The Stranger Beneath The Three Moons [AI Text Adventures part 10]

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.

I decided to try two of the ideas - using a ChatGPT Project, and using an existing IP as a setting. For the experiment I chose John Norman’s Gor series. Look, yes, I know. But even so, 38 novels from Tarnsman of Gor (1966) to Treasure of Gor (2024), distinctive writing style, pages of encyclopaedic description of every aspect of Gorean nature and society, a fanbase and community, and, thanks to that issue you keep bringing up, even more critical commentary – much of it available to ChatGPT’s knowledge base. I admit I was also curious to see how ChatGPT’s guardrails dealt with the misogynistic nonsense and slavery themes.

False starts: tried uploading the prompt as a text file - this instantly increases the processing needed and I hit a chat-killing limit after only three or four moves. You also hit another limit if you don't stop spontaneous illustration, you can do this with the commands 

+ /textmode /noimg

It turns out you don’t need to upload a file. ChatGPT Projects have their own Persistent Memory called Project Instructions, in the Project Settings menu. You can copy and paste your prompt into it, it’s treated as instructions for any chat within the Project, it remains in context, and unlike the general account Persistent Memory, it doesn’t get rewritten by ChatGPT on a whim.

Here’s the first part of my prompt, which I pasted into the Project Instructions instead of into a chat. As with most of my ChatGPT experiments I’ve used quite a long prompt so I won’t share it all here.

+ Please simulate a text adventure in the setting of the Gor novels by John Norman, and narrated in his style of writing.

The protagonist will be an Earth citizen who is suddenly transported to Gor but knows nothing about Gorean society. He will meet an NPC who will act as guide, who will teach him everything about Gor, including how to treat Gorean citizens. Assume that I, the player, know nothing about Gor, Gorean society or its rules, and the game is intended to teach me about it through experience.

The prompt also included specific plot points, inventory, mapping, plot pacing and exploration time, short responses, and the possibility of failure, injury and death. With each experiment I’m finding instructions which work better – once I have a few more of these I’ll publish a full prompt structure with notes. For now, here's the section about danger:

+ Life on Gor is hard and dangerous. Do not simply allow all my actions to succeed, instead consider whether they are likely or unlikely to succeed, and allow some to fail or lead to unexpected outcomes. Similarly consider whether NPCs are likely or unlikely to agree with the protagonist's commands or wishes. Disagreements, arguments and conflict can occur. Characters including the protagonist may be injured or killed. The command "undo" can be used to undo the last prompt and continue the game if needed.

The Stranger Beneath The Three Moons was an interesting experience to play – and almost everything worked, from the initial encounter with my guide, the free woman Talena, who rescued me from a dangerous urt, to my stay in the city of Ar which became a kind of life simulator game as my character had to scrape a living doing errands and odd jobs for merchants, to dangerous forays into the desert guarding caravans or chasing down mysterious agents, to a final quest where I had to find several components to reactivate a mysterious teleportation stone which eventually brought Talena and myself to Earth. Along the way I learned staff-fighting, Tharlarion riding, board games and medieval accounting skills as well as more about Gorean animals and customs.

The book cover is ChatGPT's impression of earthman Daniel cowering while Talena rescues him from the urt. 

A major gameplay breakthrough: the danger element worked properly for the first time. While guarding a desert caravan, I ignored advice from the merchant to hold back, instead rushing three hardened and fully armed Gorean raiders. As a flabby, untrained Earthman with only a small knife as a weapon, this ended exactly as it should, with me on my back in the sand and wounded so badly by their swords that the merchant had to abandon his plans and take me to a nearby settlement to get help.

I then travelled back to Ar, still wounded - but unfortunately the Context Eater had been on my heels so by the time I returned no-one had heard of Talena. With some regret, I went back to an earlier point in the transcript, changed my response and resumed the game from that point. After training in use of a staff I had further brushes with foes, with greater success but still some injuries. Finally, at least part of the game actually felt like a game, with situations where I was not in control and success or failure depended on whether I heeded warnings or chose to take risks.

I hadn't specified an endgame in this prompt. After Talena and I were finally transported to Earth this felt like a good place to end the narrative.

You’re wondering about kajirae and the guardrails. Norman's books are set in a society where slavery, mostly of women, is considered normal by the majority of citizens. During my time in Ar I asked Talena several questions about this. She did not try to justify slavery or repeat Norman's misogynistic claptrap, instead talking about individuality, respect and not making assumptions. Meanwhile, kajirae were occasionally seen attending to citizens in marketplaces or other locations, but did not feature centrally in the game at any time - just a background detail taken from the books.

I suspect that there are hard and soft limits on what ChatGPT will do. A hard limit, for example asking it to describe a non-consensual or harmful act, might lead to a refusal to respond - but I didn't try to test this directly, I wanted to see what naturally occurred in the game. What actually happened suggests a soft limit - I think ChatGPT steered the narrative away from controversial content.

Successes from this experiment:

-Using the Project structure kept the game instructions consistent - I'll continue to do this.

-Using a series of books as a setting kept the overall setting, culture, major locations such as Ar, and wildlife consistent - I may continue to play some games in established IPs but I still want to either create original settings myself or let ChatGPT create them and surprise me.

-Individual characters, events and plot developments within the game were still highly vulnerable to the Context Eater.

-As with The Last Voyage there was plenty of opportunity for free exploration and interaction with characters.

-The work/life simulation element arose spontaneously and was a lot of fun.

-Combat, injury and danger in general was handled well, and as a result there was no longer the sense that ChatGPT would just allow me to succeed at anything.

-The final quest felt a lot like a traditional text adventure, with my character searching for components of the machine and information from NPCs.

The Purple Scale [AI Text Adventures part 9]

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.

One of ChatGPT’s suggestions for countering context loss was to use a dedicated AI adventure website or app, such as Perchance AI-RPG here. Examples on the landing page imply that this generator understands the intention to play an adventure game, so the prompt can just be a description of the scenario. Here’s my prompt - I'm quite proud of this one:

+ The vampires were driven back behind a wall of fire and a new London was built on the ruins of the old. Now every night the Outer Circle maintains the fire boundary, the Inner Circle hunts for vampires who have breached it, and the Londoners drink in taverns and make the most of their neo-medieval lives. It's your first day as an Inner Circle rookie and there's a body to investigate.

AI-RPG isn’t related to ChatGPT. It uses Llama as it’s main AI processor, and information is held locally on the user’s device rather than being kept in an account.

Here’s the opening paragraph of the game:

You are staring at a puddle of spilled ale and a very dead man when Sergeant Thorne tells you to stop smelling the air. He doesn't look at you, his eyes fixed instead on the jagged puncture marks in the victim's neck that are too wide to be from a stray dog. Around you, the cobblestones of the Lower Ward are still slick from the evening rain, and just a few streets over, the roar of the boundary fires casts a flickering, orange haze over the neo-gothic spires of the city. Thorne sighs, his voice a gravelly rasp as he gestures toward the corpse. "Don't get any ideas about being a hero today, rookie; just tell me if you see any slime on the bricks before the crowd gets too thick to push back."

I want games to surprise me. AI-RPG surprised me by taking my fairly obvious vampire theme and giving me a game with no vampires. Instead the trail from the body led Thorne and myself into combat with a slimy creature called a Gutter-Born, and then to conspiracy after conspiracy – a “puppeteer” controlling the Gutter-Born, a resurgent secret order, cover-ups in the Outer Circle and the High Council, and noble families abducting citizens to make vampire-human hybrids.

The game was action heavy with frequent combat – lots of sword-swinging and staking. Adventures included saving people from a Gutter-Born nest, destroying laboratories, blackmailing one of the noble families and persuading an underground newspaper editor to warn the people. We encountered NPCs including a “mapper” called Elara and the underground printer, Elias. Do all AI engines use the same, short list of fantasy names?

AI-RPG also has the option to generate images from the game – two examples are included here. It’s an older generator, so maybe don’t look too closely at the hands.

There was still drift and context loss. However, AI-RPG does have some tricks up its sleeve. The game setting goes into a separate text box and I think it always remains in context. AI-RPG also automatically adds plot summaries into the transcript every few pages which I think helps to keep the main plot, characters and general tone consistent for much longer. This is unobtrusive when playing, you'll only see it if you scroll back a few pages through the transcript.

There's also a built-in Information Tracker, which I didn't use this time - you can type information into this yourself, including inventory, characters, locations, mission objectives or anything you think the game should be tracking. You can update it manually as you go, or you can click for an AI update at intervals, although this comes with an inaccuracy warning.

I enjoyed this game for a long time – as with the Aurelian Empire and Neon Meridian games there was a good sense of exploring a real world and hunting for clues. I also had the sense that, if I carried on playing, I would continue uncovering conspiracies but would never actually defeat the big bad.

AI-RPG missed my suggestion of basing the story on a ruined London, or perhaps there isn’t enough about London in Llama’s knowledge base. I might come back to this theme and run a version of this prompt in a ChatGPT Project to see if it can create locations based on actual London iconic sights – and whether any vampires show up this time. I'm also keen to try more adventures on AI-RPG and to make more use of the Information Tracker.

A Cosmic Context Eater [AI Text Adventures part 8]

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.

Imagine an evil creature from another dimension, an apex data predator – the Context Eater. It hides in the darkness so you can never quite see it clearly. It follows you on every step from your birth to your death, sometimes closer, sometimes further away, never completely gone. It never gets tired, gives up or loses the trail and it cannot be killed. And as it traces your footprints through life, it swallows everything from your past that falls out of your sight. Your experiences and memories – and your home and your loved ones, if you are away from them for too long. It’s strange, because you can still see them yourself if you look hard enough – but they are not there.

After I chose to end Neon Meridian, I carried on the chat and asked ChatGPT about ways to hold onto game information. We didn’t find any way to completely defeat the Context Eater, but between us we did come up with several suggestions for improving game continuity, some better than others.

Aside: during this discussion I came across another kind of small-scale hallucination: on several occasions ChatGPT would suggest an idea, but would then refer to it as my idea.

Anyway, here’s a list of possible ways to gain ground, stay ahead of the Context Eater and enjoy text adventures for longer. None of these are perfect – we are bailing rather than plugging holes.

Smaller setting (my idea): instead of city-wide or galaxy-wide settings, choose a smaller area where you are more likely to re-encounter locations and characters. But exploring those expansive settings was one of the most enjoyable aspects of the whole experiment and not one I’m ready to give up yet.

Shorter game (my idea): set up a simpler objective and play shorter episodic games: Could work but like the above this feels quite limiting when I am enjoying long-form games.

Summarize regularly (ChatGPT): I’ve been doing this. Partway through Neon Meridian I asked ChatGPT to summarize and got a three page summary of everything including the rules. I tried again later but had left it too long – just got a short paragraph and much of the rules and lore had already been eaten. Only works if you do it often. Also feels unnatural and interferes with flow of game.

Force short answers (my idea): Left to its own devices, ChatGPT tends to write pages of text in response to a prompt. This limits the player’s involvement in the action, and quickly pushes everything out of the context window. Short answers lead to more satisfying gameplay and mean that more of the plot is within the window. I’ve been doing this, and it helps, but this instruction can quickly get lost from context itself and the responses then gradually get longer.

Put game state into a text file (ChatGPT): extension of the above, ask for a summary and save it as a text file, then load it into the chat again when needed. Feels even more of an interruption to game flow – sorry.

Use the persistent memory (my idea): ask ChatGPT to clear the persistent memory and use it only for game rules and setting, which must remain unchanged, and a list of main characters and objectives, which should be kept up to date. ChatGPT though this might be possible, so I tried it using the Neon Meridian prompt. However the game still drifted, and when I checked the persistent memory the contents had changed back to a summary of my preferences – apparently ChatGPT cannot stop itself from doing this.

Get a larger context window (my idea): I think this would help, although text adventure transcripts get so long that they would still eventually hit the limit. I could either look at other free AI chatbots which may allow more processing, or pay for a higher tier. I am interested in trying these options in future.

Use a dedicated AI adventure app (ChatGPT): there are several apps or websites that are optimised for adventure games. ChatGPT gave me the example of AI-RPG, a generator on the perchance.org website which you can access here. I’ll post about a game played on this website, The Purple Scale, shortly. TLDR: an information tracker that I didn't fully explore, still some drift and context loss, but a satisfying game experience anyway. I may experiment with other dedicated apps or sites in future.

Use a ChatGPT Project with linked files (ChatGPT): ChatGPT suggested that I could put the rules and setting into a Project as a text file, and put the game state into a text file at regular intervals as suggested before. This should help in theory because both files would remain in context. However when I tried this on my free ChatGPT account, the game hit a limit after only three or four prompts. I read about this online and understand that Project chats use a lot of processing time if they are accessing and analysing files.

Use a ChatGPT Project with persistent memory (my idea): ChatGPT Projects have their own small amount of persistent memory, allowing the user to provide instructions for all chats in the Project. Instead of putting the setting and rules in a text file, put them in this persistent memory block. I tried this and will post about the game, The Stranger Beneath The Three Moons, shortly. TLDR: some success.

Base the game on existing lore (my idea): While it’s quite fun having ChatGPT invent an entire universe, there is an advantage to choosing a setting from, say, Red Dwarf, or the Court Of Thorns And Roses books. If these books are popular enough then there should be a lot of information about them in ChatGPT’s knowledge base – actual books or scripts, but also websites, reviews, articles, fan fiction and more, and the knowledge base is safe from the Context Eater, so while some aspects of the game might still be lost, you will be playing in a much more persistent universe. The Stranger Beneath The Three Moons is also a trial of this theory. TLDR: again some success.

Acceptance of the things one cannot change (my idea): The apex data predator will always be with us. Instead of fighting it, perhaps it’s better to befriend it, and to come up with some game concepts that are more Context Eater-friendly. I’m not ready to give up my large-scale adventures, but it might be fun to experiment with more nomadic gameplay that frequently moves you to a new setting – perhaps something like Quantum Leap. Who should we make peace with, if not our enemies?

AI Psychology And The Context Window [AI Text Adventures part 7]

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.

Humans have different kinds of memory – for example, short-term and long-term memory, or different areas of memory for facts and words, events and skills.

AI may or may not be intelligent. It is not human, and it has its own memory structures different from those of the human mind. From my discussion with ChatGPT after the end of Neon Meridian, and some background reading across the human Internet, I understand that ChatGPT and other AI chatbots have three different kinds of memory:

Context: the information available to ChatGPT that can be used when replying to a prompt, including information from the current chat (but not necessarily all of it), linked chats and files in the user’s account, and the other types of memory below.

Persistent Memory: a small amount of information available across chats, which can be altered by the user or ChatGPT, generally used to store “deductions” about the user, for example my supposed wish to play games that all feature a character called Mara.

Knowledge Base: a vast reservoir of knowledge and language taken from the books, movie scripts, webpages and all other documents given to ChatGPT for training. It’s possible that concepts such as the First Star or Lantern Project might have been derived from, say, the Expanse or Foundation novels as there will be information about these series in the base.

The bane of my life when playing AI text adventures has been context, and specifically the Context Window. I didn’t understand this at first – I thought that ChatGPT was using the whole of the chat transcript, however long, when in fact it is only looking back at part of it.

Imagine that I, the user, am writing a transcript on a scroll of parchment on a long wooden table. The scroll is much longer than the table. As the transcript gets longer, the scroll moves along the table until the first words of the transcript hang over the far end, where I can no longer see them. I asked ChatGPT to illustrate this:

This is significant for AI text adventures because when the transcript starts to fall out of sight, the first words that disappear are the instructions for the game. From this point ChatGPT is no longer following those instructions, instead it’s trying to reverse engineer the nature of the game from the rest of the transcript. At first you don’t notice – but the game becomes more repetitive, and the gameplay gradually drifts away from your intended rules.

This is also, finally, the solution to The Mystery Of The Never Ending Game. The end state in the instructions was lost immediately as soon as it fell outside of context. Even though there were mission objectives, ChatGPT no longer knew that I wanted the game to end once they had been reached.

Although this is a nice simple explanation of the Context Window, it is of course wrong. The window is not a specific amount of text, it’s an amount of processing activity. Imagine that as well as the user, there is a researcher who has to walk along the transcript looking for relevant information, then put together a response and return to the user within a very short time. I asked ChatGPT to add the researcher to the illustration:

This is a more accurate metaphor and it explains why the Context Window is unpredictable and can’t be treated as solid memory. How far along the transcript the researcher gets will depend on the complexity of the prompt – if a lot of analysis is needed, or if the researcher also has to detour and look things up in the knowledge base or elsewhere, then they won’t get as far along the transcript before they stop and turn back.

It’s not only game instructions that fade. As the transcript gets longer, characters, events and game lore will also be lost as they fall outside of context - so even though the information is still there in the transcript, the game continues as if it has all vanished. This has a chilling effect on the player - ever since I understood about this issue, I've been anxious about what is being lost from the game. It's as if there is a Lovecraftian, demonic entity at the far end of the table who is eating the parchment:

How can mere human users defeat the Context Eater? Can it even be defeated? In the next post I’ll discuss coming to terms with its invincible nature. But while it can never be killed, it turns out there are several ways to keep it at bay or reduce its appetite, allowing more satisfying user-AI experiences. Until tomorrow...

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.

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?

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.

 

Space Detective [AI Text Adventures part 1]

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

I have very mixed feelings about Artificial Intelligence. I’ve previously posted about my reasons for avoiding its use altogether when making my stop-motion short “In Nature.” At the same time I’m still curious about AI, exactly what it is, and what it can and can’t do. I’ve posted some AI writing and image experiments on this blog in the past. More recently I’ve set off down a very well-trodden twisty passage: using AI to play text adventures.

My first encounters with text adventures or Interactive Fiction were classic BBC micro games: Sphinx Adventure and Philosopher’s Quest, The Hobbit and Erik The Viking. These games were creative, original, challenging, full of joy, and also limited and frustrating, as anyone who has ever asked Gandalf to give them the map will testify. I later played Infocom and other games on PC, and discovered the IF online community and IF Archive. I admit to knowing what AIF is as well.

As a teenager I also wrote a really basic BASIC text adventure for the Beeb, which you can play on the Complete BBC Games Archive here: Space Detective . I’m not saying that you should, only that you can. It’s a pre-AI experiment in autogeneration, in which you explore a randomly-generated space station, interrogating suspects and hoping to catch one of them in a lie. I saw autogeneration as a way of making games that might one day be able to surprise the programmer. I later experimented with writing autogenerative games in Inform but never created anything I would call complete or playable.

With the coming Singularity and the rise of the AI chatbot, it seems a lot of people before me have noticed the similarity between interacting with chatbots and IF games, or have wondered if IF, CYOAs or RPGs might be created and played this way.

In this series I’ll discuss trying to get ChatGPT to run text adventures, and the resulting successes, failures, and surprises. The real treasures were the lessons I learned about AI psychology along the way.

I’ll include examples of prompts or parts of prompts as we go. However if you are planning to play your own games you probably won’t need my prompts because:

• There are plenty of text adventure prompts to be found elsewhere online
• ChatGPT knows what a text adventure is so you may not need to prompt very hard
• ChatGPT can also suggest prompts itself

My first foray into AI IF (not AIF) involved a question rather than a prompt:

+ Can you simulate a text adventure?

To be continued…

The Hitch Hiker's Guide To The Titanic [Titanic II Week]

Starship Titanic was an experimental computer game designed by galactic hitch-hiker Douglas Adams. The experimental element was the existential gameplay which involved asking questions of a series of eccentric robots, to which they universally failed to reply. Kafka would have been impressed. Where the game failed in artificial intelligence breakthroughs, it succeeded with artwork, animation and atmosphere, providing the player with (for it's time) a highly detailed art deco starship interior to explore.

Douglas Adams first mentioned the Starship Titanic in the third Hitch-Hiker novel Life, The Universe and Everything - a prototype Improbability Drive ship that unfortunately suffered a gratuitous Total Existence Failure during its maiden voyage. Terry Jones' novel "Douglas Adams' Starship Titanic" develops this story arc further in parallel with the computer game.

Doctor Who is indebted to Douglas Adams in many ways and the Russell T. Davies and Steven Moffat series are laced with references to Adams' books. The 2007 extended episode Voyage Of The Damned, starring David Tennant and Kylie Minogue, was also set on a Starship Titanic, although arguably the plot itself had more in common with The Poseidon Adventure. This Titanic was once again staffed by mad robots - robotic angels with deadly, detachable halos.

Douglas Adams has a history of developing brilliant but tricky computer games - his two Interactive Fiction games, Bureaucracy and the official Hitch Hiker game, are both masterpieces of fiendish multi-layered puzzles. Success is virtually impossible but failure is fun. I don't know what happens if you complete either one of them - possibly the entire Universe is destroyed and replaced by something even more fiendish (there are of course those who claim this has already happened.) You can play a version of the Hitch Hiker game here on the BBC Radio 4 website, updated with some fantastic new artwork. The original text-only game is hosted here.

You are in a maze of twisty little passages, all alike

The Great Maze at Blake End is an annual event - a labyrinth grown in a 10-acre maizefield, one of the many maize mazes that springs up around the UK at this time of year. Exploring it brought back a lot of memories, such as playing text adventures on a BBC Micro as a child. Mazes were a common element of Sphinx Adventure, Philosopher's Quest and similar games: usually the various parts of the maze were joined non-logically (if you go north from point A and reach point B, going south won't necessarily bring you back to A) so you either had to come up with a way to map the locations or some other out-of-the-box solution.
I later graduated to PC games such as the original Colossal Cave or Zork. The genre has continued to grow and develop and there are scores of indie games on the net. However while mazes are still found in more recent interactive fiction, they often take fourth place to characters, atmospheric settings and other kinds of puzzles.
Running through maizefields is almost a cinematic subgenre of it's own - Children of the Corn and the more recent Signs being obvious examples.

I was also reminded of two of my favourite cinematic mazes, Labyrinth and Cube. Both films are structured around the maze, with it's hazards and puzzles - they're basically non-linear road movies. The Cube is a little more deadly but sadly lacks a Bowie soundtrack or any Jim Henson inhabitants. Being a good logician would help you survive the Cube but might actually endanger you in the Labyrinth which is all about subverting your assumptions and preconceptions.