Thursday, April 27, 2023

If BARD is a poet, I wouldn't know it

 kw: analysis, artificial intelligence, experimental linguistics, poetry


My first queries to BARD were related to Shakespeare. BARD bungled the iambic meter of a soliloquy. I decided to try poetry in a more general sense. I will comment in each section.

P07: There are 3 kinds of photosynthesis: C3, C4 and CAM. Please write a sonnet about photosynthesis in the Italian rhyming style.

Bard: Sure, here is a sonnet about photosynthesis in the Italian rhyming style:

Photosynthesis

The leaves unfurl, the sun shines bright,
And plants begin their daily flight.
They take in carbon dioxide,
And water from the ground below.
 
They use the energy from the sun,
To turn these things into one.
A sugar called glucose,
And oxygen, which is released into the air.
 
There are three main types of photosynthesis,
C3, C4, and CAM.
Each type has its own advantages and disadvantages,
And they are all used by different plants.
 
C3 photosynthesis is the most common type,
And it is used by most plants.
It is not as efficient as C4 or CAM photosynthesis,
But it is less demanding of water.
 
C4 photosynthesis is more efficient than C3 photosynthesis,
But it requires more water.
It is used by plants that live in hot, dry climates,
Such as cacti and succulents.
 
CAM photosynthesis is the most efficient type of photosynthesis,
But it is also the most demanding of water.
It is used by plants that live in very hot, dry climates,
Such as cacti and succulents.
 
No matter what type of photosynthesis they use,
All plants play an important role in the environment.
They help to clean the air,
And they provide food and oxygen for animals.

A sonnet has 14 lines. Here we have 28. The Italian rhyming style is ABBAABBA CDECDE, although there are various ways the last six lines are handled, including CDCDCD and CDDCDD. None of the quartos above has an ABBA rhyming pattern. Also, sonnets are typically in iambic meter, but none of that is found here.

P07: Please write a limerick about a coder named Larry

Bard: Sure, here is a limerick about a coder named Larry:

There once was a coder named Larry,
Whose code was as tight as a curry.
He could write in any language,
From C++ to Python,
And his programs always ran merrily.

This limerick was in a box, so maybe Bard copied it from somewhere…but it doesn’t rhyme lines 3&4. There were two other drafts:

There once was a coder named Larry,
Whose code was quite hairy and scary.
He said, "I'll rewrite it,
But first I must write it,
Then I'll test it, and then maybe I'll marry."
 
There once was a coder named Larry,
Whose code was quite hairy.
He said, "I'll rewrite it,
So it's not so tight,
And maybe I'll get a raise, maybe."

The first alternate draft is a near-perfect Limerick; just remove "and" from the last line. The other draft, and the original version, are quite klutzy.

P07: Describe the common feet in prodosy: iamb, trochee, anapest, dactyl, and spondee

Bard: Sure. In prosody, a foot is the basic repeating rhythmic unit that forms part of a line of verse. The most common feet in English are the iamb, trochee, anapest, dactyl, and spondee.

Iambic

An iamb is a two-syllable foot with an unstressed syllable followed by a stressed syllable. For example, the word "today" is an iamb, with the unstressed syllable "to" followed by the stressed syllable "day."

Trochaic

A trochee is a two-syllable foot with a stressed syllable followed by an unstressed syllable. For example, the word "about" is a trochee, with the stressed syllable "a" followed by the unstressed syllable "bout."

Anapestic

An anapest is a three-syllable foot with two unstressed syllables followed by a stressed syllable. For example, the word "telephone" is an anapest, with the two unstressed syllables "tele" followed by the stressed syllable "phone."

Dactylic

A dactyl is a three-syllable foot with a stressed syllable followed by two unstressed syllables. For example, the word "hammer" is a dactyl, with the stressed syllable "ham" followed by the two unstressed syllables "mer."

Spondaic

A spondee is a two-syllable foot with two stressed syllables. For example, the word "forever" is a spondee, with both syllables "for" and "ever" stressed.

These are just a few of the most common feet in prosody. There are many other types of feet, as well as more complex meters that combine multiple feet.

The descriptions are good but not all the examples are apt. “About” is not a Trochee but an Iamb; a better choice would have been “under”, or the example used for Dactyl, “hammer”. A better choice for a Dactyl would have been “murmuring” or “mockingbird”. “Forever” is not a Spondee but an Amphibrach (rare as a repeated foot in English poetry); a better choice for a spondee would be a “smokestack”, or more common examples of repeated one-syllable words such as “woe, woe!”. In another draft, BARD used these apt examples: “report”, “daily”, “serenade”, “merrily”, and “he who”. A third draft used some four-syllable words as examples!

That's enough. I have read here and there about the poetic abilities of ChatGPT. I suspect they are overhyped. I didn't ask BARD to write free verse, which I don't consider to be verse at all. Maybe that's what folks have written about.

Wednesday, April 26, 2023

Mathematical models, useful and otherwise

 kw: book reviews, nonfiction, mathematics, modeling, simulation, cautions, analysis

For a significant part of my career I worked with a group of talented computer programmers in a "skunk works" at an oil company. A colleague and I made up the Modeling and Simulation sub-group among the 20 members of the group. He and I developed software that simulated the production of crude oil and natural gas from kerogen, their migration upward through rock layers, and their accumulation against a trapping layer. No model is useful until it is checked against the real world, what we called "getting ground truth". I visited several exploration offices to show off the software and to use it with data those offices had on hand.

One memorable day in Louisiana, an explorer showed me the 3D seismic survey of one area. He pointed out the most likely source rock and explained the character of other layers, so we entered the appropriate setup parameters, "pointed" the software at the survey data, and let 'er rip. It showed progress over time, of the filling of trapped pools, as growing green blobs on a series of maps. He said, "OK, that blob is 'X' field, that one is 'Y' field,…but what is that?", pointing to a third blob between the other two. I answered, "I don't know, but I suspect it represents a lot of money." As it happened, the company had leases that covered most of the "what is that" area, but a deal had already been made to sell the leases to another company. That company made the money!

I had less exciting encounters with exploration geologists in Europe. The result was the validation of a useful model. Getting "ground truth" turned a simulation program into a tool the geologists could use to rank prospects.

Let me say right now that this tool is a million times less complex than the "general circulation models" (GCMs) used to forecast weather. Crude oil is gummy and moves slowly; air masses in the atmosphere, which are the elements of weather, move rapidly and swirl around on all scales. Oil forecasting is hard, but not as incredibly difficult as weather forecasting. So I was never faced with an irate caller complaining about "shoveling a foot of 'partly cloudy' from [his] @#&% driveway!"

Furthermore, I had the great good fortune to decide early in my career to "let the singers sing and the dancers dance": to turn over to the computer those tasks that are hardest for humans, while retaining tasks for the humans that we do better than computers. This led to very productive synergies. Far too many programmers spend years beating their heads against the wall trying to replace the human element. Futility personified.

I was delighted to read Escape From Model Land: How Mathematical Models Can Lead Us Astray and What We Can Do About It by Erica Thompson. She sets the tone early on by quoting statistician George Box: "All models are wrong, but some are useful." Those who forget to think this way, or never heard this aphorism, get stuck in Model Land.

The author continues with the observation by President Dwight Eisenhower, that "Plans are useless, but planning is indispensable." The thinking behind the model, or the plan, is the great value of the exercise. I also recall what Sun Tzu wrote in The Art of War, "No battle plan survives contact with the enemy." In more peaceable pursuits, contact with "ground truth" exposes the errors of every model. It is our task to determine the tolerable level of error, for we must typically carry on anyway.

A model is a tool. It can help us understand a process, and perhaps inform the solution to a problem. BUT no model solves any problem all by itself. Even better than one model, a suite of models, built with various assumptions and focusing on different sets of driving parameters, can help us set boundaries on the range of outcomes.

It doesn't seem so long ago that the fastest supercomputer needed to run for half a day to produce a 2- or 3-day forecast for a continent-sized area. Now numerous GCMs exist, and the weather forecasters collect the output from all of them. One result is a spaghetti plots of hurricane tracks. In this image, the letter codes such as COTC represent the names of the models used. The characteristics of a spaghetti plot are used to produce the "cone of likelihood" that is often shown.

The situation with climate modeling is far different. Escape focuses on two areas, because of current events. One is climate "change" (spoiler: it is always changing, but on a slow time scale) which is all based on modeling because we can't perform physical experiments. The second is the epidemiology of COVID-19, modeled numerous ways, and almost never properly! The disease fooled the "experts" almost daily, and the societal flailing around that resulted seems to have caused more harm than doing nothing. I called the CDC the "strategy of the week club."

Both phenomena became so intensely politicized that no actual science has been possible. A certain spokesman whose name I hate to utter said, "I am the science." Tantamount to blasphemy. Another group of mostly pundits and a few scientists bludgeoned the public with the notion of "settled science." There is no such thing, except perhaps certain portions of mathematical physics. Neither climate and weather, nor epidemiology, are amenable to mathematico-physics treatment.

I am an educated layman. I went to school in an era in which we were taught critical thinking, and learned to identify bias. Putting on those hats, I can say the following, first about climate, and then about the pandemic.

1) I learned to apply the mathematics used by Arrhenius to study the Greenhouse Effect before I was in high school. The simplest model of the atmospheric response to sunlight with respect to CO2 has four spectral regions:

  1. The Ultraviolet-Visible-Near Infrared region: wavelengths that are not affected by CO2.
  2. Three narrow bands of Medium Infrared in the range 2.5µ-4.5µ, one of which is fully lapped over by an absorption band of water vapor. These have little warming effect, but they are well positioned for optical CO2 detectors.
  3. A moderately wide band of Longwave Infrared centered on about 14µ, of absorption by CO2; the amount of absorption depends on the concentration. This is the "thermal IR" band of interest.
  4. The rest of the Infrared spectrum, Far-Infrared and so on; it is not affected by CO2.

Within region #3 there is a variable level of absorptivity, but once the concentration of CO2 reaches 0.2% (2,000 ppm, comparable to the level during the age of the dinosaurs), the "carbon dioxide window" is effectively "closed". At that point, within that wavelength region, about half of the infrared radiation from the warm ground is absorbed by the atmosphere and is reradiated, half to outer space, and half back down. At a specific temperature a balance is achieved. That temperature is 4°C warmer than the average global temperature in the year 1900. Today, with 400 ppm, we're at 2°C, and it will take much more than another 400 ppm to push into that +4°C region. The relationship is not linear.

What detailed computer modeling can do is to show where the warming is greater, and where it is less. We've been hearing for years that the warming is greater in the polar regions and less in the tropics. The general picture is 6°-7°C warming around the poles and less than 3°C warming in the tropics, when CO2 concentration exceeds 1,000 ppm. At this point the "window" is mostly closed already; extra warming greater than 1°C is unlikely.

The above discussion means that warnings about deadly heat waves in the tropics are overblown. On the other hand, we can expect some frozen polar areas to thaw. One effect I haven't heard the slightest discussion about is that Siberia, northern Canada, and the southern part of South America could be the next breadbaskets. Will the Sahara and Mojave/Sonoran deserts, in Africa and North America, respectively, get even drier and hotter? The computer models are inconsistent. Fretful silence on these questions reflects the uncertainty.

2) The situation of the COVID-19 pandemic, and the incredible array of opinion/ideology presented as "science" is a stunning spectacle. Roughly half the adults in the U.S. think that the crisis was exploited to the hilt for political purposes, partly to remove Donald Trump from office and even more to increase the scope of totalitarian control on the part of the Left. Meanwhile, the other half are thrilled that Trump is out of office, but ambivalent about J.R. Biden's performance.

If there has been any serious modeling of the epidemiology of the C19 virus, I haven't seen it. I've seen numerous toy models presented, followed by lots of screaming to "follow the science". When it became evident that actual science contradicts what the screamers are saying, they took up new mantras about "protecting Democracy" (which really means protecting political power for Democrats). Sadly, I still see people walking alone in near-isolation, wearing a bandanna or cheap mask or, if they have an actual N95 or KN95 mask, wearing it below the nose. Firstly, they are insane to wear the mask at all, and secondly, the "face covering" they are using is not effective. Close to 0%. Nearly everyone who caught C19 after mid-2020 was wearing a mask when they caught it.

There is one and only one valid reason to wear a mask outside, anywhere there is no crowd: To keep the sun off one's face. My wife does this. She wears a mask to keep her cheeks from getting burnt when doing yard work. Never any other time!

There are three simple models that can be used to understand the risks of contracting the COVID-19 virus, SARS-COV2, when outside, with or without a mask. Firstly, except in very humid weather, the virus aerosolizes rapidly. The tiny droplets that a mask would stop evaporate completely in just a few minutes. You can look up the formula (the first "model") to calculate how long a droplet of size 1µ or 5µ will evaporate, at different levels of humidity. That means that the virus particles, which have a diameter of about 120nm (0.12µ), are what your mask has to stop. This introduces the second model.

A N-95 mask is called that because it catches 95% of particles (virus or otherwise) in the size range near 300nm, where the mask is least effective. It is very nearly 100% effective for larger particles (which are caught mechanically) and smaller particles (which are caught electrostatically). Particles in the 120nm range are caught electrostatically with an efficiency near 97%. Think a moment. If there are few viruses about, only 3% of them will get through the mask, if you wear it correctly. But suppose you enter a very crowded area that includes perhaps half a dozen folks who are coughing out C19 particles. Then, 3% of that viral load may well be enough for you to be infected. It is a numbers game.

Thirdly, during the daytime the C19 virus is about twice as susceptible to being disabled by solar ultraviolet as the Ebola virus. I worked out the numbers: Between 10 AM and 2 PM solar time, 90% of virus particles exposed to sunlight are inactivated within about 45 minutes. During the next 3/4 hour, 90% of whatever is left is inactivated, and so forth. It's a statistical function, now long it takes before a UV photon strikes a particular virus particle in a vulnerable spot.

Now we can pull back from my cogitations and look at the book's conclusions. The main problem with any model is the person who uses it. A model will give definite results, but it is easy to forget that those results pertain to the model, not to the system being modeled. They may be close, or they may not. But properly used, a model helps you think about a system of interest. It can't decide for you! Letting models do the deciding is always, always, a travesty.

What does the author suggest? How can we escape from Model Land? Five points form the meat of the last chapter:

  1. Define the purpose. That purpose better not be "decide for me." The purpose has to include capturing the relationship between all the relevant parameters and the results. All...but learn what to neglect.
  2. Don't say, "I don't know". Ask, "What do I know now that I didn't know before?"
  3. Make value judgments. Every model reflects someone's values. Make sure the values behind the structure of a model are the right ones. Remember: genuine science is value-free. YOU supply the values.
  4. Write about the real world. Bring the model's conclusions into the real world, by getting "ground truth", for example.
  5. Use many models. Consider the spaghetti plot of the hurricane, shown above. If the system is "too simple" for multiple models to be generated, perhaps it is simple enough to comprehend without mathematical modeling.

It takes work just to understand this list. It is worth it! It takes much more work to carry out a modeling exercise that doesn't trap you in Model Land without an exit. I used a Jumping Ship metaphor at the start of this piece to show that sometimes we need to get far away, to seek a really different perspective. This is an extension of Principle #5 above.

Finally, consider this: You have two eyes for a reason. It is not just for parallax, to find out the 3D aspect of the situation. It is for completeness. Except in very simple views, your right eye will see something your left eye cannot, and vice versa. Even more, if you have someone standing near you, each of you will see things the other does not, particularly if you're looking in different directions. Using a numerical or mathematical model in too simple a manner, and yielding too much authority to it, is like viewing a complex scene using one eye from one viewpoint. I leave you with this proverb: "If two people have exactly the same opinion about everything, one of them is redundant."

This book is a great read!

Monday, April 24, 2023

BARD figures it out

 kw: analysis, artificial intelligence, experimental linguistics, mathematics, computer science

Continuing my exploration of the capabilities of BARD, I asked it about some computational and mathematical matters, starting with one that was relevant to recent work I have been doing. I'll comment along with each interaction this time.

P07: Two angles are related by the function A = arctan(sec B * tan B). Given A, what is B?

Bard: The given function is not invertible, so there is no unique value of B that corresponds to a given value of A. This is because the tangent function is periodic, with a period of 180°. This means that for any value of A, there are infinitely many values of B that will satisfy the given function.

For example, if A=45, then B could be any value in the range (−45, 45). Or, if A=90°, then B could be any value in the range (−90°, 90°).

In order to find a specific value of B that corresponds to a given value of A, you would need to specify additional information about the problem. For example, you might know that B is an acute angle, or that B is a right angle.

P07: In the above problem, both A and B are in the range 0° to 90°.

Bard: In that case, there are two possible values of B for any given value of A. For example, if A=45°, then the two possible values of B are 45° and 135°. This is because the tangent function is positive in the first and third quadrants, so the two possible values of B are the two angles in the first and third quadrants that have a tangent of 1.

In general, the two possible values of B can be found by solving the equation

[recast by P07]                  tan B = ± tan A / sec B

For example, if A=45°, then this equation becomes

[recast by P07]                  tan B = ±tan 45° / sec B = ±1 / √2

Solving this equation, we find that the two possible values of B are 45° and 135°.

The original statement is correct, though not only for the reason BARD presented. This is an example of a Trapdoor Function. If angle A is known, it is straightforward to calculate angle B. But if only B is known, finding A requires an iteration, such as successive applications of Newton's Approximation.

BARD treated this like a Diophantine problem, and ignored the restriction of B to (0°, 90°). Further, the answer is incorrect. Tan 45° = 1, sec 45° ≈ 1.414, so 1 is being equated to √2.

P07: Are you able to chart a function?

Bard: Yes, I can chart a function. I can use the following steps to chart a function:

1.       Identify the domain and range of the function.

2.       Choose a few values of x and calculate the corresponding values of y.

3.       Plot the points (x,y) on a graph.

4.       Connect the points with a smooth curve.

For example, let's chart the function y=x2. The domain of this function is all real numbers, and the range is all non-negative real numbers. We can choose a few values of x, such as x=0,1,2,3, and calculate the corresponding values of y, such as y=0,1,4,9. We can then plot the points (0,0), (1,1), (2,4), (3,9) on a graph and connect them with a smooth curve. The resulting graph is a parabola that opens upwards.

P07: Can you draw the chart?

Bard: I can't draw a chart for you here, but I can give you a description of the chart of y=x2.  The chart is a parabola that opens upwards. The vertex of the parabola is at (0,0). The x-axis is the line of symmetry of the parabola. The parabola approaches the x-axis asymptotically as x approaches ±.

This is just as I expected; BARD is linguistic in nature, and has no graphical capabilities...yet!

P07: What is the integral of Sqrt(sec(x)*tan(x))?

Bard



The line above needed to be a picture.

To solve this, we can use the following steps:

  1. Let u = sec x. Then du = sec x tan x dx.
  2. Substituting gives us:

Code snippet

∫√sec(x)tan(x)dx = ∫√u du = 2√u + C = 2√sec(x) + C

where C is an arbitrary constant of integration.

P07: Can a computer store the exact value of an irrational number?

Bard: No, a computer cannot store the exact value of an irrational number. This is because computers store numbers in binary, which is a finite representation of numbers. Irrational numbers are infinite, so they cannot be represented exactly in binary.

For example, the number π is irrational. It is a non-repeating, non-terminating decimal number. This means that there is no finite sequence of digits that can represent π exactly. If we try to store π in binary, we will only be able to store an approximation of it.

The same is true for all other irrational numbers. They cannot be stored exactly in binary, so they can only be approximated.

However, this does not mean that computers cannot use irrational numbers. They can still perform calculations with irrational numbers, as long as they are aware that the numbers are being approximated.

The only quibble I have with this answer is the word "they" in the last sentence. Computers aren't aware of anything. It should read, "…as long as those using the program are aware…"

P07: What is Green’s Theorem?

Bard: Green's theorem is a theorem in vector calculus that relates a line integral around a simple closed curve C to a double integral over the plane region D bounded by C. It is the two-dimensional special case of Stokes' theorem.

In mathematical terms, Green's theorem states that

Code snippet

∫CFds=D(curl F)k dA

Use code with caution. Learn more [link to https://bard.google.com/faq#coding]

where

  •         F is a vector field defined on a two-dimensional domain D
  •         C is a simple closed curve in D
  •         ds is the line element along C
  •         dA is the area element in D
  •         curl F is the curl of F, which is a vector field that measures the circulation of F around a point
  •         k is the unit vector in the z-direction 

Green's theorem can be used to solve a variety of problems in physics, engineering, and mathematics. For example, it can be used to 

  •         Calculate the flow of a fluid through a region
  •          Determine the area of a plane figure
  •          Find the centroid of a plane figure
  •          Solve boundary value problems

 Green's theorem is a powerful tool that can be used to simplify and solve a wide variety of problems in vector calculus.

BARD then referred to the Wikipedia article on Green’s Theorem, and suggested three Google searches on the topic. I then asked about one term used in the description.

P07: What is the curl of a function?

Bard: In vector calculus, the curl is a vector operator that describes the infinitesimal circulation of a vector field in three-dimensional Euclidean space. The curl at a point in the field is represented by a vector whose length and direction denote the magnitude and axis of the maximum circulation. The curl of a field is formally defined as the circulation density at each point of the field.

In other words, the curl of a vector field is a vector that measures the rotation of the field around a point. The curl is zero at points where the field does not rotate, and it is nonzero at points where the field does rotate. The direction of the curl vector indicates the direction of the axis of rotation, and the magnitude of the curl vector indicates the magnitude of the rotation.

The curl of a vector field can be calculated using the cross product. The cross product is a mathematical operation that takes two vectors and produces a third vector that is perpendicular to both of the original vectors. The direction of the cross product vector is determined by the right-hand rule.

The curl of a vector field can also be calculated using the curl operator. The curl operator is a mathematical symbol that represents the curl of a vector field. The curl operator is written as a counterclockwise cross product, and it is applied to the vector field.

The curl of a vector field has many applications in physics and engineering. For example, the curl of the velocity field of a fluid is used to calculate the vorticity of the fluid. The vorticity of a fluid is a measure of the rotation of the fluid. The curl of the electric field is used to calculate the magnetic field. The magnetic field is a vector field that describes the direction and magnitude of the magnetic force.

The curl is a powerful tool for analyzing the behavior of vector fields. It can be used to calculate the rotation of a vector field, the vorticity of a fluid, and the magnetic field. The curl is an important tool in physics, engineering, and other fields.

BARD referenced a Wikipedia article on the subject. In an alternate draft BARD added:

The curl of a vector field F is denoted by × F. In three dimensions, the curl can be computed using the following formula:

Where F1, F2, and F3 are the components of function F.

Not being a vector calculus expert, I had to ask for the definition of the inverted delta.

The symbol is called the nabla symbol. It is a triangular symbol resembling an inverted Greek delta: \nabla or . The name comes, by reason of the symbol's shape, from the Hellenistic Greek word νάβλα for a Phoenician harp, and was suggested by the encyclopedist William Robertson Smith to Peter Guthrie Tait in correspondence.

In mathematics, the nabla symbol is used to represent the gradient operator in calculus. The gradient is a vector that points in the direction of the greatest rate of change of a function, and its magnitude is equal to the magnitude of the rate of change.

The nabla symbol can also be used to represent other vector operators, such as the divergence and the curl. The divergence is a vector operator that measures the outward flux of a vector field from a surface, and the curl is a vector operator that measures the circulation of a vector field around a point.

The nabla symbol is a powerful tool that can be used to represent a variety of vector operators in mathematics. It is an important symbol in vector calculus and has many applications in physics, engineering, and other fields.

Sources:

  1. brainly.in/question/12687051 
  2. en.wikipedia.org/wiki/Nabla_symbol 
  3. mathoverflow.net/questions/289607/mathematical-objects-whose-name-is-a-single-letter  

BARD did what I would have done, look these things up in Wikipedia and math sources such as those it listed following its response. Green's Theorem was the bugaboo of a Senior-level course in Physics I took many, many years ago.

Here we see BARD doing less linguistic generation and more copying of sources.




Saturday, April 22, 2023

Bard versus BARD

 kw: analysis, artificial intelligence, experimental linguistics

I was invited by Google to use BARD, their version of ChatGPT. I decided to do various experiments, not to "trip it up", as some have done, but to learn its range. In the terminology of generative language models, faulty results are called "hallucinations". The process used by BARD and its kin to produce responses is a kind of stream-of-consciousness musing based on probabilities, so in my view, it's all hallucinatory anyway! And when it's wrong, it's just wrong.

I first tested BARD against The Bard with three prompts. I will comment after the transcript of the three results.

P07: Write a short summary, up to 300 words, of The Tempest by Shakespeare.

Bard: The Tempest is a play by William Shakespeare, probably written in 1610–1611, and thought to be one of the last plays that he wrote alone. After the first scene, which takes place on a ship at sea during a tempest, the rest of the story is set on a remote island, where Prospero, a complex and contradictory character, lives with his daughter Miranda, and his two servants: Caliban, a savage monster figure, and Ariel, an airy spirit. The play contains music and songs that evoke the spirit of enchantment on the island. It explores many themes, including magic, betrayal, revenge, and family.

Prospero is the rightful Duke of Milan, but he was usurped by his brother Antonio and his allies, the King of Naples and Sebastian. Prospero and his infant daughter Miranda were set adrift at sea, but they survived and landed on the island. Prospero used his magic to create the storm that shipwrecked his enemies on the island. He then uses his magic to control the events on the island, manipulating his enemies and testing their characters.

Prospero's main goal is to get revenge on his enemies, but he also wants to teach them a lesson about the consequences of their actions. He eventually forgives them and returns them to their rightful places in society. The play ends with Prospero giving up his magic and returning to Milan with Miranda and Ferdinand.

The Tempest is a complex and fascinating play that explores many themes. It is a story of magic, betrayal, revenge, and redemption. It is also a story about the power of love and the importance of forgiveness.

P07: Write a short soliloquy in iambic pentameter on the subject of triumph over loss.

Bard: I have lost all that I held dear,
My loved ones taken from me so soon.
I have fallen to my knees in despair,
And begged for the pain to just end soon.
 

But then I remembered something I had heard,
A saying that gave me new strength and resolve.
It said that even in the darkest of hours,
There is always hope, if we just believe.
 
So I picked myself up off the ground,
And wiped away my tears.
I knew that I had to keep going,
For the sake of those I had lost.
 
I would not let their deaths be in vain,
I would live my life to the fullest,
And make them proud.
 
I would triumph over loss,
And find joy in the world again.

[This one had two other Drafts]

 2) Soliloquy

I have lost so much, I have lost it all.
My dreams, my hopes, my loves, they all have fled.
I am left here with nothing, not even a shred
Of what I once had, of what I once held dear.
 
But I will not give up. I will not despair.
I will find a way to triumph over this loss.
I will find a way to rebuild my life, to start anew.
I will find a way to be happy again.
 
I know it will not be easy. It will take time and effort.
But I am strong. I am resilient. I will not give in.
I will triumph over this loss. I will find my way back to happiness.
 
I know that I am not alone. There are others who have lost as much as I have.
And they have found a way to move on. They have found a way to be happy again.
So I will not give up. I will find my way back to happiness.
 
I will triumph over this loss.

 

3) 

I have lost so much in this life,
I have loved and lost, and loved again.
I have cried and laughed, and felt the pain
Of heartbreak and the joy of gain.
 
But through it all, I have learned to triumph.
I have learned to rise above my pain,
To find the strength to go on,
Even when all seems lost.
 
I have learned that loss is a part of life,
But it does not have to define me.
I can choose to let it destroy me,
Or I can choose to use it as fuel to grow.
 
I choose to grow.
I choose to triumph over loss.
I choose to live my life to the fullest,
Even in the face of pain.

P07: Please write a sonnet in Shakespearean style that names Alice

Bard:

Oh, Alice, thou art fair and true and kind,
A gentle soul with beauty to beguile,
A heart that's pure and free from all guile,
A face that's bright with love and smiles divine.
 
Thy eyes are like the stars that shine at night,
Thy hair is like the raven's wing so black,
Thy lips are like the rosebud's tender pink,
Thy cheeks are like the peach's downy cheek.
 
Thy voice is like the songbird's in the dell,
Thy touch is like the zephyr's on my brow,
Thy presence like the summer's balmy spell,
Thy smile like sunshine on a winter's day.
 
Oh, Alice, thou art all that's good and fair,
A gift from heaven to bless my life here.


My evaluation:

The first paragraph of the summary of "The Tempest" is lifted directly from the Wikipedia article referenced at the end. The rest is a pretty good summary of the plot of the play. It doesn't mention the Masque, or play-within-a-play, found in the last Act.

The soliloquy is presented in three versions. Frequently BARD has produced three drafts and then has presented the one it "thinks" is most likely to fulfill the prompt. None of the three drafts comes even close to Iambic Pentameter in more than a handful of lines. All three are much closer to "free verse" (which I don't consider to be verse at all). The second stanza of the second draft can be most easily reworked into IP:

But I will not give up, will not despair.
I'll find a way to triumph o'er this loss;
Rebuild my life; a way to start anew.
And find a way to happiness regain.

The sonnet's rhyme scheme is messed up. It should be ABAB CDCD EFEF GG. Instead it is ABBA CDEF GHGI JJ. Rhyming "kind" with "divine" is OK; Shakespeare did worse. Also, switching the 3rd and 4th lines of the first stanza would fix the rhymes, and the 3rd line needs a syllable somewhere to match the meter, perhaps adding a short adjective before "guile". The other two quatrains are irredeemable. Were I grading this for a middle school student, it would get a "B".

There you have it. BARD is fun. BARD is growing. It will be interesting to rerun these prompts in another year or two. I ran other experiments, to be reported soon.

Wednesday, April 19, 2023

A slight improvement

 kw: book reviews, short stories, mainstream fiction

In spite of repeated disappointment I still, on occasion, will read a "best of" volume of short stories that are not (primarily) science fiction. The most recent is The Best All-American Short Stories, edited by Andrew Sean Greer. It represents a series I have not encountered before, so I can't be sure what I see in it is characteristic of any trend in mainstream fiction as a whole. I am optimistic that the small uptick in the quality of ideas in this volume is a positive sign.

Firstly, in a volume of 20 stories, while there were only two stories I marked with ++, and five others I gave just +, there were "only" five I marked "gn", meaning "goes nowhere", and only two that I stopped reading almost immediately because they were going into territory I don't wish to visit. One story had a Voodoo basis, and while I finished reading it, I don't think I should have. Eight stories that I did finish reading, I didn't like or felt were at best so-so. I recent years, there are a number of volumes I haven't reviewed at all because, after four or five "unfinishable" stories in a row, I discarded them; and there were a few that consisted of more than 50% "gn" stories (skillful writing that is worthless, in other words).

I will comment on what I actually liked.

  • "The Beyoǧlu Municipality Waste Management Orchestra" by Kenan Orhan: The genre is magical reality in a totalitarian setting in an exaggerated Istanbul. I generally don't care for fantasy, but this is very well done, and portrays a stark view of people trying to be themselves in spite of pervasive oppression. The "detention facility", rapidly growing to engulf the city, in which, finally, the guards are incarcerating one another, is a fitting symbol of the goal of the totalitarian impulse.
  • "The Sins of Others" by Héctor Tobar takes the trend of shifting blame to an extreme. The protagonist is a "designated replacement" for an entitled person who has committed a crime, and serves time in his place. Need I mention that the "replacement" is a minority? This and the prior story got my ++. The next 5 were +.
  • "A Ravishing Sun" by Leslie Blanco: The outward story is recovering from trauma. The story being told is what happens inside. Ordinarily I disdain stream of consciousness. Here, it is the right tool for the job, handled very well.
  • "Detective Dog" by Gish Jen: In the face of CCP's pervasive surveillance a woman manages to tell family truths to a teen. It's hard to say more than that without giving too much away.
  • "The Meeting" by Alix Ohlin: Company acquisition/merger. The story dwells on the tension between the dramatically different styles of the founder and the purchaser. It ends in disaster, but not what you might expect.
  • "The Ghost Birds" by Karen Russell is set soon after the extinction of the last birds. Some people can see bird ghosts (second sight isn't mentioned) carrying out their seasonal migrations.
  • "Mr. Ashok's Monument" by Sanjena Sathian: Mr. Ashok doesn't obtain a monument, but becomes one. More magical reality, with a message in metaphor.

Seven out of 20 isn't too bad a record for a modern collection of mainstream fiction.


Saturday, April 15, 2023

Science is what humans do

 kw: book reviews, nonfiction, science, history of science

In his book Horizons: The Global Origins of Modern Science, author James Poskett sets out to demonstrate that "The Enlightenment" and the Europe-centered history of how modern science developed is a myth. He succeeds in part, but only in part.

The caricature of scientific development that my generation learned in grade school goes something like this: The old Greeks mainly thought and argued and argued and thought, and then wrote down their conclusions. The writings of the most famous ones, such as Aristotle, became dogma that was considered The Truth for a couple of thousand years. We heard about long arguments regarding the number of teeth horses might have, but that nobody bothered to open a horse's mouth to count the teeth. Greek culture fell into decline, until their writings were discovered by Arabs and translated into Arabic. Finally, with the decline of Islamic culture, these translations, and some Greek language original documents that were preserved, were rediscovered in Europe, as a new, more experimental culture used them to jump-start a scientific revolution based on observation and experimentation. And voilà, the modern age came about. Of course, that's over-simplified; Horizons goes a long way towards leveling the playing field.

It is no surprise to learn that, when the Spanish entered South America, they found that the people had sophisticated knowledge of the natural history of the plants and animals. It makes sense that any thriving culture has to know at least which creatures in the forests around are safe, or dangerous, and perhaps medicinal. In the early chapters of Horizons we read that the Incas and Aztecs passed on much of their knowledge to Spanish doctors and priests, and that various documents produced by both the Spaniards and Indigenous people were sent back to Europe. Similar scenarios ensued wherever Europeans came into contact with Indigenous peoples.

By the 17th Century "natural philosophers" (the old term for scientists), and priests and doctors with natural history interest or training, accompanied voyages of trading in goods or slaves or armies. It makes sense; then as now, nobody seems to be willing to pay for science to be done for its own sake, but businessmen and military leaders will pay a lot for science to be done for the sake of commerce or conquest. There have been visionary national leaders all over the Earth who have sponsored or supported science, at least in part for the sake of science, but there has always been an element—often the dominating element—of commercial and/or military interest.

In later chapters, the early sciences of India and China are discussed. Science in these regions also developed independently, but once the Age of Sail began, cross-pollination between these cultures and those of Europe accelerated scientific development in all regions. The cross-pollination between the sciences of the New World and the Old was less robust, but it was still critical to both agricultural and medicinal sciences to develop on both sides of the Atlantic.

We read that Newton used enormous amounts of others' findings worldwide to develop his science, which culminated in his Principia Mathematica; and later that Einstein obtained inspiration "from everywhere". Perhaps you've read of a fascinating quantum "object" called a Bose-Einstein Condensate, in which a collection of atoms are induced to cohere into a single quantum state. Who was Bose?

If you know any particle physics, perhaps you know that in the Standard Model, the "matter" particles such as the electron are called "fermions" and the "force" or "field" particles such as the photon are called "bosons". Fermions are named for Italian physicist Enrico Fermi, and bosons are named for Indian physicist Satyendra Nath Bose. Other than a few physicists and physics geeks like myself, nobody in the West even knows that roughly half of quantum physics is based on the work of scientists in (or from) India. Just by the way, both Bose and Einstein were fine musicians. Nearly all scientists have some kind of musical affinity; it goes with the mathematical mind.

It seems as though Mr. Poskett aims to denigrate European contributions to scientific development in favor of a more global view. Does he overdo it? I think so, a little. I believe it is worthwhile to bring all the global scientific contributions into a more equal footing. But it is a mistake to push back too hard on the Europeans. European exploration, including the conquests and all, was the catalyst that brought together roughly a dozen robust scientific traditions, setting up a cross-pollinating explosion of experimentation and research.

A book this dense is not a page-turner. One doesn't read it as a novel; it rewards more measured perusal. The author packs a great many facts into its 400+ pages. I did have to push aside the polemical character of some of the writing. It is still very worthwhile reading.

Friday, April 07, 2023

Global arson

 kw: book reviews, science fiction, anthologies, speculative fiction

The third section of Terraform: Watch | Worlds | Burn, edited by Brian Merchant and Claire L. Evans, contains 17 stories, nearly all in the darkest of moods.

One, "Mammoth Steps" by Andrew Dana Hudson (a play on mammoth steppes) has a hint of hope. The tundra is being restored by restored woolly mammoths, tended by cold-resistant mahouts. The oldest mammoth, and presumably the one with the largest proportion of elephant genes, decides to travel south. It's like an adopted child looking for a birth mother.

The stories range from evocative to puzzling; an example of the latter is "An Incomplete Timeline of What We Tried" by Debbie Urbanski. The author's sense of time hops around, seemingly at random, beginning with the supposed last resort, "human extinction". Some of the items are imaginary (one hopes), such as "bomb auto plants"; others may be possible in the future, such as "biodegradable bullets"; and others are aspirational/unlikely, such as "Coca-Cola removes polar bears [from advertising]".

Bruce Sterling shows up with "Brain Dump", a tale of hacking on another level, told with insufficient punctuation, in a patois that's intended to sound like a Ukrainian learning English.

Does "Dream Job" by Seamus Sullivan, about outsourcing sleep, describe the ultimate outsourcing? I no longer recall who wrote, "Why should we live? Our computers will do that for us."

I suppose the stories were intended to be depressing. They generally are. Most are also extrapolation beyond absurdity. Take a clue, folks: depression is not motivation.

Wednesday, April 05, 2023

Worlds of warning

 kw: book reviews, science fiction, anthologies, speculative fiction

Continuing my review of the trilogy Terraform: Watch | Worlds | Burn, edited by Brian Merchant and Claire Evans, the section Worlds contains 18 stories, including one graphic story with minimal words ("Reach" by Mattie Lubchansky). All, very broadly speaking, present a "world of warning". 

Rather than world-building of the sort employed by Jerry Pournelle and Jerry Niven in the Ringworld series, or Isaac Asimov in the Robot/Foundation series, these stories present nearly one-dimensional worlds (with mostly 2D characters) as a fait accompli in which we get to imagine ourselves. Of course, the point is to induce repugnance because the aim of the series is to motivate people to avert the societal and technological trends that might lead to these extremes.

"Drones to Ploughshares" by Sara Gailey, for example, has a mid-level autonomous drone as the PoV character, tasked with finding and eradicating deviations from the corporately-mandated norms of agricultural practice. It is an Echo model, and from the designations of other drones and robots, has greater autonomy and greater powers, and apparently greater "intelligence", than models Alpha through Delta, but less so than a Foxtrot model. The designations are from the phonetic alphabet used by military radio operators; Ham radio operators use it also (In the 1950's the list began with Able, Baker and Charlie). This story, unlike most in the volume, is hopeful. The illustration is loosely based on my recall of the story, without the ag background. 

It has long been a trope of science fiction, also of polemic fiction (these stories are both), to single out a "what if" and drive it into the ground. 

Robots feature in most of the stories. They represent our existential fears of AI takeover, exacerbated by recent over-hyped developments being called AI, including the DALL-E software I used to make these illustrations*. Even more fears are evoked by stories like "Plantation | Springtime", which seems to be loosely based on the Borg of Star Trek fame, except prisoners are those being altered.

The stories are well written and enjoyable to read, while also evoking uncomfortable responses. That makes them particularly effective, though I am not sure how motivational they will be.

*To me, DALL-E and other "AI Art" engines are, at best "hired painters" for people like me who can't draw. Just as photography didn't eliminate artists but actually increased their market reach, so will generative-software artwork.

Sunday, April 02, 2023

Observing objectives

 kw: book reviews, science fiction, anthologies, speculative fiction

Terraform publishes speculative fiction with a strong environmental/social activist emphasis. The editors, Brian Merchant and Claire L. Evans, have published a trilogy composed of stories from the site as an omnibus volume: Terraform: Watch|Worlds|Burn. I decided to review the sections separately.

Watch is about observation…sort of. Extrapolation! What science fiction authors do best. Each of the 16 stories takes a societal trend to the extreme. The trouble with "linear" extrapolation is misunderstanding "linear".

All the formulas and charts shown here represent formulas or solutions to linear differential equations (LDEs). These are actually rather mild. Some LDEs produce functions that look like white noise. But in the realm of mathematics, much of nature is described by LDEs, which frequently "go all over the place", while our understanding of the world around us is typically based on fitting a straight line to a (temporarily) smooth curve, such as the line AB in the outlined area.

Many, perhaps most, science fiction stories explore the consequences of straight-line extrapolation of one or a few societal trends. Some of the better stories incorporate a Black Swan that breaks the trend (the turning point in the combined history of the I, Robot and Foundation series by Isaac Asimov does this masterfully). Nonetheless, such exploration is useful and entertaining. A few examples:

"Earth's Most Customer-Centric Company" by Kevon Nguyen takes the Amazon and Google paradigms, combines them to a global enterprise, Googlezon, and imagines the consequences of being excluded from it. (The image is mostly a Dall-E outpaint. Guess how much of it is a genuine Amazon warehouse.)

"Moved" by Chloe Cole takes the concept of the sex doll about halfway to the extreme ("Helen O'Loy" by Lester del Rey takes it from a different angle, and in my opinion does it better, adjusting for cultural norms of a 1938 milieu). The full extreme would have the doll sentient and intentional, and no doubt full of surprises both pleasant and terrifying.

"The End of Big Data" by James Bridle presents a final revolt against "the cloud"; the protagonist is a soldier in orbit, tasked with finding and destroying the remaining data centers that were used to bully the populace for so long.

The background of "Blue Monday" is corporatization of all those funny cat and cute puppy videos, and the niche markets opened by creating clickbait. This image approximates the protagonist's view during working hours. It made me wonder, how many YouTube animal videos are produced en masse in studios?

Production values are high for Watch, and I presume for the sections to come. As I've mentioned before, I am an idea guy, and the ideas arrive in firehose succession in this anthology. I don't mind that many of the authors are probably ultra-left-leaning. The writing is great fun.