Wednesday, October 11, 2023

The needs of the many: determining the right side of history in Star Trek

You don't have to be a Star Trek nerd to grasp the real point of this post. I don't count myself as one. For this bit of insight  I'm going to retrofit something that Spock famously said in the 1982 movie The Wrath of Khan with one of the original series episodes.

No, it's not the episode in which Khan appears. It's one of the ones some fans consider the greatest episode of all: The City on the Edge of Forever. This one involves not just romance and saving the universe but time travel and a difficult decision to make in a form of galactic trolley problem. 

This post will contain spoilers, so if you haven't seen this yet and want to first see it, go ahead and then return to this post.

The story gets going pretty quickly when Dr. McCoy stumbles through a time portal and ends up saving a woman named Edith Keeler (played by Joan Collins) from being run over in what turns out to be Chicago in the 1930s. 


This is not an alien version but the real past with major consequences for the future.Those consequences soon come to light.  

Here's the clip in which Spock shows what happens in this alternative timeline:



The way to hell was paved with good intentions

When Edith is spared the accident, she goes on to found a peace movement that is influential enough to prevent the US from entering WWII when it did. Germany succeeds in developing the atomic bomb first and wins the war. That's very bad with consequences that extend to the present of the Enterprise crew. 

So even when Kirk declares, "I believe I'm in love with Edith Keeler," Spock responds, "Jim, Edith Keeler must die."  

While he doesn't invoke the Vulcan saying, "The needs of the many outweigh the needs of the few ... or the one," as he does in the 1982 film, this is definitely what's understood. One woman's life cannot outweigh consideration for the lives of billions of people under a monstrous regime that is extended many years and retains influence on generations.

When war is the only moral option 

Star Trek is set in a more enlightened future in which humans have advanced beyond engaging in war themselves, though they do still have to fight to defend themselves from hostile alien forces. However, as the show was actually produced in the early 60s, its creators and actors had first-hand familiarity with the horrors of WWII and the possibly-well-intentioned-yet-still-deluded people who were pushing to avoid war at any cost.

The thing about that "any cost" is that it can end up being an even more terrible price than the war itself, horrendous as it was. A regime bent on genocide becoming a world empire is worse, as they see from the way the sustained ramifications of the change in history.

In fact, there  were highly influential people like this, ranging from Neville Chamberlain's appeasement of Hitler for what he thought was the assurance of "peace for our time" to isolationists who may have really had antisemitism as their motive like Charles Lindbergh. Then there were countless others who were still haunted by WWI and believed that anything had to be better than that. 

They fell into the same mistake that Edith Keeler does, and in reality the US entered the war very late only when Pearl Harbor forced it to take direct action. Over those years of delay, Germany continued to gain ground, and the people of England suffered terribly. Plus the Final Solution got underway, and 6 million Jews were killed, along with 5 million other undesirables, including the Roma people.

In the early 1960s, people were well aware of this relatively recent history, and that is reflected in this Star Trek episode. It comes to the clearly logical conclusion that even a good person end up doing something devastatingly wrong and has to be stopped for the sake of the many and many generations. Though it breaks his heart, Kirk prevents McCoy from preventing Edith from stepping in harm's way, thus allowing her to die as predetermined and for history to take the right course without Germany winning WWII.

The moral imperative to combat the evil of terrorism 

So what has this got to do with the present? In a situation in which one set of people feels justified in attacking another because they feel slighted or they just want what they have, or they believe in jihad, it is an untenable position to say that the attacked people cannot fight back because war is bad.

Yes, war is bad, but allowing evil to grow and flourish is even worse.  Taking a passive stance, as so many Europeans did when Hitler extended his empire,  make you complicit in evil. 

That's the point of that episode. It was not acceptable to just let this alternative time line run its course. Kirk had not only allow an innocent woman to be killed but take an active part in preventing her from being saved. That was the only moral action under the circumstances. Refusing to do it would have been immoral, condemning billions just to be able to say, "I didn't kill anyone."

When people declare that the 9/11 attack was justified because the terrorists who did believed the United States needed to be taken down a peg, they are being immoral. An attack to kill thousands of innocent civilians simply because they are associated with an entity you hate is evil. Certainly, the United States went after the people behind it, and no one accused it of a war crime.

Dangerous naivete or just a double standard for Jews?

But when it comes to Israel, suddenly there's an impossible standard to meet of putting the lives of the attacking side ahead of your own men, women, and children. People seriously say that Israel may not bomb Gaza because civilians, including children are there. They may be as well-intentioned as the fictional Edith was, but what they propose is just as damaging. 

I refer to people with large Twitter (X) followings like Seerut K. Chawla @seerutkchawla who posted today: 
"How can you (correctly) condemn the recent attack on Israeli citizens but say nothing about bombing civilians in Gaza. Civilians whose food & water supply is cut off and who cannot escape. HOW."



Chawla is presenting the false argument of two wrongs don't make a right here. That's not the case in war. Certainly, Israel will not rape, torture, and mutilate women, children, and civilians and make snuff videos of such events. 

But to expect them to supply electricity and water to the people who continue to hold hostages they threaten kill on video and who continue to lob rockets at civilian areas and who slaughtered 400 cows to destroy the country's milk supply and who bombed the storehouses of food to create a shortage is frankly immoral. 

It's literally empowering the people sworn to destroy you to do so because of some mistaken idea that Israel's own children's lives count for less than any other children's lives. Are they to be allowed to continue to perpetrate such atrocities unchecked  because they use their children as human shields? That leads to more and more violence -- not peace. 

Get the context right to understand the heinousness of  what happened this past Saturday. Children were deliberately targeted and most brutally slaughtered, not to mention the women who were raped, and the other tortures and mutilations applied to the 1200+ victims of the most savage attack since the Holocaust. 

And do not dismiss this with a naive thought like "Well, yes, that was terrible, but it already happened. Vengeance will not bring back the victims." 

You think the worst is over? Think again. While this attack is definitely the worst to date, there's nothing final about it. 

In fact, over 700 admitted Hamas supporters openly held a live meeting today on Twitter (X). I took a screenshot of the group the session called "I refuse to condemn the Palestinian resistance." Taking lessons out of Goebbels' playbook, they rationalize exterminating, torturing, and raping Jews. The Nazis claimed to have reasons for their genocide, as well. 




What Churchill said


This is evil that must be checked. The Allies had to bomb Germany and harmed many civilians, including children, in order to win the war. It wasn't pleasant. They didn't relish the bloodshed, but they certainly celebrated the victory over evil forces, and this is the same situation in which Israel is at present. 

This is why the rhetoric coming out of Israel right now that people are deliberately misconstruing as a call for genocide at worst or collective punishment at best is really an echo of what Churchill said during WWII.

"Hitler knows that he will have to break us in this island or lose the war.

"If we can stand up to him all Europe may be free, and the life of the world may move forward into broad, sunlit uplands; but if we fail then the whole world, including the United States, and all that we have known and cared for, will sink into the abyss of a new dark age made more sinister, and perhaps more prolonged, by the lights of a perverted science.

"Let us therefore brace ourselves to our duty and so bear ourselves that if the British Commonwealth and Empire lasts for a thousand years men will still say, 'this was their finest hour'."

House of Commons - 18 June 1940


There is no ethical imperative to keep your citizens in danger of murder, rape, torture, and being taken hostage to avoid any civilian casualty on the other side. No one would ever dream of demanding of anyone other than Jews who have barely made it through the 20th century genocide attempts. 

Espousing a false moral code to limit what people can do to check evil allows it to flourish and for more innocent victims to fall prey to it. That is not the way. It's putting the needs of the few ahead of the many, to the ultimate devastation of all. That's the real lesson here. 



Thursday, September 7, 2023

Vermeer in Philadelphia

Seeing a Vermeer painting may warrant a trip from New York to the Philadelphia Museum of Art (PMA),  but I'm not certain that is what I saw there  

This was not a special exhibit with a masterpiece on loan like the one at the Frick I described 10 years ago. This was just a painting that had  sustained damage and was not displayed until an expert suggested it is a genuine Vermeer rather than a copy of The Guitar Player, c. 1672  that lives in Kenwood House in England.

.

The Guitar Player, c. 1672 Johannes Vermeer 


If you zoom in on the image on the Google Arts & Culture, you would see some cracks in the paint, which is to be expected after over three centuries. But that painting is still in fairly good shape, especially when you contrast it with the version that was thrown into storage and incurred a very visible rip on the lower right hand corner. That's the state of the painting you can currently see in-person in Gallery 364 of the PMA's main building. 


The Guitar Player (Lady with a Guitar) (detail), c.1670-1720, by Possibly Johannes Vermeer or a copyist (Dutch (active Delft), 1632–1675), Cat. 497


As you can see, this is essentially the same picture twice with just a variation in the sitter's hairstyle. That is why it was assumed to be a copy of the Vermeer an not treated with the greatest of care. But that changed just this year.

As the tour guide explained, and the museum site records:

 In March 2023, researcher Arie Wallert reasoned that the Philadelphia painting could be by Vermeer himself, altered at some time in its past by aggressive cleaning attempts that removed much of the artist’s uppermost finishing layers of paint....

Old restorations were removed from the painting 50 years ago, revealing exactly what remains of the original paint. The painting is on view in this unrestored condition, giving all a rare opportunity to see what researchers have been looking at for the past five decades in their search for clues of style, technique, or materials that might yet tell us—Vermeer’s own work, or another artist’s?

Wallert found that the paint samples of the paintings in question were consistent with the paints available to and used by Vermeer, including his favored shades of yellow and the very costly ultramarine blue. He also established that the canvas is from the right time period, though it doesn't quite match the ones  in the other Vermeer paintings.  

It adds up to a Schrödinger's Vermeer situation. It may be worth 9 figures, or it may only hold the value of a good copy that's about 350 years old. It has yet to be determined. For now, the museum currently lists the painting as a Vermeer in the signs on the main floor, though the paper maps do not yet include it among its "must-see" items.

If you do make the trip into Philadelphia to draw your own conclusion on the Vermeer questions, there is also a lot more to see in this museum. Crowds also line up outside to take selfies with a statue of Rocky, the boxer who made the steps of the museum famous in this iconic film scene:



Oddly enough, though, the statue doesn't show him in the basic sweats but in his boxing shorts. Capitalizing further on the Rocky association, Philadelphia plans a Rocky Run on November 11

You you may want to steer clear of the museum that day. It's challenging enough to park nearby as it is, though I recommend you look around the numbered streets in the mid 20s perpendicular to Green street. .

The museum charge $30 for admission and  grants a mere $2 discount for seniors over 65. Students with valid ID pay $14, and kids under 18 get in free. To save on the admission cost, you can plan to go one of the "pay what you wish occasions." That's every Friday after 5 PM (the museum stays open until 8:45 on Fridays) and the first Sunday of each month.

The site still is showing timed tickets that you can purchase in advance, but  you really can just show up when you want and buy the ticket on the spot.


Related:

Jane Austen at the Morgan


Monday, August 28, 2023

Add a pinch of salt to creative claims for AI

Moira Rose on "Schitt's Creek" saying, "That doesn't sound right."


Sometimes someone or even somethings -- as in the case of generative AI -- will confidently assert something to be true. Don't suspend your disbelief. Investigate and demand the basis for that claim. 

Creative  lies from AI


Having investigated the output of both Chat GPT and Bard, I have concluded that you always have to fact-check whatever generative AI tells you because it is prone to what is called hallucinations. 

In fact, as related in The perils of prompt engineering, Bard  does not hesitate to fabricate facts and will double-down on its assertions with even more hallucinational as it spins out an even more elaborate web of AI-generated reality. 

While I remain baffled about what motivates AI to generate false information when it should have access to all the data necessary to report accurately,I can't say that humans have a monopoly on data-backed truth. They may not fabricate editions out of thin air, but they are quite prone to fabricate conclusions on the flimsiest of pretexts.

coarse salt scooped with a wooden spoon


To profess is human 


Unlike the AI thought process, I can understand the human motivation in this case.  Human want to make a name for himself (really it is most often a he) about an area and knows that saying something surprising will get more attention than reporting what people expect. 

Knowing that some kind of apparently scientific approach is needed to justify the claim,the person just draws on a handful of students, gives them the task, and draws conclusions that turn into a major claim based on those very limited results. 

I've read a lot of Dan Ariely books and really enjoy his insights into human responses and triggers. But I always take them with a grain or two of salt. 

That's because the majority of his experiments involve a tiny, not terribly diverse segment of the population, namely the undergraduates at the university who can be induced to participate. Often that means that his conclusions are based on just two dozen people or so. 

The small sample size doesn't guarantee that the conclusions are incorrect. However, assuming that it is conclusive proof is the classic logical fallacy of hasty generalization. 

What he does with whichever group of students happen to pass by that today is not necessarily replicable by the population at large. It's kind of like just polling your siblings or neighbors to conclude that everyone's favorite flavor of ice cream is chocolate. That may be true, but we'd really need a bigger sample size to be sure.


Claiming AI is more creative than humans

Yet who can fault Ariely for doing this when everyone else does it? Indeed, that is precisely what  Erik Guzik, Assistant Clinical Professor of Management at University of Montana did for is article in The Conversation entitled  "AI scores in the top percentile of creative thinking." 

What does a person who just reads that title think was involved in making such a claim for AI creativity?  It sounds like thousands of creative people were compared to the AI to determine that its output was comparable to the top 1%.

But that's not what happened at all. Instead, this major claim is based on nothing more than 24 students whose output was deemed to be not all that creative relative to the output of ChatGPT(after 4 iterations, it sounds like) based on the assessment of the Torrance Tests of Creative Thinking, or TTCT.

We get very little shared about what the process for the students was and how they scored. The only clue we get about the creative prowess of ChatGPT is the professor's assertion:


Consider the following prompt offered to GPT-4: “Suppose all children became giants for one day out of the week. What would happen?” The ideas generated by GPT-4 touched on culture, economics, psychology, politics, interpersonal communication, transportation, recreation and much more – many surprising and unique in terms of the novel connections generated.

This combination of novelty and utility is difficult to pull off, as most scientists, artists, writers, musicians, poets, chefs, founders, engineers and academics can attest.

Yet AI seemed to be doing it – and doing it well. 



Notice that the professor is merely telling us that ChatGPT did well. He fails to show us the creativity by sharing the actual output and letting us see a contrast between it and even one of the 24 students who may well have all been math or engineering majors who don't considers themselves creative writers at all.
 

My own test

This is not a strict replication because I had to use ChatGPT3.5 instead of 4, but it should still show what most people would actually get when putting exactly that prompt to the generative AI. Here's its response enclosed in rows of stars:

*************************************************************************

If all children were to magically transform into giants for a single day each week, the world would undoubtedly witness a fascinating array of changes and events:

  1. Physical Transformations: The sudden change in size would lead to various practical adjustments. Everyday items like furniture, clothing, and even vehicles might need to be redesigned or adapted to accommodate the giant children.

  2. Playful Activities: Children would engage in unique and imaginative activities that capitalize on their newfound size. Parks and playgrounds would transform into vast landscapes for epic games, obstacle courses, and adventures.

  3. Exploration: With their enhanced height, children could explore their surroundings from a different perspective, possibly leading to new discoveries or insights about their environment.

  4. Education and Learning: Schools might introduce special days to leverage the giants' size advantage for educational purposes. Science classes, for instance, could involve experiments that demonstrate the effects of size on various phenomena.

  5. Social Interactions: The dynamics of social interactions might shift as children grapple with their changing sizes. Friendships could take on new dimensions, and children might learn valuable lessons about empathy and acceptance.

  6. Impact on Economy: The demand for goods and services tailored to giant children could create unique economic opportunities. Businesses might offer oversized toys, clothing, and other products on the designated giant day.

  7. Environmental Impact: The increased scale of activities could lead to concerns about environmental effects. Authorities might need to manage waste, traffic, and other logistics associated with giant-sized activities.

  8. Scientific Exploration: Scientists and researchers would be intrigued by the temporary transformation and could use the opportunity to study the physiological, psychological, and ecological impacts of such a phenomenon.

  9. Creativity and Art: Artists and creators would likely draw inspiration from the whimsical idea, resulting in a surge of giant-themed literature, artwork, movies, and more.

  10. Sense of Wonder: The experience of becoming giants would foster a sense of wonder and imagination among children, encouraging them to think beyond conventional boundaries and consider new possibilities.

Overall, a day when all children become giants would be a remarkable and unforgettable event that would influence various aspects of society, culture, and individual experiences. It would provide a unique chance for children and adults alike to see the world from an entirely different perspective and explore the imaginative and transformative power of change.

************************************************************************

Color me not impressed. This is just an analysis of various points of view one can take on such a scenario presented in a fairly analytical way. It's not at all what I consider creative output. What would be creative is to construct a story in which some -- but not all -- of the possibilities delineated would be manifested. But simply listing them as possible considerations is analytical rather than creative thinking.  

Visit WriteWayPro.weebly.com  Like and follow on Facebook and on LinkedIn

Related: Why you always need the original source  A matter of degree Bard vs Bard


 

Tuesday, August 8, 2023

The perils of prompt engineering





You may have noticed a few people who formerly called themselves writers or content creators now calling themselves "prompt engineers." This title gives a veneer of a more scientific credentials to what really amounts to playing around with Chat GPT or Bard or some of the lesser-known generative AI tools out there to elicit the response you seek.


At present, though, there is absolutely no licensing or testing to "prove" oneself as a prompt engineer. It's a self-declared title that can't really be disproven until we come to a stage where Microsoft, Google, or OpenAI decide to make it an official credential. 

You get to call the shots and take credit for when the generative AI delivers. Sounds ideal, right? 

It might have been -- if only you really could wholly rely on the AI to be accurate. Unfortunately, you can't. You have to fact-check everything it assert, no matter how confident it may sound about it. 


Here Be Hallucinations

Why is that? Generative AI has learned to fabricate facts to back the narrative it's constructing. 

This is what has come to be called "hallucinations," though I really don't like the term because it makes it sound like what humans experience from external forces acting on their minds. No one seems to be giving generative AI the equivalent of mind-altering drug to prompt it to come up with this --sometimes rather elaborate -- hallucinations. 

Bard Gets Creative 

 Bard got incredibly expansive in one hallucination, positing an edition of Ben Horowitz's book The Hard Thing About Hard Things that doesn't exist. I asked it if the book ever references Built to Last, an extremely popular and influential business book from the late 20th century, when I noted some striking similarities and even the same title  for a chapter at the end of both books.   

Bard answered:
The passages where Ben Horowitz mentions "Built to Last" explicitly in his book "The Hard Thing about Hard Things" are on the following pages:
Chapter 6: The Flywheel, page 125
Chapter 10: Core Ideology, page 197


I countered that the pages and chapter titles didn't correspond to the copy of the book I had in front of me, and so it compounded the original hallucination as follows:  and it answered:

The passages where Ben Horowitz mentions "Built to Last" explicitly in his book "The Hard Thing about Hard Things" are on the following pages:
Chapter 6: The Flywheel, page 125
Chapter 10: Core Ideology, page 197


Say What?

I countered that the pages and chapter titles didn't correspond to the copy of the book I had in front of me, and so it compounded the original hallucination as follows:

You are correct. The pages I provided correspond to the 2015 edition of the book. The 2014 edition has different page numbers. The passages where Ben Horowitz mentions "Built to Last" explicitly in the 2014 edition are on the following pages:
Chapter 6: The Flywheel, page 107
Chapter 10: Core Ideology, page 177

It then went on to explain that that the chapter titles were changed:

You are correct. The chapter names in the 2014 edition of "The Hard Thing about Hard Things" are different from the chapter names in the 2015 edition. The chapter that I referred to as "The Flywheel" is actually called "Concerning the Going Concerns" in the 2014 edition. The chapter that I referred to as "Core Ideology" is actually called "The Ideology of Success" in the 2014 edition.
I apologize for the confusion. I have updated my previous response to reflect the correct chapter names.

It sounds pretty credible until you look for the 2015 edition of this book and find it never existed. Bard simply created this out of thin air and went on to support the fiction with additional details.



This is very dangerous for anyone who is not by nature as skeptical as I am. Most people would likely accept that if Bard can give an account of an edition of a book as detailed as this, its must really exist. In fact, though, you'd have to not be taken in by the confidence of the assertion and do your own due-diligence.

I'd say that would be the real work of the prompt engineer today: not just coming up with the request for information but rigorously questioning the results and doing your own research to be certain that they're not the product of hallucinations.

Related: