Month: April 2023

GPT4 And Movie Scripts

On By Christopher LansdownIn TV & Movies, UncategorizedLeave a comment

I asked a friend to have GPT4 (the successor to chatGPT) write a prompt for itself to write a movie script. Here’s the prompt it came up with:

Craft an engaging and original movie script that revolves around an enigmatic object with mysterious powers. The story should include a diverse and dynamic ensemble of characters, each with their own unique backstory, who must come together to uncover the truth behind the object. The plot should feature unexpected twists and turns, with a focus on character development and emotional depth, while incorporating elements of suspense, action, and heartwarming moments. Please provide a complete script, including character dialogues, scene descriptions, and visual details.

I love how generic this description is. To a great degree that’s what chatGPT/GPT4 specializes in; it’s an engine for generating the most probable text that the people who wrote what it was trained on would say. That is, it is a cliché engine.

I should also note, in fairness, that chatGPT/GPT4 is woefully underpowered to generate a full movie script. Those are usually about 100 pages long (the rule of thumb is 1 minute per page for a competently written script), while chatGPT/GPT4 is limited to 4096 “words” (where “word” is defined a bit weirdly, almost more like “syllable”, though not quite). That said, it’s interesting to take a look at what little it can do.

So, here’s the script generated from the prompt:

Title: The Enigma of the Eon Orb

INT. MUSEUM – NIGHT

A dimly lit room is filled with ancient artifacts. We focus on a particular exhibit: a small, glowing ORB, encased in glass. This is the EON ORB.

Right off the bat, this is not right for a movie script. A movie script describes what the audience sees and hears, it does not give exposition to the reader as if it’s a narrator in a novel. Movie scripts are essentially the blueprints for creating a movie; you can’t do anything with “This is the EON ORB.” You could probably get away with “The camera focuses in on the exhibit with the EON ORB, though it’s only labeled ‘mysterious artifact'” That lets the prop department know which prop to use.

EXT. MUSEUM – NIGHT

Establishing shot of the museum. A heist is taking place; masked THIEVES break in and steal the Eon Orb.

Again, this is not how movie scripts work. In a movie script you have to say things like how many people we see, vaguely what they look like, and it needs to describe in detail what they do. This is more like the prompt you might give to an improv group.

Further, how are we supposed to see that they steal the EON ORB from outside the museum? There is a lot of detail available in HD movies these days, especially if you spring for the 4K version, but showing a heist inside a museum from the outside of the museum is asking a lot even of 4K.

CUT TO:

INT. CIA HEADQUARTERS – DAY

AGENT JAMES PARKER (40s, experienced, determined) is briefed about the theft. He learns about the Eon Orb’s mysterious powers and its ability to manipulate time.

Again, not how movie scripts work.

Also, if people knew about the Eon Orb’s mysterious powers and its ability to manipulate time, why was it just left in a museum, rather than in a securely guarded vault?

PARKER
(serious)
We need to assemble a team to retrieve this artifact before it falls into the wrong hands.

Who is he talking to? Why does he believe that it has not already fallen into the wrong hands?

CUT TO:

INT. VARIOUS LOCATIONS – DAY

That’s not how movie scripts work! You can’t cut to several different places. Or is this meant to be split-screened like the Ang Lee hulk movie which I never saw but I heard was unwatchable because he show several scenes simultaneously in split-screen?

Parker recruits a diverse group of experts for his team:

This is more like a summary than a script, and barely even that.

DR. OLIVIA MARTINEZ (30s, intelligent, strong-willed), an archaeologist with knowledge about the Eon Orb
LENA JONES (late 20s, athletic, tech-savvy), a skilled thief with a troubled past
RAYMOND “RAY” SMITH (40s, charismatic, mysterious), a history professor with expertise in ancient artifacts
RUBY ZHANG (early 20s, quiet, empathetic), a gifted artist who can recreate any object she sees

OK, the archaeologist with knowledge about the Eon Orb I get. A history professor expertise in ancient artifacts… I guess is defensible. Why is the CIA recruiting a tech-savvy skilled thief with a troubled past? Don’t they have tech-savvy people with thief-like skills but without the troubled past in the CIA already? And what on earth could the point be of recruiting an artist who can recreate any object she sees? Is she supposed to make commemorative figurines to help them remember their adventures once it’s over?


INT. CIA HEADQUARTERS – DAY

The team gathers, and Parker briefs them on the mission.

Yeah, this isn’t how you write a movie script, but it’s also pointless because it’s summarizing one of the few lines of dialog that comes immediately after.

PARKER
We have intel that a powerful criminal organization is behind the theft. Our mission is to retrieve the Eon Orb before they discover its true power.

The team agrees to work together, despite their differences.

GPT4 really believes in “tell, don’t show.” That said, why does having different jobs mean that they have to agree to work together “despite their differences”? Also, isn’t that what they did when they were recruited? Were they only recruited to hear the briefing and then they’d decide on what they were committing to?

EXT. VARIOUS LOCATIONS – DAY

The team travels to different parts of the world, following clues and leads. Along the way, they encounter dangerous situations and form strong bonds.

This is impressively generic, even by chatGPT standards. Also, it’s not a movie script. I need a macro for that…

INT. ABANDONED WAREHOUSE – NIGHT

The team discovers the ORGANIZATION’s hideout. They devise a plan to retrieve the Eon Orb.

The place where they discover the hideout of the ORGANIZATION (what a creative name for a criminal organization!) is outside of an abandoned warehouse? This is also where they devise their plan? They walked up to it planless and only when they were sitting around outside did they devise a plan???

Also, why is the team who is going to infiltrate a hideout in an abandoned warehouse a CIA agent, an archaeologist, a history professor, a thief with a troubled past, and an artist? Remember, these weren’t thrown together by coincidence, they were recruited by the CIA agent. When it comes to sneaking into a criminal organization’s hideout, there’s no one he’d rather have by his side than these people with (possibly aside from the thief) no relevant skills?

INT. ABANDONED WAREHOUSE – NIGHT

The team infiltrates the hideout in an intense action sequence. They succeed in retrieving the Orb, but they accidentally activate its powers.

CUT TO:

EXT. ANCIENT CITY – DAY

The team is transported back in time to an ancient civilization, where they meet the original GUARDIANS of the Eon Orb. They learn about the Orb’s true purpose: to maintain balance between the past, present, and future.

GUARDIAN
You must return the Orb to its rightful place in your time. The balance of the world depends on it.

Wow. What a plot. So the Eon Orb’s purpose is to maintain the balance of past, present, and future. It does this by being in the time where it’s supposed to be. So why does it have a user interface which you can accidentally trigger that sends it to the wrong time? Seriously. The thing’s function is best accomplished by not doing anything with it. Why does it have the ability to allow people to screw that up when literally nothing good can come of it. That would be like putting a self destruct button on a sandbag used for holding floodwaters back. That’s not helpful.

The team faces moral dilemmas and confronts their personal pasts. They grow and learn from their experiences.

Man did this follow the prompt to “feature twists and turns with an emphasis on character development”.

INT. ABANDONED WAREHOUSE – NIGHT

They return to the present, but are discovered by the Organization. A thrilling chase ensues.

I guess we’re supposed to take the script’s word for it that the chase was thrilling.

EXT. CITY STREETS – NIGHT

The team is cornered, but they use their individual skills to outsmart the Organization and escape.

I really want to know which skill the history professor used to outsmart the Organization and escape. No, scratch that, I want to know which object the soft-spoken artist copied perfectly during a thrilling chase which allowed her to escape.

INT. MUSEUM – NIGHT

The team returns the Eon Orb to its rightful place, restoring balance to the world.

The script never actually mentioned anything bad happening because the Eon Orb was gone, but OK.

EXT. MUSEUM – DAY

The team says their goodbyes, having formed lifelong bonds.

MARTINEZ
We’ve come a long way. I’m proud to call you all my friends.

RAY
Our paths crossed for a reason. I’ll never forget our journey together.

LENA
Who knows? Maybe we’ll cross paths again someday.

RUBY
(softly)
I hope so.

PARKER
Until then

Oh wow is that dialog original!

GPT4 suggests that the title of the movie should be “The Enigma of the Eon Orb,” but I suspect “Action Team Cliché: Origins” would be a better title.

I guess this wasn’t an entirely fair request. It’s not easy to write an original, engaging, heart-warming movie that focuses on character development. Let’s give it something easier.

Here’s GPT4’s attempt at a script for a sequel to Star Wars Episode VII: The Force Awakens:

Title: Star Wars Episode VIII: Shadows of the Past

INT. RESISTANCE BASE – DAY

Commander POE DAMERON is briefing a group of pilots, including REY and FINN.

POE
We’ve discovered an old Imperial outpost on the distant planet, Tython. Our intel indicates that there might be valuable information on the whereabouts of other potential Force-sensitive individuals.

REY
We can’t let the First Order get their hands on that information.

FINN
Agreed. We have to get there first.

EXT. SPACE – DAY

The Millennium Falcon and several X-wing fighters blast off towards Tython.

EXT. TYTHON – DAY

The Resistance team arrives on Tython and enters the ancient outpost.

INT. IMPERIAL OUTPOST – DAY

The team explores the outpost, uncovering hidden rooms and ancient artifacts.

REY
(sensing something)
There’s a strong presence of the Force here.

FINN
Let’s find that information and get out of here.
[4:26 PM]
As they continue to search, they discover a holocron with the data they need. However, they also awaken an ancient DARK SIDE ENTITY, which attacks them.

INT. IMPERIAL OUTPOST – BATTLE

The team fights the dark side entity. Rey’s powers are tested as she struggles to protect her friends.

EXT. TYTHON – DAY

The team escapes the outpost, but the entity follows them. A massive battle ensues between the Resistance and the dark side entity.

REY
We can’t defeat it alone. We need help.

POE
Rey, you have the power within you. Trust the Force.

Rey takes a deep breath and focuses her energy. She harnesses the power of the Force and defeats the entity.

EXT. RESISTANCE BASE – DAY

The team returns with the information and is greeted by General Leia Organa.

LEIA
Well done. With this information, we can find and train others like you, Rey.

FINN
The First Order won’t know what hit them.

REY
We’ll be ready.

The movie ends with the promise of a new generation of Jedi and the hope of defeating the First Order once and for all.

Yup. It was better than the one Rian Johnson wrote. (If you’re curious, here’s my twenty seven thousand word review of Star Wars Episode VIII: The Least Jedi.)

Of course, that’s a very low bar to clear. You have to dig in order to find it.

Agatha Christie and Miss Marple

On By Christopher LansdownIn UncategorizedLeave a comment

I’m going out on a limb a little, but, Miss Marple is perhaps as iconic a character as Hercule Poirot is. At least most of everyone who has heard of Poirot will have heard of Miss Marple. And while I think Poirot has been adapted into movies more often, Miss Marple might have been more influential. I can’t think of any other detectives who exist because of Poirot, but Murder, She Wrote would not have happened without Miss Marple.

Having said that, there can be no question of which one Agatha Christie wrote more of. There are something like three times as many Poirot stories as Miss Marple stories. Part of this, of course, is that Poirot had a seven year head-start. Those were seven very productive years for Agatha Christie, too—in addition to several Poirot novels, she wrote a great many short stories.

The subject of short stories is interesting, here, for while Poirot first appeared in a novel, Miss Marple first appeared in a short story. Most of the Miss Marple short stories were gathered together into the book The Thirteen Problems, and in the introduction to it—written years after most of the short stories themselves—Agatha Christie opines that Miss Marple is at her best in short stories, while Poirot demands novels. This is curious because she only wrote a few more Miss Marple short stories, while she had yet to write eleven of the twelve Miss Marple novels that she would ever write. This may, perhaps, be attributed to the changing economics of fiction. In the twenties and thirties the real money was in short stories; this was much less the case in the 1950s and 1960s. (I’m not sure how things were in the 1940s; television had not yet taken over from short stories as popular short entertainment but magazines and newspapers were hit hard by the war, especially since paper was in short supply.)

She also remarked in that introduction that Miss Marple was as popular as Poirot—she got about an equal number of letters requesting that she drop Poirot in favor of Miss Marple as requested that she drop Miss Marple in favor of Poirot. And here we come to one of the things that intrigues me about Miss Marple: it was twelve years between the first Miss Marple novel (The Body in the Vicarage, 1930) and the second (The Body in the Library, 1942). While the stories themselves were written (and published) between 1927 and 1930, the foreward to The Thirteen Problems was written in 1932. After declaring Miss Marple to be as popular as Poirot, it would be ten more years before she published another Miss Marple novel. And so far as I can tell looking at original publication dates, she only wrote three Miss Marple short stories in that time, one in 1939 (commissioned by the BBC as a radio play) and two in 1941. Two more would appear in 1942 after the publication of The Body in the Library, another in 1954, and the final Miss Marple short story in 1956.

I can’t help but wonder why it is that Agatha Christie thought that Miss Marple was better in short stories but after the first collection wrote her mostly in novels, and thought her as popular as Poirot but waited twelve years to write more of her.

That said, the wait did her no great harm. Miss Marple was always a creature from a previous age so she did not suffer greatly from how the world changed during and after the second world war—if anything, she felt less out of place after the war than before it. Young people in the 1920s and 1930s were concerned with being Modern in a way that only the hippies of the 1960s came close to. By the 1950s, people simply didn’t look down on their elders as they once did and Miss Marple’s Victorian girlhood was not the object of (indulgent) ridicule that it once was.

Which reminds me: I wonder if Agatha Christie, in writing Miss Marple, was at all inspired by G.K. Chesterton’s Father Brown. Certainly not entirely; she mentions inspiration from her own grandmother who had a sheltered Victorian upbringing and thought the worst of everyone. That said, the indulgent way that people assumed that Miss Marple knew nothing of the world is very reminiscent of the indulgent way that people assumed that Father Brown knew nothing of the world—and they had been assuming that of Father Brown for seventeen years by the time Miss Marple came on the scene. If so, she was inspired well.

But getting back to my main question, I wonder if it was merely that it was harder to come up with plots for Miss Marple stories than it was for Poirot stories. Miss Marple was a very different kind of sleuth and her stories (almost) always involved a great deal more investigation by people other than Miss Marple herself. It would be an exaggeration, but not too much of an exaggeration, to say that until the last few novels Miss Marple didn’t appear in the novels more than she did in the short stories, there was just a lot more of other people in the novels padding them out to full length. This means that the stories for Miss Marple require a setting in which amateurs (or ordinary policemen) can do the investigating and find the clues, but not understand them. This is not so easy to do. It is much more convenient for the author, especially of a novel, to have a detective who can look for clues that most people would not. Often this is unraveling the mystery of a red herring so that it can be set aside and further clues looked for, but it in any event helps.

This is also, I think, why Agatha Christie said that Miss Marple is at her best in short stories. Short stories allow there to be a summarizing of the evidence without much time to think about it, then Miss Marple can give her brilliant interpretation. If this is to be done in a novel, it’s trickier both to come up with a mystery which will last without anyone figuring it out, and also to come up with red herrings that don’t need to be cleared away for the right evidence to be discovered.

This is only speculation and I have little confidence that this is correct. Unfortunately, Agatha Christie says nothing on the subject in her autobiography, so I doubt that I’ll be able to advance much beyond speculation.

The Golden Age and Theories of Detection

On By Christopher LansdownIn Mystery, UncategorizedLeave a comment

One of the characteristics I’ve noticed quite a bit in detective stories from the golden age of mysteries (roughly, From 1890 until the start of World War 2) is how many detectives had a theory of detection which they discussed.

In the very early days, the detectives differentiated themselves from the police through their use of forensic investigation. In the 1890s, Sherlock Holmes performed chemical analysis to prove a stain was blood and wrote a monograph on how to identify cigar ash. In the early 1900s, Dr. Thorndyke looked at everything he could under a microscope, and what he couldn’t he would look at with enlarged photographs.

Sherlock Holmes did not long predate real forensics, though. By 1901 Scotland Yard was using fingerprints to identify people and in 1902 the first conviction was obtained with the use of fingerprint evidence. (See Fingerprints And Forensic Evidence.) It did not take the police long to make use of this kind of forensic evidence, and private detectives began to shift their methods. G.K. Chesterton would revolutionize the field of private detection in 1910 with Father Brown’s psychological approach to solving crimes, and to varying degrees this has been the primary tool of detectives ever since, so no advances in forensic technology can make psychology obsolete.

Through all of these changes, there remained an air of novelty. The brilliant detective during the golden age was not merely brilliant; he had a method. He got his results because he brilliantly followed his method while others either followed the wrong method or else had no method.

Perhaps nothing exemplifies this as well as the unjustly neglected second Poirot novel, Murder On the Links. Poirot’s method is contrasted very strongly with that of the indomitably forensic M. Giraud. Giraud examines the crime scene with the utmost care and uncovers impressively small clues. Yet Giraud dismisses a section of pipe as being of no importance because it’s not the kind of clue he’s looking for. As Poirot remarks to Hastings, “Mon Ami, a clue of two feet long is every bit as valuable as one measuring two millimetres! But it is the romantic idea that all important clues must be infinitesimal!”

Poirot considers all clues because his method is to adjust his theory until nothing is out of place; Giraud’s method is to ignore whatever does not fit his preferred kind of evidence. The point, here, is not the specifics of the contrast, but that the contrast is so important.

Another, though less important, example that comes to mind is in The Strange Case of Mr. Challoner. In it the detective, Malcolm Sage, delivers a lecture on how the Police misunderstand the evidentiary value of photographs and fingerprints. They think that photographs are for identification while fingerprints are evidence; in reality fingerprints are for identification and photographs are evidence. He took a series of photographs of the crime scene and announces that they will be the principle evidence at trial, and then uses fingerprint evidence to show that the butler is actually a wanted criminal. I don’t know that the police ever ignored the identificative value of fingerprints or the evidentiary value of photographs, but that’s not the point. In a short story written for entertainment value, the writer and editor thought that the audience of the newspaper would be entertained by a lecture on how the police don’t understand the proper use of evidence.

I’m not sure exactly when this aspect of detective fiction died off. Certainly you can’t find it in the Cadfael series, which started in the 1970s. I can’t think of any detective fiction I’ve read from the 1940s through the 1960s except for Miss Marple. I haven’t read any of the Poirot stories written after 1947 (yet). I don’t remember this in the Miss Marple stories from that time period, but then I don’t recall it in the Miss Marple stories from the golden age, either. (To be fair, that’s only one novel, though it is also most of the short stories.) Miss Marple was never really a detective, though. People told her things and then she would give them the solution. With the exception of Nemesis, and to a lesser extent A Caribbean Mystery, she never went looking for clues of any kind. On the other hand, there were her typical reminiscences of people who committed similar sins in Saint Mary Meade, which was certainly a unique style of detection.

By the time we get to television detectives like Columbo in 1971, the aspect of a unique method is missing. While it might be objected that Columbo is a policeman and therefore cannot contrast with policemen, he is still a contrast with the other officers who do not get nearly the same results.

There is similarly no trace of in the 1980s’ Murder, She Wrote.

So, what happened?

Alternatively, what was special about the golden age?

I’m really not sure which of these questions we should be asking. It is tempting to think that there was something special about the time that the golden age happened. To some degree it was the first time police forces were getting organized and police detectives were becoming a real thing. Advances in technology also made various kinds of detection newly possible, or at least newly practical, and so the whole thing had an air of novelty to it.

On the other hand, it’s also possible that there was simply a fundamental split in the mystery genre, with mysteries taking the psychological and logical aspects of detection and police procedurals taking the forensic aspects of detection.

On the third hand, it may just be that all of the possible theories of detection have been expostulated and all that remains is to do one of them well.

Perhaps it’s a bit of all three.

A Weird Take on the Thief on the Cross

On By Christopher LansdownIn Christianity7 Comments

Somehow Instagram (a social media site for looking at pictures of reptiles, though I believe some people look at it for photos of other things) recommended a video to me of a guy who was talking about the thief on the cross. Specifically, the one that upbraided the one who was abusing Jesus, and who asked Jesus to remember him when He came into His kingdom, and Jesus said, “this night you will be with me in paradise.” The guy asked, “how does this square with your theology? He wasn’t baptised, didn’t receive communion or confirmation, didn’t give anything to the poor, Jesus didn’t take away his suffering, he didn’t speak in tongues, etc.”

It’s a fairly obvious point, though one worth making from time to time that the ordinary ways that God gives to us to live are not the only ways he gives to people, and while he works through his sacraments he is not bound by them, etc. etc. etc. This is certainly a doctrine of orthodox theology, and you can see it in things like the baptism of blood, the baptism of desire, and so forth. But this guy is making a really big deal of it like he’s the first one to think of it, and also like it’s revolutionary. Somehow he doesn’t seem to take into account that the good thief was nailed to a cross. People tend to focus on the death in excruciating agony part of dying on a cross—reasonably enough—but it’s also a feature of the cross that a person nailed to it can’t do anything. The good thief didn’t do anything for the poor, but he also couldn’t. You can’t extrapolate from that to people who can do things for the poor. It’s just possible that Jesus’ words about the importance of caring for the poor might have some applicability. In short, just because it’s possible to be saved while nailed to a cross doesn’t mean that no one should bother with anything other than what a person nailed to a cross can do.

Then he went full-heretic (never go full-heretic). He said that the only thing that the thief had to offer Jesus was his belief.

This is dead wrong.

It is true that people can’t buy salvation with their good works. It is equally true that people can’t buy salvation with their belief. People simply can’t buy salvation.

Salvation is a gift from God freely given to us. The thing is, we have to accept it. And this is where we come to the part where Jesus said, “It is not everyone who says to me, ‘Lord! Lord!’ who enters the kingdom of heaven but he who does the will of my Father.” Good works are the content of faith. It is possible for one to have faith without works where those works are prevented, but for most of us this is academic. Most of us are not nailed to a cross. Most of us have the opportunity to live according to the truth of Christ’s death and resurrection.

I find it really weird that there are people who are still trying to peddle the idea that salvation is a matter of pledging allegiance to Team God or having some sort of emotional experience of “belief”. I get why Martin Luther tried to redefine faith so as try to get rid of the need to trust God without having to get out of having the word; it made sense in the context in which he found himself. These days, there are much easier ways of not being Christian.

Just Imagine What It Will Be Able To Do!

On By Christopher LansdownIn UncategorizedLeave a comment

Something I hear a lot when it comes to the recent AI stuff like Stable Diffusion, Dall-E, chatGPT, etc. etc. etc. is some version of “this technology is just in its infancy, imagine what it will be able to do in a few years!” I’m not saying that these AI technologies won’t improve, but the thing is, it’s just not true that these technologies are in their infancy. These technologies are all developments of technologies which have been worked on for decades.

At their core, these approaches are various ways of doing massive quantities of massive matrix multiplications in order to encode the relationships between data. The T in chatGPT stands for “Transformer,” which is a variant of the previous types which had generally had some form of “neural” in the their name, such as Convolutional Neural Networks or Recurrent Neural Networks. In particular, Transformers (which were first mentioned publicly by a team at Google in 2017) replaced RNNs as the model of choice in natural language processing by being simpler and having the feature of being able to do the pre-training in parallel, which made vastly larger training data sets feasible.

Transformers were not a radically new idea that created a field which didn’t exist before; they were a new approach which was created because a large number of well funded smart people had been working in the field for a long time on relatively similar approaches. It’s an innovation which yielded noticeably better results, it might even be a breakthrough. What it’s not is the first dipping of humanity’s toe into something no one had ever done before. It may be the first supersonic flight; it is not the first flight at Kitty Hawk.

Moreover, the hardware to execute these things has been under development for a very long time. A huge breakthrough in performance came when the AI algorithms were adapted to run on GPUs (graphics processing units, the things that do all of the calculations for 3D graphics). This provided a relatively inexpensive source of incredibly high performance in number crunching that made the massive amount of processing involved in AI far more accessible. The thing is, this was like a decade ago. Since then special-purpose GPUs have been created to do the work even more cost-effectively (One I know of in the current generation of them is the nVidia A100 which costs around $10,000). But wait, there’s more!

Cerebras developed the Wafer Scale Engine—an AI processing chip the size of an entire silicon wafer—back in 2019. It’s an impressive piece of technology; it consumes about 22kW of electricity in a silicon wafer that’s 300mm in diameter (basically, 1 foot wide). It’s quite a technical achievement, but it went on sale back in 2019. There will be newer and better ones, to be sure, but it’s not a new idea with completely untapped potential.

Don’t get me wrong. I’m not saying that this is the end of technological development, or that AI won’t get any better. It would be outright shocking if there were no further improvements. My point is that the improvements that we’re going to see are most likely to be much slower than the people who don’t know anything about the history of AI development think it will be. We’re not at the very beginning of an exponential curve.

I do strongly suspect that generative AI is going to be useful, just as classificational AI has proven useful. The thing is, classificational AI has been with us for a while—it’s things like face unlock on phones and de-noising of video and audio and actually usable speech-to-text. It’s gotten better, and it continues to get better, but speaking as someone who develops technology: a technology becomes viable when it works all of the times for a use, not merely when it can do an impressive demo under favorable circumstances. And in the real world, edge cases are often 99% of the work and not being able to handle them often means that a tool is more work than it saves. The result is frequently a limited-use tool for cases which the new technology is good at, and it’s one more tool in the toolbox of a human being who can handle all the edge cases.

That’s why the result of all of the labor-saving devices is people being so busy all the time.

Poirot, ITV, and the 1920s

On By Christopher LansdownIn Mystery, Uncategorized, WritingLeave a comment

Something curious about the ITV version of Poirot is that (with the exception of The Mysterious Affair at Styles) all of its episodes were set in the 1920s. Not literally the 1920s, per se; I’m sure that plenty of the technology or fashions were from the 1930s, but neither the Great Depression nor the looming war due to the military buildup of Germany ever feature.

This is not true at all of the novels.

The Poirot novels are always set contemporaneously to when they were written and current events, or at least current conditions, play into the plot. The only anachronism is Poirot himself; when Agatha Christie first wrote him, she presented him as being at least in his sixties. In her autobiography she mentioned that this was an unfortunate choice on her part, but she had no idea how popular he would be or how long he would last, and as of the time of her writing about it he had to have been over 100 by then. She simply ignored this problem and made Poirot always an old man of unspecified age.

When ITV made its version of the stories with David Suchet, they chose to set all of the stories in the same few years, though rarely with anything that would date them. There were practical reasons for this, of course. For example, it would be difficult to age the actors appropriately by decades in order to follow the real stories. Wardrobe and set decoration would be far more difficult if they kept track of the changing styles. Moreover, a series of episodes (or short movies) would be far more jarring if they skipped forward by years every few weeks or months, while the books always skipped ahead by however long it had been since the last one.

However many practical reasons to set Poirot in the span of a few years, though, I suspect that the biggest reason was that the 1920s are simply far more interesting, and far prettier, than later decades. This isn’t the totality of the 1920s, of course. Poirot was a celebrity and tended to deal with clients of means. Accordingly, the stories are set largely among the prettier parts of the 1920s. This is as it should be. Detective stories are stories for the common man, and so they should deal with things that he will not normally come across. Fiction about the lower classes is the domain of the upper classes, who need to read about drudgery and difficulty to find variety from their lives.

There are complex reasons why this should be, but the one thing I think it isn’t is rose-colored glasses from anyone’s past. By the 1990s when ITV was making the Agatha Christie’s Poirot series, the 1920s were seventy years before. No one remembered them. Instead, if we look to the specifics, we will find a decent answer. The 1930s were an interesting time but heavily influenced by the world-wide Great Depression and in the later portion by the looming war on the European continent. The 1940s were dominated by the second World War, to the point where no one ever talks about the events of 1946-1950. The 1950s had a primarily industrial aesthetic, as people took refuge in the post-war plenty which was so different from the great depression and the war years. In more rarified circles, architects and designers were greatly attracted to anything which was not beautiful. This was the era of the Helvetica font and the beginning of the era of buildings which no one likes. The 1960s spiraled off into kaleidescopic colors that meant nothing but were fun and new. The 1970s were, of course, varied, but let us leave it with two words: shag carpet. That takes us to the end of when Poirot stories were written, but for completeness: the 1980s were the era of big shoulder pads and bigger hair with leather jackets and denim jackets, while the 1990s… I wonder what the style of the 1990s even was? T-shirts and jeans or shorts? It’s been thirty years since 1993, and has anyone figured out anything to be nostalgic for? Classic video games are the only thing that I can think of.

Anyway, I think that I’ve made the point. The 1920s are an era with a fascinating aesthetic that’s pleasing to look at, and it was the last time to have that for quite some time. (Portions of the 1930s were more-or-less continuous with the 1920s, but I’m counting them as part of it since they were, aesthetically, a continuation of them.) There will be others, of course. At some point our fascination with trying to see how little clothing people can wear will be over, and people will try to make their clothing interesting rather than revealing, again.

This is not the same thing as nostalgia for the 1920s, by the way. I don’t think that it being fun for Poirot to be set in the 1920s is nearly the same thing as wishing to live in the 1920s. It’s merely a recognition that the interesting parts of the 1920s were very interesting, while the interesting parts of later decades weren’t nearly so interesting.

There is also the argument to be made that the 1920s (and 30s) were the last real era of the private detective. After World War 2 we live much more in the era of the spy thriller. In the spy thriller people kill and are killed for governments and large organizations; we don’t care nearly so much for the concerns of the individual. There may be some truth to this, though for all that people still go on murdering people for their own reasons even in the 2020s, and people even still care when people are murdered. It may be fewer than in former times, but detective stories were always about unusual people.