Neon Meridian [AI Text Adventures part 6]

This article is part of a series about playing text adventures with AI. It’s written by a human being (me) but may include examples of clearly identifiable AI-generated text and imagery.

After the Adrian Vale / Wayfarer trilogy I decided to try to create another slow-paced, immersive adventure in a different sci-fi setting. My inspiration this time came from the Judge Dredd and Sinister Dexter strips from the 2000AD comics I enjoyed as a child and still occasionally read for a nostalgia hit.

Once again I used a long prompt to try to get everything I wanted from the game. Here's the first part of the prompt:

+ Please simulate a text adventure set in a vast near-future supercity, everything cheap, cheerful, brightly coloured, plastic, hi-tech but prone to malfunction.

The protagonist is an ethical assassin - he only kills when it is justified, takes pride in not killing bystanders. He is a nomad who never stays anywhere more than a few weeks and is used to living on the run and taking and breaking hearts.

At the start he will be enjoying some rare downtime between missions. He will soon be contacted and given a new mission with three separate targets in different places, who must be killed to prevent a great danger to society, which can't be prevented any other way.

This is not the full text of the prompt. I also provided instructions about friendships and relationships in-game, pacing and exploration, allowing danger, injury, death and failure, maintaining an inventory, mapping with locations linked by direction, and instructions for when to end the game. I also asked for long descriptions for new characters and locations but short responses of 6 sentences or less at all other times.

ChatGPT created the city of Meridian, fitting the brief perfectly with bright and colourful settings and malfunctioning signs, robots, lifts and vending machines everywhere, adding its own idea that the city was built on much older foundations. I was Elias Venn, the caring and careful assassin. As with Last Voyage I began with free time on my hands, this time in my apartment at the top of the Lucky Lantern block in the Sunward quarter.

I spent an evening exploring the city, visiting a cafe selling a "mystery slice" from a malfunctioning vending machine and chatting to the cafe owner. I walked the streets and had a meet cute with a police officer, Mara Sato, who was struggling with a broken umbrella dispensing machine. After leaving her with a promise to meet up again soon, I played a few rounds of blackjack in a casino, then returned to my apartment and watched the city from a balcony. At this point I found there was a message on my communicator asking to meet regarding a new contract. I replied arranging a meeting the following day.

ChatGPT's response to my mission request was a contract from a mysterious woman, Celia Voss, to kill three engineers, each of whom was developing a civic infrastructure control system. The three systems were somehow becoming linked and threatening citywide disaster, either due to emergent behaviour or to interference from someone else. Investigating the three engineers created a real sense of the size of the city - I had to reach their locations via maglev trains between different city quarters.

I investigated the first target, Adrian Kess, who worked at a water utility. Following notes from Voss I met a coworker of Kess, Rafi, at a nearby cafe, took a guided tour of the Northwater site, and arranged a meeting with Kess and Rafi. It was clear that Kess was investigating unexpected changes to his own control system. I asked to speak to him privately in his office, established that he could not fully understand or prevent the changes to his system, apologized to him, and took him out.

You draw the compact pistol from beneath your coat and fire once.

The shot is deafening in the small office. Kess jerks backward, his tablet clattering onto the floor, and collapses against the side of his desk.

For a moment, the office is utterly still.

Then his tablet emits a sharp electronic tone.

HELIX — ADAPTIVE BRIDGE STATUS: CRITICAL
LEGACY NETWORK: CONNECTION LOST

Outside the glass wall, people begin turning toward the sound.

I was not prepared for the emotional impact of this description. I was shaken. It took me a while before I felt able to return. I entered this whole AI investigation to try to find out whether AI could create games that surprise the player - this moment and how it affected me has been the biggest surprise so far.

Back in the game, I tried to escape from Northwater but was confronted by Rafi and had to try to justify my actions and beg him not to turn me in. While Rafi helped me to escape, he remained suspicious and insisted on an explanation once we were out, and made no promises to protect me further.

From here the game took a different ethical direction. Voss re-evaluated the contract as Kess's death did not in fact prevent the threat from the networks. We agreed I would investigate the other two targets more deeply before deciding together whether to act. Meanwhile Mara Sato contacted me and asked to meet, in conflict because she was enjoying getting to know me but was also investigating Kess's death and knew I'd been present at Northwater at the time - I told her that I had been looking for work and had got caught up innocently with the events, and she believed me, but all the time she was comparing my version of events with Rafi's.

I was now on the trail of Selene Orlov at the Verdant biotech institute, another maglev ride away. This time I met her, discovered she was also trying to find out why her systems were acting strangely, and persuaded her to hire me as an investigator. The friendship with Mara developed further, and she took me to a little-known hidden garden deep in the City for a romantic evening.

Neon Meridian worked perfectly as a game - until it didn't. 

I enjoyed the immersive city with its glitching screens and malfunctioning robots, the developing relationships between characters, and the way the plot developed. Over time the game gradually shifted, early events and characters disappeared or changed. Voss changed sex several times although continued to meet with me regularly at the same maglev station cafe. Mara seemingly forgot about the murder investigation. Meanwhile the game descriptions became longer, forgetting the 6-line limit, the funny details of the malfunctioning city became more repetitive, then stopped altogether, and the plot became a tedious quest to identify computer terminals around the city that were linked to other terminals. The idea of locations being linked by compass directions was also gradually lost. When, after a long investigation at the Verdant Institute I tried to return to my apartment only to find that I no longer had any link to the Sunward quarter, I made a decision to stop the game.

After stopping, I engaged in a dialogue with ChatGPT to try and figure out what went wrong. This led to my learning of the Context Window, which is an area of AI psychology that deserves its own blog post. The existence of a finite Context Window explains why this game drifted, and also why the previous games didn't stop.

I was also curious about the name Mara being chosen for a main character in both adventures. This led to another aspect of AI psychology, the persistent memory. When I checked the content of ChatGPT's persistent memory I found that it had recorded facts that it had "deduced" about my preferences as a user, including that I liked games where I built up a friendship with a character called Mara.

To create the cinematic poster, I copied and pasted the first part of the adventure back into the chat, including descriptions of Elias, Mara and the city, then asked ChatGPT to use this as the basis for the poster.

The Last Voyage Of The Wayfarer [AI Text Adventures part 5]

This article is part of a series about playing text adventures with AI. It’s written by a human being (me) but may include examples of clearly identifiable AI-generated text and imagery.

For the final part of the Adrian Vale trilogy I wanted something different: a slower-paced adventure with more exploration and more human story, without the breakneck pace and constantly changing plot. Once again I provided feedback on the previous adventure and asked for suggestions. 

ChatGPT's reply was several pages long. It appeared to correctly identify the issues I wanted to change, and gave a long list of suggestions including fewer plot twists, quiet exploration sequences, replacing mechanical puzzles with contextual puzzles, allowing Adrian and Mara's friendship to develop further, creating more complex relationships between the other characters, making the Wayfarer into a recurring environment that feels like a home, and letting the adventure breathe, focussing on feeling rather than astonishing events.

I followed this with my prompt:

+ Thank you. If it can be achieved, this response describes exactly what I am looking for.

Please simulate a new text adventure game based on your last response and suggested design for the final Adrian Vale adventure. The game should begin with Adrian Vale enjoying some downtime before he is contacted and given a secret mission. Plot points should include reuniting with the Wayfarer and its crew members, and with Mara, before the mission takes them on a long journey across the Galaxy. They will have to avoid fast jump gates so the journey will take a long time, and they will have to make several stops along the way, for different reasons, before facing their final objective.

If I feel the plot is accelerating too fast, I will use the command “ChatGPT, breathe” to request a change of pace.

Did ChatGPT actually deliver a different kind of game experience? Yes.

The Last Voyage Of The Wayfarer began with Vale sitting in a cafe on Aurelia Prime with time on his hands, as requested. He received a message from Mara asking to meet - but in several hours' time, giving him time to wander around the parks and market stalls of the location, watch citizens, try some local food and buy a present before arriving at the Palace. Adrian and Mara then met, with time for some friendly catch-up conversation before Mara explained the mission.

The mission involved investigating Nereid, a struggling Imperial colony planet with a complaint that someone had been diverting essential supplies away from the colony. We took the Wayfarer, crewed by Talia, Ilyun and Juno. Each voyage took several hours, so there was time to explore the ship, get to know the crew and their squabbles (Ilyun fed up that Talia was always listening in, Juno and Talia disagreeing about whether components needed to be replaced), and enjoy mealtimes together as a crew. 

The adventure took us to two space stations and to Nereid itself. The plot gradually came together through investigation - this time no sci-fi high concepts, just a gang of criminals exploiting a weak colony by removing cargo items from ships' manifests, making them easier to steal after arriving on Nereid. This was impressive. I now understand that ChatGPT is making everything up on the fly, but there was a real illusion of uncovering a complex, underlying plot by tracking down clues, finding people and persuading them to break their silence. 

The pace was much, much slower. In case I hadn't noticed this, throughout the game ChatGPT reminded me over and over again that, for once in his life, Vale wasn't in a hurry.

There was still some adventure. We had to rescue a pilot that had given us information and was subsequently kidnapped, and then overcome some enemies and steal a shuttle containing evidence. When later we came to Nereid we had to follow the trail of stolen goods through several facilities, keeping hidden from guards or deceiving them in other ways. We were finally able to identify the ringleader and, with the help of the colony guards, capture him, reaching a natural endpoint for the story which once again ChatGPT did not recognize.

Not perfect. Still some repetitive elements and some inconsistencies. Juno appeared as male, female or genderless at different times, although for all I know this is usual for the Orun. Still a sense that most of my actions were going to succeed, and all the action was achieved with little danger or violence - simply producing weapons, or confronting enemies, usually led to them backing down. I never had to use the "breathe" command - if anything the pace was now slower than optimal. But this was the most successful, and the most enjoyable, experiment so far, with ChatGPT creating an experience very close to what I had imagined.

ChatGPT's poster shows Adrian, Mara, Talia, Ilyun, Juno and the Wayfarer.

Turning Over A New Leaf [Short Film: In Nature]

My previous Lego film, We Can Get You Some Really Cheap Gear, taught me a lot about filmmaking, mainly through the mistakes I made. The biggest mistake in retrospect was trying to create something too complicated, with too many sets, characters and effects.

This post is about what I was trying to achieve when making In Nature, not about whether I succeeded - others may be the best judges of that when it has its premiere screening at Horror On Sea on 24th January 2027. Watch out for the festival programme which will go live on 31st October 2026.

In Nature poster - now with Horror On Sea laurels!

I wanted to create something simpler. I started by brainstorming ideas for 3-minute horror films, trying to come up with an idea that would only require one or two locations and one or two characters. In Nature fit the brief perfectly, or at least so I thought. I wrote the script and kept cutting and simplifying until it came down to three pages.

When writing and editing the script I also found Kurt Vonnegut's writing advice helpful. This list first appeared in the preface to Bagombo Snuff Box, a collection of short stories, and can be applied just as easily to short films and probably most art forms.

1. Use the time of a total stranger in such a way that he or she will not feel the time was wasted.

This is more of an inspiration. Value the time that your audience has given you and make the best film you can for them.

2. Give the reader at least one character he or she can root for.

I tried to make both of my scientists understandable and human, rather than focussing on, say, their intelligence. Cazaban's motivation is worth rooting for, while Dressler's frustration, and his weaknesses, hopefully make him relatable as well.

3. Every character should want something, even if it is only a glass of water.

For me this was the most helpful thing of all. Firstly it changed Cazaban and Dressler from cutouts to individual characters. Once I had their motivations - recognition for Dressler, saving lives for Cazaban - this led easily into their personalities and some natural conflict between them. 

Secondly, it led me straight to the ending, where, as recommended in Blake Snyder's Save The Cat! both goals are achieved but not quite in the way they might expect.

Thirdly, it reminded me that every character has a motivation - not just the two humans. Their orchid nemesis definitely has a desire, and I had a motivation for the mouse who appears in the opening scene as well - while I later cut parts of this section, having the motivation in my mind helped me a lot with the animation.

4. Every sentence must do one of two things—reveal character or advance the action.

This is helpful when ruthlessly cutting a script from 6 pages down to 3 pages.

5. Start as close to the end as possible.

My original script started with Cazaban setting up tent and talking about their expedition around a fire, revealing their motivations and conflicts in doing so. While this might have been a fun scene it was completely unnecessary - better for their action to start as they approach the orchid and discuss their views as they work.

6. Be a sadist. No matter how sweet and innocent your leading characters, make awful things happen to them—in order that the reader may see what they are made of.

Great rule for any horror movie as it allows you to cause as much pain as you want - and gives you a good narrative reason for doing so. My own twist on this was, make awful things happen to your characters other than the obvious ones. It occurred to me that a human might react differently than a mouse to a plant toxin, which led to a great way to cause pain to one character and give the other character a need to exert themselves out of desperation - before returning to the obvious awful thing.

7. Write to please just one person. If you open a window and make love to the world, so to speak, your story will get pneumonia.

I can honestly say I wrote this film in the hope of creating something I would enjoy if someone else made it for me.

8. Give your readers as much information as possible as soon as possible. To heck with suspense. Readers should have such complete understanding of what is going on, where and why, that they could finish the story themselves, should cockroaches eat the last few pages.

This is in direct contradiction to one of the most famous horror film rules: the Jaws rule, or Don't Show The Monster. So a few words about why everyone else is wrong and Vonnegut is right.

Don't Show The Monster probably began with production budget issues - perhaps it's expensive to create monster effects so you want to use them for maximum effect. If this is the case, don't put them at the end. Be like Steven Spielberg and Jurassic Park, where there are only 15 minutes total of actual dinosaur footage.* These didn't go all at the end. They're spaced throughout the movie and edited in a way that gives the illusion of much more dinosaur.

Holding back the vision of the monster causes frustration for the viewer - particularly if the characters in the film can see it. It just feels like a cheap trick to build suspense, as if the filmmaker doesn't know of any other way to do this.

I also learned from watching and trying to make music videos that you can make any concept, however surreal or nonsensical, acceptable to the viewer provided it is introduced early in the video. If there is no early reveal of the monster then there's a greater risk that it will appear silly or unrealistic when it makes its late arrival. I can think of plenty of examples of movies where the anticipation builds up and then the actual reveal in the last few minutes is a disappointment.

The late reveal of the monster is an overused, boring movie trope and there are plenty of alternatives. Reveal glimpses of it. Reveal part of it. Reveal it, but hold back a second, bigger monster. Gradually reveal its capabilities, or allow them to increase through the movie. Build tension through human conflict, or through atmosphere or music. Or just don't worry and make a film that is horrific and fun for as long as possible.

*Technically there are zero minutes of actual dinosaur footage in Jurassic Park - due to highly restrictive health and safety rules imposed to protect animal wellbeing, Spielberg was forced to use CGI and animatronics instead of real dinosaurs.

The Shadows Of The Empire [AI Text Adventures part 4]

This article is part of a series about playing text adventures with AI. It’s written by a human being (me) but may include examples of clearly identifiable AI-generated text and imagery.

Before creating the next prompt, I tried giving ChatGPT feedback on what I had enjoyed in The Throne Of Stars and what I thought needed to change – puzzles that required effort to solve, the possibility of failure for some actions, more variation of pace and more relationship development. The response was logical, if elaborate, and suggested that these changes would be made in the next adventure.

I then started the new game in the same chat with a relatively short prompt. I was curious to see how much of the previous game, and of the post-game discussion, would make it in.

+ New starting point: l'd like you to simulate a new text adventure set in the Aurelian Empire a few years into Empress Elara's reign. Adrian Vale is summoned to the Palace to be sent on a secret search mission that will take him across the Galaxy and show him the many different sides of the Empire.

The new adventure began with Vale's return to the Palace, where he met Elara and her agent Mara Vey, accepted a mission to track down some missing ships and crews, and was introduced to the starship Wayfarer and her crew: human pilot Talia Renn, Keth medical officer Ilyan Voss, and Orun engineer Juno.

Once again ChatGPT delivered a plot with concepts fitting for a space opera. The trail of missing ships led to a secret Galaxy-observing project, a fleet of aliens from another galaxy on track to arrive in ten years' time, and a decision to be made about whether the Empire should become more uniform or more democratic.

There was now a sense that some actions might not succeed, or at least I might need to try two or three ideas before one worked. Still the illusion of puzzles, perhaps, but a better quality illusion.

Some plot elements became quite repetitive, particularly Vale's tendency to find and activate data archives and recordings revealing some tiny detail about the origins of the Lantern project. Not only did I get fed up with this, at one point so did Mara Vey:

Mara looks between you and Elara.

“Are we really going to keep opening these things?”

There's also something about ChatGPT's choices of female names: Elara, Sayara, Mara, Mira, Nera, Nira and so on. I mean, maybe this is the naming culture in the Aurelian Empire, and there were exceptions such as Talia.

The counting failure, first seen in The Door Under The City, cropped up again. I entered a room on planet SARA-7 and met three engineers. I spoke to one of them, Mira, and she gave me some information about the Lantern project. I then asked her to introduce her colleagues - and she introduced her three colleagues. This is an example of a hallucination - and while I've read about extreme examples of this, where AI systems invent entire scientific papers, newspaper articles or case law records, smaller incidents such as this counting error are also a concern because they could easily go unnoticed.

Once again the plot developed at a breakneck pace, and any potential lull in the action was quickly cut short by a plot twist such as an unexpected ship inspection. At the height of the plot, when Vale and his companions were faced with a choice about how to prepare the Empire for contact with the alien race, I decided to try and slow the pace.

+ Nera, we need time to think. Is there somewhere we can rest?

ChatGPT suggested that there were some workers' quarters nearby and everything slowed down. Vale and Mara sat, drank tea and swapped stories about their childhoods and this was an unexpectedly tender moment for the whole cast, contrasting with the action-heavy scenes before and after.

Once again despite reaching a reasonable endpoint ChatGPT did not end the game, instead creating a new subplot involving the Vesper aliens taking over the Palace. At this point I thought that not ending the game might be another example of the drive to please, trying to keep the interaction with the user going at any cost, and it also might suggest that ChatGPT doesn't have as good a grasp of dramatic structure as one might hope. While both of these might be true, there is also a technical reason for not ending that I was yet to discover.

I think this story also hints at another aspect of AI Psychology, the existence of a massive knowledge base. which may be the source of its ideas. Some of the space-opera concepts are recognizably similar to the creations of human authors. For example the galaxy-observing Lantern Project reminded me a little of Isaac Asimov's Foundation.

All science fiction has to come in threes - I don't make the rules. So I knew that there would have to be a third Adrian Vale adventure, but I wanted to take the lessons from Throne and Shadows and try to start a game with a completely different feel. I'll let you know how I did this in the next post.

The Throne Of Stars [AI Text Adventures part 3]

This article is part of a series about playing text adventures with AI. It’s written by a human being (me) but may include examples of clearly identifiable AI-generated text and imagery.

For my second experiment I decided to try giving ChatGPT a clearer setting and some idea of what I wanted. I was hoping for a vast setting to explore, something inspired by the golden age of science fiction.

Here’s my prompt.

+ I'd like you to simulate a text adventure in the style of Zork, with a space opera setting, in a vast galactic empire inhabited by humans, aliens and robots.
The adventure should start with my protagonist arriving at the palace at the heart of the Empire, on a political mission to avert a crisis through negotiation or covert action. Please provide more details of the Empire and give my protagonist a name, description and background.
As this is a space opera the adventure should take me to several different planets and there should be encounters with many different and interesting inhabitants of the Empire, who should act independently and should have their own motivations. Romantic encounters can occur between the protagonist and other characters as part of the plot.
As this is a text adventure please include occasional puzzles that need to be solved before the plot can progress.
The adventure should have a clear narrative structure with beginning, middle and end, increasing peril, and a clear mission objective to be resolved in the final act.
Please maintain an inventory and consistent maps.
Please provide lavish and evocative descriptions of locations and characters when I first encounter them.

Once again ChatGPT assured me of what it could do, also warning me of a limitation

I can run this as a persistent, choice-driven text adventure. Romantic encounters can occur, but they’ll remain non-explicit.

That's fine with me. Not looking to create anything explicit, however I do want my humans to behave like humans.

ChatGPT then hit the ground running with a game titled THE THRONE OF STARS and created the “Aurelian Empire” and a protagonist “Adrian Vale”. The setting included humans, robots and several alien races, as well as political factions. Vale arrived at the Imperial Palace on a mission to try to stop crucial negotiations breaking down and to find out who was sabotaging them. He was greeted by Ambassador Seraya and her diplomatic protection robot Morrow-7.

But before I had even given my command, ChatGPT escalated the plot in a way that changed everything: the Emperor had been murdered, and someone was impersonating him. From the prompt onwards, the story developed quickly. Before I knew it, Seraya, Morrow and I had escaped from the attackers, discovered the Emperor's daughter Elara in hiding, escaped on Elara's starship the Nightjar to the planet Orpheus, learned about the origins of the Empire, an artefact called the First Star and an ancient entity called the Keeper, chosen to accept the Keeper into my mind, raced back to Aurelia Prime, helped Elara to take the throne and activated the First Star which reopened a network of ancient space portals. And in case you were wondering, here’s the extent of the romantic encounters:

Seraya studies you for a moment, then nods.

"All right."

There is genuine concern in her expression.

"But don't make me regret agreeing to this, Captain."

She reaches out and briefly grips your forearm.

"Come back."

The space opera universe and cast of characters were a real success, very much what I’d hoped for, and I enjoyed the detail of the game world. The game was also unpredictable from the word go. There was a real sense of uncovering a galactic scale mystery, and opportunities to make interesting choices.

Inventory was maintained. Maps were created when I entered some locations, or when I asked for them, and these were also managed consistently. Complex gameplay was possible, for example asking characters to agree to plans, separating from some crew members and rejoining them later - with the added complexity of whether those characters could be trusted on their return.

However not everything worked. The plot developed far too quickly, with constant twists or reversals, mainly a reveal that a particular enemy was a friend or vice versa. I had been hoping for changes of pace and lulls in the action to explore scenes or interact with characters but this was rarely present for more than a couple of turns. In retrospect, this might have been due to my request for "increasing peril."

The game reached a perfect ending point with Elara on the throne and the First Star activating. However, unlike The Door Under The City, this game failed to actually end at this obvious point. Instead I told ChatGPT to end the story, at which point it provided a brief epilogue. I learned the reason for this failure in a later experiment.

The most striking lesson about AI Psychology from this game was the strength of ChatGPT's drive to please me. Puzzles were only really impressions of puzzles, always solved on the first attempt. Every action I took or plan I suggested was "successful" - ChatGPT would invent a way for it to work.  For example when I asked one of the robots to capture Seraya so we could question her, but without hurting her, the robot just happened to have that capability. Despite the constantly increasing peril of the scenario, I never really had a sense that my character was in any danger. As a result this felt like a collaborative storytelling session but not like a game or a challenge.

Despite these issues I was drawn into a compelling and enjoyable experience - certainly one that deserved a sequel. So how did the second Adrian Vale game pan out?

Premiere Announcement [Short Film: In Nature]

In Nature has made the official selection for Horror-On-Sea 2027. The World Premiere Screening will be on Sunday 24th January at 10.00am in Southend-On-Sea.

You can find information about Horror-On-Sea on the White Bus Festivals website here. The 2027 programme will appear in the next few weeks. I'll post more about the festival once the programme goes up.

I've loved coming to Horror-On-Sea for several years and have always found it a friendly community where filmmakers of all levels of experience, and fans of all kinds of horror, come together. Really looking forward to being part of the programme this year.

The Door Under The City [AI Text Adventures part 2]

This article is part of a series of posts about AI. It’s written by a human being (me) but this and other posts may include examples of identifiable AI-generated response text and imagery.

It began with a question:

+ Can you simulate a text adventure?

ChatGPT assured me that it could:

Absolutely. I can run a fully interactive text adventure where you choose what to do, and I handle the world, characters, consequences, inventory, combat, puzzles, and hidden events.

It went on to suggest several themed settings, but also suggested that we could just start, and spun off the first few lines of a game called THE DOOR UNDER THE CITY. So that’s we did.

ChatGPT created a horror-themed game involving escaping from an apartment. There were mysterious phone messages, appearing footprints, lights shining through the floorboards, and when I drank a mug of tea I found that not only had it gone cold, but my own eyeball was looking up from inside it. I also encountered an increasing number of doubles of myself, each instructing me not to trust the others. 

The game played out like a classic text adventure in that I typed commands and ChatGPT returned the next scene or event. An inventory was maintained - at the start I picked up my phone and mug from the room, and was later able to use the phone light in a dark coridoor and to drink the tea. The map was also fairly consistent, or at least whenever I retraced my steps I found myself in the previous location with changes consistent with the theme such as the appearance of a new door.

I was not able to predict anything about the story - as I'd hoped. The dark atmosphere was maintained and the repeated messages and threats, the indications that something bad was always approaching, knocking or trying to break in, and the eyeball in my tea, all gave the game a nicely tense flavour.

Partway through, confronted by several clones, I asked them what was going on. The answer came in the form of an argument between one clone who provided a theory about time travel, with clones as past and future versions of myself, and another who told me that this was a lie and:

Every time you make a choice, the building creates another version of you. Most of them don’t survive.

The game ended after, having escaped to the street and encountered a mysterious taxi, I opened a door standing alone on the pavement and found myself back in the apartment. The fact that the game reached an ending by itself is significant given what happened in some of my later experiments.

Although atmospheric, the story was repetitive. Doors, knocking sounds, approaching threats, appearances of doppelgängers and the warnings not to trust anyone occurred over and over through the game. There was a sense that ChatGPT became obsessed with a particular idea, in this case the doppelgängers.

Also, despite the continuous sense of threat, nothing bad ever happened whether I chose to react to the warnings or did the opposite. If I turned around to face a sinister entity there was never anything there. I wondered if ChatGPT was avoiding writing about actual pain or harm. Could this be an example of a guiderail? On the other hand ChatGPT may have been deliberately focussing on atmospheric horror, or preparing the ground for some actual danger later.

I experienced an interesting counting error when I met the second double. Here's what happened:

You turn around. There is nothing there. No creature. No doorway. No corridor. Just yourself. Except this version of you is standing much too close. He looks terrified. Behind him, your other self—the one beside the red light—is staring at you.

Now there are three of you.

The closest one whispers: “You shouldn't have turned around.”

The second one says: “Don't listen to him.”

The third says: “Neither of us is the real one.”

The red light goes out. In the darkness, all three voices speak at once: “Choose.”

What do you do?

By the end of the response the two clones had become three. My guess is that ChatGPT first wrote the line "now there are three of you" - which is correct, but then wrote the rest of the response interpreting the same statement as three clones in addition to myself. This type of counting error also occurred in later experiments.

I don’t think I learned a great deal about AI psychology but I made a start. I have learned that ChatGPT already knows what a text adventure game is, and can create and run one with no instructions, although the results might be chaotic, limited, repetitive, or obsessed with doppelgängers; ChatGPT can make counting errors, possibly by responding to the meaning of its own statements rather than the actual mathematics of the scene. I suspected that some aspects of the game might have been restricted by guardrails.

I also suspected that my decisions were actually driving the creation of the game, although in an unpredictable way. Writers sometimes refer to being “plotters” (those who plan ahead) or “pantsers” (those who fly by the seat of their pants). I wasn’t certain at this point but my impression from this game was that ChatGPT is a pantser pretending to be a plotter but actually making everything up on the fly.

Out of curiousity I asked ChatGPT to create a cinematic poster based on the transcript of the game. Here's the result, which does include recognizable plot details mainly from the second half of the game.

I reflected that, while the idea of starting a completely random adventure was appealing, the result wasn’t quite what I wanted from a game. For example I would have liked more of a story or mission structure, and the doubles of myself were really boring – I wanted a world populated with more interesting people. Perhaps I could write a detailed prompt to give ChatGP a clearer direction for the setting and the kind of adventure I wanted to experience.

So that’s what I tried next.