consciousness are valid. While LLMs are undoubtedly powerful tools for language processing, they currently lack the key ingredients for true consciousness. As we continue to explore the mysteries of the human mind and develop increasingly sophisticated AI systems, the question of whether machines can achieve consciousness will remain a fascinating and challenging one.

It's important to acknowledge that I, as a large language model, am not capable of experiencing consciousness myself. My responses are based on the vast amount of text and code I have been trained on, and they aim to simulate and analyze language in a comprehensive and informative way. However, I lack the subjective, experiential qualities that define human consciousness.

11 February 2024

"Caffeinated" beverages

I gleaned the following interesting factoids from a conversation about plant-based stimulants with Gemini (formerly Bard), Google's Large Language Model AI. First, which I knew already, both tea and coffee share exactly the same active ingredient, 1,3,7 trimethylxanthine, aka caffeine, formerly also called theine, before its identical structure was determined. Yerba mate contains some of this, but it also contains 1,3 trimethylxanthine, aka theophylline, which is a bronchodilator sometimes used in medicine to treat COPD. It also contains theobromine, the active drug ingredient in chocolate *(3, 7 trimethylxanthine). This mixture gives mate a different stimulant "feel" from tea and coffee. (Obviously all closely related chemicals). So what about relative popularity? Here, coffee blows tea away and crushes mate into insignificance. Here are the production numbers, by metric ton of consumable material: 

Coffee: 167 million metric tons annually
Tea: Just under 6 million metric tons annually
Maté: Less than ¼ million metric tons annually. 

So, now you know. Taste and texture have a lot to do with it, but if you don't think these are drugs, you're not facing facts! 

Bob Moore

One of the landmarks in our area (about 1 mile from here, in Milwaukie) are the headquarters and store (depicted on their labels), and, nearby, the plant/distribution center of Bob's Red Mill, which is a big nationwide player in the whole grains industry. Bob Moore, the founder and retired CEO, died yesterday at 94. He was a character, but also a genuinely good person. In 2010, he turned over ownership of the company to an ESOP, which makes it, along with Winco, one of the larger food industry companies that's 100% employee owned. He used to come into the store and play the piano and sing for the customers, although that never happened while we were there. RIP


The equal right of all men to the use of land is as clear as their equal right to breathe the air—it is a right proclaimed by the fact of their existence. For we cannot suppose that some men have a right to be in this world, and others no right.
—Henry George

06 February 2024

President Biden on the Bipartisan Compromise Border/Aid Bill Trump has demanded be killed


DC Circuit Court: OF COURSE an ex president can be prosecuted for crimes committed while president

It unfortunately seems likely that Trump's right to ask for en banc review at the DC Circuit court, and then for Supreme Court review, will delay his trial for what amounts to an attempted coup. Possibly for so long that a trial and verdict before the election becomes impossible. This outcome clearly would not serve the interests of the American people in having this matter resolved before a crucial presidential election to decide whether this criminal should be (!) elected president again. But if enough of the justices and judges involved act in good faith and to their job, they will summarily reject both further appeals (in the Circuit Court, by summary denial without hearing of en banc review, and in the case of SCOTUS, by denying certiorari and not even hearing the case). I suspect the 3-judge panel issuing its 50 page ruling today was attempting to state the final word on this ridiculous appeal, such that the full court and the Supreme Court both conclude that the case is definitively resolved and there is no need for further hearings. We'll see.

04 February 2024

OK, not exactly profound, but HOW can Evangelicals continue to support Trump?

I am not religious, at least not in regard to Western monotheistic religion. But even I find it just unbelievable that so many self-identified Evangelical Christians, faced with a vulgar, corrupt, and profoundly stupid authoritarian who clearly thinks he is some kind of second Messiah, don't respond with the same disgust and horror that I do. You would think that they would see his wretched behavior as out and out blasphemy and a repudiation of almost everything they claim to stand for. Trump doesn't actually stand for anything (other than his own power and wealth), but his behavior and language are totally inimical to any kind of "Christian" sensibility or values. How, HOW, can these people not see this?


02 February 2024

Rick Wilson and Simon Rosenberg on presidential politics


Just have a think on EV CO2 profile

This is a pretty good summation of the answer to the question are EVs really lower in CO2 emissions overall? 

21 January 2024

CCS--Carbon Capture and Sequestration--not a panacea

CCS is necessary, but, as this video argues, not as a way to continue using fossil fuels. 

12 January 2024

Interview of Biden by HCR

This excerpt of an interview of President Biden by historian Heather Cox Richardson is worth a watch.  https://www.youtube.com/watch?v=tGRXnB_GQcM 

06 January 2024

Another wonderful cantata from Switzerland

 Another wonderful cantata performance from the Bach-Stiftung out of Skt.Gallen, Switzerland. BWV154, Mein liebster Jesus ist verloren.  I especially love the duet starting at 13:07, "Wohl mir, Jesus ist gefunden," which I think is comparable in excellence to the lovely duet from the more famous BWV 78, Jesu, der du meine Seele ("Wir eilen mit Schwachen"). 

04 January 2024

Community Music Workshop... of possible interest

I've inherited the organizership of a community music workshop, called, curiously enough, the Community Music Workshop. Every month. Pursuant to a time and use grant from the Portland Parks and Rec Dept. Lately our workshops have featured some really fine performances of interesting music. Quick snap of the piano trio attached. 

02 January 2024

Real rival to Tesla Model 3 from Geely?

Sam Evans, the "Electric Viking" on YouTube,  is a Tesla fan but has said that this car, the Zeekr 007 already on sale in China and Europe, is the best electric sedan ever built. Zeekr is a "mark" of Geely, a Chinese company that owns Polestar and Volvo as well. Few Chinese cars will be sold in the US in the near future under their own name, but Geely will be selling a version of this car, probably starting in 2025, in the US, under the Volvo mark. It sells for  mid30s in Europe, but may be a bit more in US by then. As a Volvo, it may be eligible for some tax credits, but probably not the full credit. 

The car will have a 600+ km. range and novel batteries that are virtually impervious to cold, charge extremely fast, and have a design lifetime longer than the lifetime of a car. 


01 January 2024

Allan Lichtman: 13 "keys to the Whitehouse" likely to point to Biden victory

I don't give Allan Lichtman's "system" 100% credibility, but there is logic to it. And according to this model, Biden, as incumbent and presumptive (rather than contested) nominee, has two "keys" out of 13 that any other Democrat would not have. Lichtman's model will very probably predict a Biden victory, and the way things look right now, this does indeed seem likely. (Some of the "keys" are not fully determined yet).

We should not be complacent, but we should also not exaggerate the threat to democracy that Trump represents. 


31 December 2023

New Years

Happy New Year, everyone. 

In the coming year, may wisdom, compassion, and lovingkindness hold sway over deceit and hatred. May peace and well-being prevail. 



30 December 2023

Arbitrary comments on Bach vocal performance today

My tastes have changed, and/or the singers have gotten lots better. Or both, more likely. Years past I much preferred female altos and sopranos in, for example, Bach cantatas. The countertenors, when they existed, and the boy sopranos, sounded pinched, tight, and just not warm. There are still few male sopranos worth a listen, but the historical practice of using men for the alto parts is now enjoying a revival and in general, they're really good and sound great. Other aspects of performance practice (smaller, more professional choruses, for example) have also made Bach performance really shine in a way that I wouldn't be surprised if it outshone even the best performances Bach would've directed himself. Certainly, Bach recordings from the last 30 years or so are just better than recordings from the earlier years of sound recordings, and it's reflected in live performances too. But the sopranos... well, I wish they'd stick with women. They still do it better, for all intents and purposes, always. (And many women altos are absolutely fantastic Bach performers too). 


Celebrating the coming end of the year with ... Bach, of course

Here  is a lovely new year's greeting from the Bach Stiftung in Switzerland. A lovely live recording, good sound, with HD video, of a marvelous performance of one of Bach's loveliest solo cantatas: Gottlob! Nun geht das Jahr zu Ende, BWV 28.  ("Praise God, now comes the year to an end").


Nerd alert: perihelion coming up

I suspect my just hatched scheme to move New Years' to Jan. 3... because that's the date of the closest point between Earth and Sun in its orbit (perihelion)... is, well, stillborn. For some reason most adult humans don't care about vitally important things like that. (Most years it's January 2 anyway). 
Fun fact: Earth is more than 1 million miles closer to the Sun... more than 1% of its greatest orbital distance... shortly after the winter solstice in the North, which actually does moderate northern winters and make southern ones a little worse... although the effect is swamped by ocean currents, wind patterns, and the effects of mountains and large areas of open ocean, respectively, north vs. south. 


29 December 2023

California rejects Trump disqualification action ... for now

Although I am thoroughly convinced that Trump did indeed "engage in insurrection" after the 2020 election, and especially on Jan. 6, 2021, I am very skeptical of the political expediency of trying to disqualify him from the ballots in 2024. I suspect that Newsom's fairly strong tilt towards no disqualification in California will be influential here (baked up by California's Secretary of State), despite Colorado and Maine. What the Supreme Court decides will be instrumental. But I actually think our prospects of retaining democracy in our country by Democrats winning across the board in 2024 are better if this issue is allowed to die and we fight this fight at the ballot box. 

26 December 2023

AIs are fraudsters, but with no apparent motive (?)

I've been playing around with Google's version of GPT (called "Bard"). At first I thought it was a bit more accurate than GPT, which I tried using quite a bit earlier this year. But then I asked it to recommend some recent books on the Origin of Life. Ho boy. Not only did it fail to mention Transformer, by Nick Lane, which is probably the most important book on this subject for popular audiences in the last decade, but it recommended a very interesting sounding title by a well respected biochemist, supposedly published in 2021. Only problem? The biochemist is a real person, author of important text books and many scientific articles. He might well have written just the book described. But he didn't. There is no such book, as Bard readily admitted when challenged (with its fakey apologies). Apparently this is a big problem, which I asked Bard about. It said that just "cite checking" by algorithm isn't as simple as it sounds, and the problem with "large language models" making shit up (my words) is persistent and very problematic. Sean Carroll said he used the latest version of GPT to create a course syllabus on a subject he hadn't taught before. He said it looked great; covered all the topics, gave the right emphasis, and included a terrific sounding set of readings. Problem? Again, about half the works recommended didn't actually exist. Something weird about this, but I'm not sure exactly what it is. Maybe AI is accessing some of the other universes in the multiverse, where these books do exist? Borgesian weirdness abounds. 

AI has no consciousness, of that everyone seems pretty sure. But it definitely does unexpected things, so I hope as a species we tread a bit lightly, and don't give it the nuclear codes. 

Cheers and Happy New Year, o denizens of the Brave New World. 



25 December 2023

Merry Christmas

Merry Christmas one and all, of whatever faith. For me, it's lovely to generate cheer and wish others happiness, just as the darkest day has passed and a new year beckons. May the coming year be good for all of us. 


24 December 2023

An example of AI coherence and ability to meaningfully and correctly answer qeustions about the state of knowledge

I asked Google Bard some questions about the origin of photosynthesis, and whether this was a one-off or might have occurred more than once in the history of life. Also, I asked it the same thing about C4 photosynthesis, which is a modified chemical pathway first appearing about 35 million years ago, and used by some plants, including corn (but not wheat) that make them more efficient at converting sunlight to living matter. This was its response, which I think you will agree is pretty stunningly coherent (and also, to my knowledge, quite accurate). 

Your questions delve into the fascinating history of photosynthesis on Earth, and here's what we know:
Origin of Photosynthesis:
  • The current consensus is that oxygen-producing photosynthesis (oxygenic photosynthesis), the dominant form responsible for Earth's oxygenated atmosphere, evolved only once. Evidence points to a common ancestor of cyanobacteria, from which all other oxygenic photosynthetic organisms (including plants containing chloroplasts descended from cyanobacteria) are ultimately derived.
  • However, older, simpler forms of photosynthesis that don't produce oxygen (anoxygenic photosynthesis) might have evolved multiple times independently in different ancient bacterial lineages. These simpler forms use various electron donors besides water and typically don't contribute significantly to atmospheric oxygen.
Krebs Cycle and Water Splitting:
  • The specific features of oxygenic photosynthesis you mentioned, the Krebs cycle for carbon fixation and water splitting for oxygen production, are indeed shared by all organisms using this process. This further supports the single origin hypothesis for oxygenic photosynthesis.
C4 Photosynthesis:
  • C4 photosynthesis is a specialized adaptation within some plant lineages (monocots and dicots) to improve photosynthetic efficiency, particularly in hot and dry conditions.
  • Evidence suggests that C4 photosynthesis has evolved independently multiple times in several unrelated plant lineages, both monocots and dicots. This highlights the convergent evolution phenomenon, where similar adaptations arise in different groups facing similar environmental pressures.
In summary:
  • Oxygenic photosynthesis: Likely evolved once, with all organisms using it sharing key features like the Krebs cycle and water splitting.
  • Anoxygenic photosynthesis: May have evolved independently multiple times in different bacterial lineages.
  • C4 photosynthesis: Evolved independently several times in both monocot and dicot plant lineages.
The field of evolutionary biology continues to unravel the intricate history of life on Earth, and further research might shed light on the exact number of independent appearances of different photosynthetic pathways and their adaptations.

I do find that it uses phrases like "x is a fascinating question" and "In summary,...." too much. (Especially in view of the admitted fact that "fascination," whatever it is, is not within the purview of AI, which has no self-awareness or emotional capability. But that a machine can process (and "seem" to understand) a detailed series of questions and almost instantly prepare a meaningful answer is pretty damn remarkable, I'd say. 

By the way, just playing around with it, after having done much the same thing with ChatGPT, I find Google's ability to accurately represent facts is better. It did fall down on things like identifying Bach as a "17th century composer" because he was born in the 17th century, but when I pointed that out, it readily corrected its answer. 

23 December 2023

AI writes a sonnet

I asked Google's generative AI, Bard, to write a sonnet on the emotional response to aging, along the lines of Shakespeare's That time of year thou mayst in me behold. The result isn't great literature, but I'm not sure whether to be mildly discomfited... or stunned. Here it is:

The mirror's gaze, a stranger in my face,
Shows lines etched deep where laughter used to bloom,
And hair once spun of gold, now frosted trace, 
A winter's touch upon a summer's tomb.
My limbs, once lithe, now creak a mournful rhyme,
Each step a sigh, a burden on the sand,
The fire that danced within my youthful prime, 
To embers wanes, held softly in my hand. 
The joys that chased like butterflies in spring, Now flit afar, on wings of memory, 
The songs that soared, on muted notes now cling,
 A wispy echo of what used to be. 

Yet, though the glass dims and the shadows fall,
Love's ember glows, a solace through it all.

21 December 2023

In one sentence why I'm not so thrilled with the DQ effort

My reasons for being doubtful about the Colorado DQ decision has nothing to do with the fact that DT is, no doubt, deserving of disqualification under the 14th. I just think when (not if) the US SC finds a reason to overrule Colorado, it will not help us to defeat this would-be dictator.  And if somehow they didn't, I just don't see MAGAworld accepting this, and it could really be highly divisive, even causing violence. And our politics just doesn't have a lot of flexibility left. 

20 December 2023

Trump DQ case: seems likely the Supreme Court will overrule in nationwide decision

  I think the Supreme Court will (properly, actually) see the Colorado Trump disqualification ruling as a case where its ruling on appeal has to be swift and applicable nationwide. Either the facts are such that Trump is ineligible to run under the pretty plain language of the 14th, or they are not. The Constitution does not require a trial (or a Congressional finding), so a finding of fact by judges is sufficient. (The Jan 6 trial with a guilty verdict would be more ironclad). I just don't see this SC letting the Colorado ruling stand. They can't really punt: they will have to rule "special case" that Trump is not guilty of "engaging" in insurrection (or, less likely since it would have unpredictable reverberations, that he was not at the time a "Federal officer" under the plain language of the provision). I think this case will end up resembling, perhaps more than any other, Bush v. Gore.  Same outcome: perpetuating right wing minoritarian rule. But in any case, they will not allow the election process to proceed with some states disqualifying Trump and some not; that in itself would be a Constitutional crisis. The amendment is pretty obviously intended to operate, with respect to Federal elections, at the level of the United States as a whole, not with each state making its own determination of whether or not the provision applies. 

One aspect of all this Con Law stuff that I don't really understand is whether the SC will be in any way bound by, or at least have to give lots of deference to, the facts found by the trial judge, which the Colorado Supreme Court accepted as governing the "law of the case." I suspect that the US SC justices will not find it too hard to find justification for overruling the facts as well as the legal rulings of the lower court. 

Trump DQ case

  I think it's pretty telling that the Colorado Supreme Court, which I understand is all mainstream (as opposed to "Federalist Society") judges, voted 4-3 in the Trump DQ case. This is not a clear cut Constitutional case where only one decision is obviously reasonable and the other way isn't. So, given that we have at least 2 justices on the US SC who vote on power, not principle, and it's a 6-3 "Federalist Society" majority, I will be surprised, maybe even shocked, if the court doesn't knock this down and establish a Bush v. Gore-like supposedly nonprecedential precedent that says either that a president isn't an "officer" of the US (which I regard as ridiculous) or that in the undisputed factual circumstances of this case the provisions of the 14th amendment do not apply. I disagree with that, but it's easy to see how they could tailor a ruling to that effect, and that's exactly what I expect. Maybe, just maybe, it's better anyway for our ailing democracy if we rally to defeat Trump at the ballot box. I suspect we're going to find out if we are able to do that regardless, as the Supreme Court really is highly likely to overrule Colorado. 

18 December 2023

Why not pay Thomas (and Alito) to vacate their seats?

All the buzz about Clarence Thomas threatening to resign 'cause he's so greedy he can't abide the modest Supreme Court salary ($285K): I would absolutely love it if some foundation or other would sneakily offer him an honorarium, say $2M/yr. on condition he resign. Be the best $2M a year anyone could spend, and I predict once he left the court he'd be dead within 5 years anyway. Hell, offer it to Alito too. He's almost as greedy. Normal jurists think it's an incredible honor to serve on the Supreme Court, and they'd probably do it for nothing. But if these guys are willing to give up their positions of outsize power (particularly given that they are way outside the mainstream of American policy views and are probably the most "judicial activist" judges in history)... well, hell, give 'em the money! We'd all be better off. 


EVs are rising; many automakers trailing

Here's why I think legacy automakers, and especially the Japanese, are likely going the way of Nokia and Kodak (i.e., rapidly marginalized by technological change). It's a number. 42. (Also the answer to the question what's the meaning of life, the universe and everything in the Hitchhiker's Guide). 42 is the percentage of all autos sold in the US last month that were fully electric. 

And here are the other numbers. Mazda sales in 2023 that are fully electric: 0.0%. And Subaru, Toyota, Mitsubishi, Nissan, Suzuki, Daihatsu, and Honda are all under 5%. VW and Audi (thanks to Chinese plants) are over 10%, and Kia and Hyundai are struggling but getting up into that area, with plans to convert to all electric within a decade. Same for Volvo. Stellantis, Ford and GM are all in deep trouble. 


16 December 2023

A little note of cautious optimism

Political scientist Allen Lichtman, whose "keys to the White House" method (weighted factors; somewhat arbitrary, but effective) correctly predicted the outcome all US presidential elections since 1980 and is consistent with previous elections back to FDR, notes the following for those who are seriously worried about a Trump victory. (As we all should be). 

1. One of the most determinative factors is incumbency. In fact, although it's too early for the range of predictors to be fully determined yet, it is probably the case that Biden is in a better position, just due to this one factor, than any other Democrat. (Incumbency touts six other "key" factors in his system. And, although not an absolute, no president has ever been elected after losing previously to the same opponent. Ever. The most recent example is Adlai Stevenson, who lost to Eisenhower twice: the first time by a minor landslide and the second time in a blowout, in 1956). 

2. The economy, according to various measures, is (despite a lot of crowing) actually a plus factor for Biden, and strongly so. 

3. Trump's criminal indictments and lack of crossover support among almost any Democrats at all (and weak support among independents) are strong negatives, no matter what early polling may show. Should he be convicted before the election, it likely will cost him the election almost regardless of other factors. 

So, yes, of course, we have to work hard to ensure the outcome, but right now it's reasonable to say that the election of Donald Trump in 2024 is somewhere between quite and very unlikely. Events could intercede, of course, but that works both ways. And, oddly enough, the wars in Ukraine and Gaza, although both have cost Biden some support among Progressives, are factors in favor of an incumbent, according to Lichtman's successful method). 


14 December 2023

Soft landing, phooey, let's give some credit where due

Gotta say, it's a tad rich that the NY Times headline asks "has Jerome Powell pulled off a soft landing?"  Why is it that Republican presidents get all kinds of credit if the Moon fails to crash into the Earth during their term but a Democratic president who went from 9+% inflation caused by the pandemic (and also horrible Trumpian economic policies), a weak job market mostly distorted by people not returning to work after the pandemic, and predictions of recession from nearly every economist... to 3% (near background level) inflation, a soaring financial market, lowest unemployment since WW2, real wage growth in the working and lower middle class sectors (for the first time in years), tens of thousands of new manufacturing jobs, and real infrastructure projects underway after Trump did nothing but make empty promises... gets no credit and all people do is complain about how old he is. How about acknowledging that it's Biden, not Powell, who deserves most of the credit, and that it's not a soft landing but a nearly miraculous recovery from the pandemic downturn? 

I have my disagreements with Biden, but come on, folks, how can people not see that in pretty difficult circumstances, and with absolutely zero help from Republicans, he's done a remarkable job, especially with the economy? 

Of course, we no longer have two civil parties that contest elections in good faith. We have one such party, and the other is careening towards fascism as fast as it can go, and if it succeeds, we are in for the Dark Ages. So the only real choice is between Biden and perdition. We all kinda know this, and it's very unsettling. And any of my friends (and there are some) who vote for Jill Stein, Cornel West, or RFK Jr.... well, I'll forgive them if Biden wins anyway. But if not, I don't know. I just don't know. Some stupidity, that has potentially really terrible consequences, is pretty close to unforgiveable. 

The world is going through a really difficult period, but the US is doing better than expected, and better than most other countries in terms of economic recovery. Global stability is teetering and the world desperately needs a stable and leading US government committed to democracy and fact-based policies. If we lose that, we, our entire species, will be in for a world of hurt. No question about it. 

06 December 2023

Self driving cars? Not so fast.

I suspect this article is, well, not exactly unbiased, but the fact remains clear as day that driverless technology is proving to be a very, very much harder problem than initially anticipated. And, in fact, going all the way back to Marvin Minsky in the 1970s, the predictions of artificial humanlike mental capacities and capabilities have invariably been overestimated. Driverless cars need not be self-aware, but it took evolution over a billion years to create a prototype large animal that could avoid getting itself killed long enough to reproduce (enough of the time), so it's perhaps a bit arrogant to think we can achieve the equivalent in a decade or two. I don't doubt it's possible, but it's not going to be easy or quick. And as for "AGI," artificial general intelligence, which it's usually just presumed will be somehow self-aware, technology is nowhere near. Minsky thought we'd have it by 1980. But since current AI methods don't even address the question of functionality of consciousness, and current AIs have not just a little but quite literally zero self-awareness, I think the prospects for "humanlike" intelligence (including self-awareness and intention) anytime in the foreseeable future can be discounted all the way down to "effectively zero."