Some Friday Music

There is some good songwriting on display here.

Bluegrass covers of Simpson's existing music.

Jan. 6 Fact Sheet

From Julie Kelly.

Among the most disgusting claims about the January 6 riot is the notion that half a dozen officers were killed. One officer died the following day of a stroke, after suffering from pepper spray on the day of the riot. Several more officers committed suicide later. In contrast, four protesters died on the scene: one was shot by an officer and died immediately, while three others succumbed on the scene to some kind of violence that is less clear in the record. The official version seems to be that two died of heart attacks and the third from an overdose; the protester version is that the heart attacks could be attributed to excessive police force, while the third, an unarmed woman, was frankly clubbed to death. I am aware of at least one later protester who appears to have been hounded to suicide.

If the same standard of lethal causality were applied to the protesters as to the officers, the body count would be far different from what has been peddled by the powers that be for the last couple of years. For that matter, if the same standards of law and order were applied to the BLM and Antifa mayhem throughout 2020, the conviction count would alter drastically. It's hard to imagine a clearer example of "protesting while Republican."

The riot was a stain on conservative politics. The aftermath, especially this week's appalling attempt at censorship, is an even worse stain on this country's leadership, including most recently Senate Majority Leader Mitch McConnell. I've defended him for years, but I'm done. There can be no possible excuse for objecting to the airing of video evidence because it "contradicts" the way the police have chosen to "depict" the events. He has proved himself on a level with Senator Schumer.

Kudos to Jonathan Turley for continuing to point out the egregious Brady Rule violation of federal prosecutors in withholding exculpatory evidence for the last two years.

Women in Philosophy

The Cambridge Elements series on women in the history of philosophy is available for free download through the end of next week. They did a similar promotion a year or so ago, but at the time as I recall it was only part of the list that you could download. 

I think several of you would enjoy Early Christian Women by Dawn LaValle Norman of Australian Christian University. It raises an interesting claim about the introduction of these women to philosophy and its effect on how philosophy was anthropomorphized. Probably many of you have read Boethius' Consolation, and are familiar with his picture of Lady Philosophy. It was common to depict Philosophy as a sort-of goddess, sought through difficult and heroic adventures, or found in tragedy like Boethius. That conception was changed by the women who came into the practice: 

The personification of philosophy as a woman assumes that philosophers, her erotic desirers, are symbolically masculine. The binary of male lover–female beloved imagines that the target of such pleas are men who were inspired by the idea of choosing wisely between competing types of women. Yet in the third century CE, the Christian dialogue writer Methodius of Olympus reimagined the gendered relationships of allegorical females in educational ascent myths. Virtue, daughter of Philosophy, still dwelt on top of a mountain that was steep and dangerous. But instead of questing men who attempted to enter her secluded garden, educated women were invited to her garden party.

I can attest for the quality of at least one of the authors in this series, who is a dear friend of mine. I assume the others to be of similar quality. 

AI Illustrations

OpenAI, the same company that put out Chat GPT, also has an illustrator. I asked it to give me illustrations of the Elric the Barbarian story in the style of N. C. Wyeth. This is what it came up with.

"Elric the Barbarian," I suppose.

An older Elric.

These are obviously not anywhere near the quality of N. C. Wyeth illustrations, but they're good enough for a paperback cover. Hope you're not an illustrator, because you're out of work: there's no way a publisher will pay you hundreds or thousands of dollars when the job can be done 'well enough' for free.

Corruption is the Answer

This is an article with multiple significant insights about the problems of the moment. The conclusion is shocking to those of us from another era, but there may not be anything wrong with it.

Under conditions of bureaucratic dysfunction typical of a party-state, corruption isn’t a problem, it is the solution. 

That was certainly my experience living in China, a party state of the sort he is describing. I had the wrong kind of visa to be employed, but I had a job. I didn't worry about it; the man who got me the job was the same man who signed for my visa renewal. I've told the story about getting paid in China before (although if you don't remember reading it, you should: it's one of my better stories). It was many months after I'd been working before I saw any of my promised pay. The problem wasn't that they weren't going to keep their word about paying me, it was that they had to build out a slush fund first. Once they'd solved the practical problem of arranging a corrupt solution, they paid me every single thing they promised.

As our system becomes captured by interests basically hostile to the people and the nation, we are all going to end up having to adopt these ways. They are like the illicit economies that prisoners develop, as a means of escaping the control of the guard towers. They are, in a way, a moral duty to embrace: just as a prisoner of war has a duty to try to escape out of loyalty to the country of his birth, so too do we. 

"Elric the Barbarian"

So the third thing I asked Chat GPT to do -- as discussed in the immediately prior post -- was to write a short story in the manner of Robert E. Howard. Here is what it came up with.

The sun beat down on the dusty plains as Elric the barbarian rode towards the small village. He had been wandering for days, searching for a way to ease the restless fire that burned within him.

As he rode into the village, he could sense the tension in the air. The people were on edge, their eyes darting nervously at him as he passed by.

Ignoring their wary glances, Elric strode into the local inn, his hand resting on the hilt of his trusty broadsword. He knew he needed a stiff drink and a warm meal before he could continue his quest.

The innkeeper eyed him warily as he approached the bar. "What brings a man like you to these parts?" he asked, his voice trembling.

"I'm just passing through," Elric replied, his voice low and rumbling. "I need a meal and a place to rest."

The innkeeper nodded, his eyes flickering towards the door. "You best keep your wits about you," he warned. "There's trouble brewing in these parts."

Elric raised an eyebrow. "Trouble? What kind of trouble?"

The innkeeper leaned in close, his voice dropping to a whisper. "There's a group of bandits that have been raiding the nearby villages. They're ruthless, and they've already killed dozens of innocent people."

Elric's grip tightened on his sword. "I'll take care of them," he growled.

The innkeeper looked skeptical. "You're just one man," he said. "How do you plan to take on a group of bandits?"

Elric smiled grimly. "I've faced worse odds than this," he said. "And I've always come out on top."

With that, Elric left the inn and rode out towards the bandit's hideout. As he drew closer, he could see the flicker of torchlight and hear the sound of raucous laughter.

Elric drew his sword and charged towards the bandit's camp, his battle cry echoing across the plains. The bandits were caught off guard, and they fell quickly to Elric's mighty sword.

As the last of the bandits lay dying at his feet, Elric felt a sense of satisfaction. He had protected the innocent, and he had once again proved that he was the greatest warrior in the land.

With a fierce grin on his face, Elric rode off into the sunset, ready for whatever adventure lay ahead.

You can see elements that are right: the use of a fantasy-style name, the existence of swords, the attempt at dramatic tension leading to violent sword-based conflict. Nevertheless the story is terrible to the point of being ridiculous. 

REH's works are in the public domain, so Chat GPT presumably can access large parts of them and map them. However, creating writing requires more than  just getting a lot of the right words into the right order. 

My guess is that this means we are doomed to even worse popular art than we have been subjected to already. Autotune proved attractive to the recording industry even though it is terrible, obvious, and offensive to the ear. This was because it allowed pop music stars (which now includes contemporary Nashville country music) to be selected for physical looks rather than the ability to sing. Since there are a lot more pretty faces than talented singers, that allowed the recording studios to shift more of the profit to themselves and pay less to the "talent" that is no longer talented.

AI generated visual art is already starting to pop up everywhere, and is having a similar negative function. Actual artists used to be well-paid because their talents took years to develop. Now you can generate something good-enough for free just by plugging a description into somebody's AI. It's not going to be great art, or even good art, but it will have the right elements more-or-less.

I expect we'll see a similar shift to crap like this in screenplays, especially for episodic TV but even for movies. It's free, and all they want is a consumable product to bring in money -- money they get to keep, since they don't have to pay anyone who actually knows how to produce something of genuine value. As a result, our popular entertainment will become even worse than it already is. 

It's a depressing thought. 

Playing with Chat GPT

I had read a bit about this here and there, but was not planning on messing with these Large Language Model "AIs" myself. However, I was explicitly asked to do so by a professional contact who wanted me to evaluate them. I ran three, which produced significantly different results. 

One thing I asked it to do was to explain Aristotle's ethical theory. The answer it gave was plausible at about the college level, or even at the grad school level for people who weren't specialists. The mistakes it made are mistakes that even ethicists who haven't actually studied Aristotle closely might make: for example, it claimed that Aristotle's virtues are means between two extremes. I've heard even trained philosophers make that error, because it's very close to what Aristotle does say; it's just not quite right. I decided that wasn't a good test for Chat GPT, though, because it's too easy for the kind of model it is: if it's just mapping out what experts have said about Aristotle and regurgitating it in a slightly reordered format, that's what you'd expect. Actually understanding and being able to apply the knowledge, as humans do, that's hard. Chat GPT doesn't have to understand, it just has to know that there are very frequent connections between various words that imply that using those words together in the commonly-encountered order is correct.

So the next thing I asked it to do was to diagnose a problem with a 2007 Jeep Wrangler Rubicon that I just finished resolving. It involved a poltergeist-like failure of multiple electrical systems. The answer it gave was wrong but plausible: it started with the assumption that there could be multiple system failures and walked through how to diagnose possible issues with each in turn. In fact the problem was that the ECM had gone bad, which I told it. It said that was also a possible cause of the multiple failures I described, and said it was too complex for me to fix so I should take the Jeep to a shop. I told it the shop had refused the job because the ECM was discontinued, and therefore they couldn't get parts from an authorized source. It offered four ways to obtain a functional discontinued ECM, all of which were plausible, but cautioned me that it was too complex to try to fix without substantial technical knowledge. 

In fact, it was the easiest car repair I've ever done: I bought a refurbished one from Flagship One, and just dropped it in. You do have to know which numbers are the right ones so you order exactly the right thing, and you have to take care to have it programmed to the right VIN, which you can do yourself if you buy the diagnostic software from Alfa Romeo (the parent company of Jeep, these days). But FS1 will be happy to do it for you, if you send them your VIN. Once you get the right part there are only three bolts and three electrical connections. 

A plausible reason it might have been thought difficult, which Chat GPT did not mention when I asked why it thought the repair was difficult, is that the ECM is normally located against the firewall. Getting to it is already potentially a pain. This particular Jeep, however, has had it relocated to an easily-accessed space further forward. That's something Chat GPT couldn't possibly know, and didn't; but it didn't know that I ought to have worried about the firewall issue either.

So it was wrong on several points, but the answer was still useful if I had been someone who knew little about car repair. It's not terrible even with physical technology, because a lot has been published online in various help fora. 

The third example was actually terrible, though, so I'll post it separately.

Another Afghanistan Failure

The Marine Corps' snipers are some of the best-trained in the world. The psychological operations team described is a capacity I'm less familiar with; the USMC did not field PSYOP units until very recently. 

The real story here, though, is the fact that the command structure was in complete disarray.

On August 26, 2021, Vargas-Andrews was in position at HKIA when he noticed suspicious individuals outside the gate to the airport as thousands of people were attempting to flee Afghanistan as it fell to the Taliban, fearful for the future and what retribution anyone who'd helped American forces over the previous twenty years would face. 

"I requested engagement authority when my team leader was ready on the M110 Semi-Automatic Sniper System," Vargas-Andrews said, testifying in his personal capacity. "The response: leadership did not have the engagement authority for us — do not engage."

Vargas-Andrews said he requested that his battalion commander "come to the tower to see what we did. While we waited for him, psychological operations individuals came to our tower immediately and confirmed the suspect met the suicide bomber description," Vargas-Andrews recounted. When the battalion commander "eventually arrived," he was presented with the evidence and photos of two men, one who met the description of a suicide bomber. "Pointedly, we asked him for engagement authority and permission — we asked him if we could shoot," Vargas-Andrews told lawmakers. "Our battalion commander said, and I quote, 'I don't know.'"

"Myself and my team leader asked very harshly, 'Well, who does? Because this is your responsibility, sir," Vargas-Andrews explained. "He again replied he did not know but would find out. We received no update and never got our answer." 

I find it absolutely astonishing that a battalion commander of a unit deployed at war would neither have the authority to approve a self-defense shooting nor even know who did have it. This is the most basic chain-of-command issue: who is in charge?  

The story that has been emerging from the Afghan withdrawal continues to shock. These were professional military units with decades of combat experience, led by men and women who were educated and trained in what were once the finest military science programs in the world. Yet in every aspect of this story we see a complete failure to do even the most basic tasks: 

• Plan an orderly retreat/retrograde. 
• Secure and defend the appropriate facilities (for example, by holding Bagram as the final airhead, with its many heavy lift runways and secure perimeters, rather than withdrawing to a civilian airport with only one runway and a perimeter that let the enemy get within easy mortar range). 
• Assign command authority with clear lines that everyone understands.
• Evacuate American citizens from a crisis zone.

There were many other failures as well, but some of those could be put down to the exigencies of the crisis. These were issues we had the capacity to control. We had all the time we needed to plan, because we didn't have to go at all. The enemy couldn't force us out. We had plenty of time and force to choose and secure the right airbase -- in fact, it was already secure until we abandoned it. We had plenty of time to clarify chains of command. We had plenty of time to round up all the American citizens before it became a crisis.

There is no excuse.

Oldest-yet Odin Inscription

I’m not sure how newsworthy this is, because my source is my wife sending me a Facebook link. However, I hadn’t heard of it before now. 

That may be because it’s not exactly earth-shattering. It’s an older inscription than before, but in an area where younger inscriptions have been found. It was also supposed to be a challenging translation, which also means that there might be some doubts about it. 

Still, it’s a subject of discussion here. 

A Reflection on Presence

 

Good Article on Volunteer Fire Fighters

Salina Zito writes about the decline in volunteering in America and interviews some volunteer firefighters in PA.