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. 

 

______________________________

COMMIT TO SUPPORTING DEMOCRACY 

______________________________

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). 

______________________________

COMMIT TO SUPPORTING DEMOCRACY 

______________________________

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").

______________________________

COMMIT TO SUPPORTING DEMOCRACY 

______________________________

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. 

 

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. 

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. 

David 

______________________________

I SUPPORT DEMOCRACY 

______________________________

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. 

______________________________

I SUPPORT DEMOCRACY 

______________________________

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. 

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.

 

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. 

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. 

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. 

______________________________

I SUPPORT DEMOCRACY 

______________________________

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. 

______________________________

I SUPPORT DEMOCRACY 

______________________________

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). 

______________________________

I SUPPORT DEMOCRACY 

______________________________

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. 

 

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."