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?

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…

Global Superpower [Review: The WONDERfools episode 1]

Started the first episode of The WONDERfools this week and was completely gripped. The episode opens on Eun Chae-ni (Park Eun-bin, star of Extraordinary Attorney Woo) who lives and works in her grandmother's restaurant, dreams of travelling, has a severe heart condition, no money and lots of punk attitude. Within the first 1-2 minutes there's a fantastic, character-defining scene where she takes on a group of street evangelists announcing the end of the world.

This opening episode is about establishing characters - in addition to Chae-ni, her family and friends, we also meet Lee Un-jeong (Cha Eun-woo), a very junior official in a government complaints office. Where Chae-ni is comically loud and punk, Un-jeong is the opposite, facing down the angry complainant that terrorizes everyone else in the office with a calm, deadpan response. It's early in the series but I feel like it isn't going to be a coincidence that these two have complementary personalities. 

The episode also establishes that there are links between several of the characters, and that pretty much everyone is hiding something. This also applies to the setting, Haesong City, on the surface a regular mid-sized modern town but there are hints of mysterious goings on in the past and the present.

Although I've been looking forward to this series for a long time I didn't know what to expect, apart from a superhero TV show with a different tone from the MCU. I'm now fighting the urge to binge-watch and looking forward to wherever this series takes me.

Everybody Was Mok'Bara Fighting [Review: Star Trek Section 31]

A team of Section 31 special agents on the hunt for a rumoured superweapon must persuade space pub landlord, ex-Section 31 agent and even-more-ex-Mirror Universe evil dictator Phillipa Georgiou (Michelle Yeoh) to ally with them. It turns out this is not the only thing linking Georgiou and the weapon.

In Star Trek history, Section 31 is the Federation's secret service, sent to carry out covert, deniable missions that might be seen as clashing with the Federation's ideology or laws - a lot like Special Circumstances in Iain M. Banks' Culture novels, or perhaps the secret services of our own world. Section 31 first appeared in Deep Space 9 episodes. They have cropped up in Enterprise, Picard, Lower Decks and some of the recent films, and were central to the plot of Discovery, which also introduced Emperor Georgiou.

The Section 31 movie was in many ways not what I had expected. The films and episodes above give an impression of a sinister and super-efficient spy agency, possibly with a mild black leather fetish. It's a little surprising that the team of special agents in this movie, supposedly Section 31's elite, are actually a bunch of comical, clumsy, arguing misfits. How do they ever actually get anything done? And how did powered-armour-obsessive Zeph and work experience girl Rachel, in particular, qualify for the Star Trek equivalent of 00 status?

However this description misses the point of Section 31, which is really all about Georgiou - and about Michelle Yeoh. I first saw Yeoh in action in the mind-blowing martial arts film Crouching Tiger, Hidden Dragon. Yeoh is a talented actor who has appeared in a wide range of roles, not least Everything Everywhere All At Once, but Section 31 is designed to put her martial arts talents centre stage. This is an action-heavy movie in which no opportunity is missed for fantastic, joyous hand to hand combat - unusual in the phaser-heavy world of Star Trek.

Section 31 may not be the best Star Trek movie (obviously that's Galaxy Quest) but it's certainly the best Star Trek martial arts movie.

Score: Three stars out of five.

All movies reviewed on The Sci-Fi Gene blog are awarded three stars out of five.

Zoom And Enhance

For many years now, fans of TV crime drama and sometimes science fiction have been taking the piss out of episodes featuring image enhancement. You know the trope: "stop, that frame, now zoom in, can you enhance that?" and four pixels are sharpened into a UHD quality portrait. Supposedly there are algorithms that can do this, and by coincidence this is something the geekiest member of the CSI:Your Town Here crew has been working on in their spare time. A selection of particularly amusing examples has been compiled by Duncan Robson in the YouTube video above.

However the game has changed. Until recently we could simply laugh and say that no such algorithm exists. Now we know what the algorithm is - it's Stable Diffusion, the principle used by Midjourney, Dall-E and other generative art AIs. And it's no longer impossible - instead it's dangerous. AIs are prone to bursts of creativity and "hallucinations" (the term used by AI scientists to mean "lying"). When an AI enhances an image, the face that is digitally pencilled in doesn't have to be the actual face of the suspect seen on CCTV, it just has to be a plausible image. It could be anyone's face. It could be your face.

So here's my question: how many innocent fictional people in episodes of CSI have been wrongly convicted of the most heinous crimes on the basis of an AI-enhanced image?

JUSTICE FOR FICTIONAL IMAGE ENHANCEMENT VICTIMS NOW

Here’s One We Made Earlier [Review: The Creator]

CONTAINS HUMAN-GENERATED CONTENT

I’ve followed Gareth Edwards’ career with interest ever since his short film Factory Farmed won the Sci-Fi London 48 Hour Film Competition in 2008. He went on to make the low-budget feature Monsters, in which two journalists make their way through alien-infested Mexico, followed by two mega-franchise movies, Godzilla and Rogue One: A Star Wars Story, and now by his new film The Creator.

The Creator is a high-budget sci-fi/war movie epic with a cast of hundreds, a globe-spanning plot and CGI effects in almost every scene – but it’s an original story, not part of a franchise or cinematic universe. It concerns the rise of AI and the war between anti-AI Westerners and a pro-AI Asian nation, seen through the eyes of American soldier Joshua played by John David Washington. It’s well cast and well acted, particularly by Washington, national treasure Gemma Chan and child actor Madeleine Yuna Voyles, and together with the consistently good effects it’s an enjoyable and satisfying movie although I would say the plot is a little simplistic and one-sided, setting up a clear good vs evil story rather than engaging with the complexities of AI that we are grappling with in the real world.

I’ve always admired Edwards’ ability to use CGI intelligently to build believable worlds. Here it contributes to the setting of a believable alternative history where robots and AI became commonplace early in the 20^th century, extended into the near future when the action takes place. Although it has its own distinctive visual style The Creator is not without influence from other movies – in particular many of the robot designs have definitely been touched by Star Wars. Roger roger.

Score: Three stably diffused stars out of five.

All movies reviewed on The Sci-Fi Gene blog are awarded three stars out of five.

Update 7.10.2023: The Guardian has also reviewed this film. Their review is correct (apart from the star rating).

Firefly Season 2 Episode Guide

 CONTAINS AI-GENERATED CONTENT

**Episode 1: "The Heist"**

Zoe receives a job offer from an old war buddy to steal a valuable artifact from a heavily fortified museum. However, when their plans are foiled by unexpected security measures, Zoe must rely on her training and quick thinking to save the crew and complete the job.

**Episode 2: "The Lost Colony"**

Jayne receives a message from an old acquaintance on a remote planet that was once a thriving colony. When they arrive, they find that the planet has been abandoned for years, and they must unravel the mystery of what happened to the colonists.

**Episode 3: "The Huntress"**

Inara's past comes back to haunt her when she is hunted by a former client who has become obsessed with her. In order to protect herself and the crew, Inara must use all of her skills as a Companion to outwit the deranged client.

**Episode 4: "The Diplomat"**

Simon is recruited by a group of diplomats to mediate a peace treaty between two warring factions. However, when the negotiations break down and violence erupts, Simon must put his medical skills to the test to save lives on both sides of the conflict.

**Episode 5: "The Genius"**

River's unique abilities are put to the test when the crew is hired to protect a brilliant scientist who has developed a groundbreaking technology. However, when the scientist is kidnapped, River must use her intellect and intuition to track down the culprits and rescue him.

**Episode 6: "The Outlaw"**

When Mal is captured by a group of bandits, he must use his cunning and charm to talk his way out of trouble. However, when he discovers that the bandits have a personal vendetta against him, Mal must rely on his friends to mount a daring rescue mission.

**Episode 7: "The Ghost Ship"**

Serenity encounters a derelict spaceship adrift in space, and they investigate to see if there are any survivors. However, they soon discover that the ship is haunted by the ghosts of its former crew, and they must confront their own fears and regrets to escape the ship alive.

**Episode 8: "The Traitor"**

When Serenity is hired to transport a group of Alliance soldiers, they discover that one of them is a traitor working for a dangerous criminal organization. As they try to uncover the traitor's identity, they find themselves embroiled in a deadly game of cat and mouse.

**Episode 9: "The Reunion"**

Kaylee is reunited with her estranged father when Serenity is hired to transport him to a distant planet. However, their reunion is complicated by the fact that Kaylee's father is a wanted criminal, and they must decide whether to turn him in or risk their own freedom to help him.

**Episode 10: "The Final Battle"**

In the season finale, Serenity must defend a peaceful planet from an invasion by the Alliance. As they face overwhelming odds, each member of the crew must confront their own fears and doubts to fight for what they believe in.

This episode guide was generated through discussion with ChatGPT. I had to establish that I was asking for a hypothetical episode guide for Series 2 had it been made, and then in response to the first few
attempts I encouraged ChatGPT to avoid repetition and for some episodes to revolve around individual characters. Everything else is ChatGPT. 

Grow For Me [Review: Vesper]

Like literally all of the best films, Vesper begins with text explaining the apocalyptic future we are about to enter: one where biotechnology has gone rogue, destroying much of the world and much of humanity. Rich people live in distant citadels shielded from the bio threats while everyone else scrabbles around in the mud, relying on the citadels for terminator seeds.

Vesper is a young girl growing up in an abandoned farmhouse looking after her terminally ill father. They are hermits who refuse to join the collective run by her uncle, and Vesper ekes out an existence scavenging or trading for food and for the bacteria needed to keep the father alive, while studying bioengineering using materials she has stolen from an abandoned laboratory. Her life changes when a flying biomachine from the nearest citadel crashes, and she rescues its inhabitant, a strange, pale woman, and brings her home.

Watching an indie sci-fi film like Vesper was a welcome change from the Marveltsunami that has swept through cinema in recent years. Vesper’s forest setting and biological creations reminded me of another indie sci-fi movie, Prospect. Both feature a young lead character having to fend for themselves in a hostile world and amongst hostile adults, played by Sophie Thatcher in Prospect and Rafiella Chapman in Vesper. Neither pull their punches when it comes to pain, suffering and despair, and both use special effects sparingly and intelligently rather than simply flooding the screen with lightning bolts.

Along with the understated effects comes the understated villain, the uncle, played by Eddie Marsan. He’s creepy, selfish, deceitful and vicious when he needs to be, but he’s not angry with you – just disappointed. He’s as far from a Marvel pantomime supervillain as they come.

Score: Three perfectly bio-engineered stars out of five.

All movies reviewed on The Sci-Fi Gene blog are awarded three stars out of five.

Roland Limmerich III

 Roland Emmerich's new film is called Moonfall

The Moon's going to pay us a close call

But where will it land?

And where should we stand?

I'm steering clear of the White House, y'all.

A typical Emmerich film features

Lots of rockets and heroes and creatures

What drives this mad artist?

In the depths of his heart is

A desire to annoy physics teachers.

All Time High [Preview: The Challenge]

 As I write this, Russian sci-fi feature Вызов (The Challenge) enters production. It's an unconventional movie featuring a very small production team. The plot involves a cardiac surgeon sent into orbit to save the life of a cosmonaut - and right now, director Klim Shipenko and actor Yulia Peresild are part way through a two-week stay on the International Space Station shooting the movie.

On Tuesday, Oct. 5, cosmonaut Anton Shkaplerov will join actress Yulia Peresild and producer Klim Shipenko on a @Space_Station-bound Soyuz launch, expanding commercial space opportunities in filmmaking.

Our live coverage begins at 4:15 AM ET (8:15 AM UT): https://t.co/FY7OEDbIZN pic.twitter.com/O2yKF7E6Zk

— NASA (@NASA) October 1, 2021

According to this report by the BBC this project has divided opinions at Roskosmos, with some senior managers including Sergei Krikalev, head of crewed missions, strongly opposed to it. This surprised me as Krikalev is himself the star of a movie set in space - the documentary Out Of The Present, which is an account of his record-breaking stay on the space station Mir during a time of colossal political change below him on Earth. He launched to orbit from the communist Soviet Union but returned the following year to the emerging Russian Federation. His film is fascinating, often funny, exciting, inspiring and of historical importance.

Those arguing against the project felt that it would detract from the scientific mission of the ISS. But should science be the only reason for space exploration? If this really is a different way to inspire artists and creators, and to create works of art different from those on Earth, then perhaps experimenting with this new medium is also valuable. Perhaps we should send painters, songwriters and poets into orbit to see what they bring back. And there is certainly value in storytelling to inspire the next generation. In my very brief student attachment at NASA, I learned that NASA is staffed almost 100% by Trekkies - it really is true that Star Trek inspired thousands of people to go into science, engineering and space careers.

Eleven Great Sci-Fi and Fantasy Shows On The BBC That Aren't Doctor Who - Part 2

This is part 2 of my dive into the unmapped, shadowy depths of the BBC, hidden beyond all human knowledge, where in the darkness lurk strange, bizarre science fiction and fantasy productions that are not even slightly Doctor Who. You can read part 1 here.

The Cipher

When 16-year-old genius Sabrina (Anya Chalotra) cracks The Cipher, an impossible online puzzle, she is recruited by a mysterious organization to help in the hunt for a serial killer targetting scientists. Although this BBC audio drama/podcast is also about conspiracies and medical mysteries, The Cipher exchanges the bleak horror of Tracks for a rollercoaster of sci-fi concepts and 180-degree twists in every episode.

Life On Mars

So this is a show about a time travelling policeman, starring John Simm, and it's still not Doctor Who. Instead it's a modern take on Mark Twain's Connecticut Yankee. By-the-book policeman Sam Tyler suffers a head injury which sends him back in time from 2006 to the 1970s, where he finds himself working for DCI Gene Hunt (Philip Glenister), a character who positively embraces the non-politically-correct policing attitudes of the era. As we all know, it is the law that police officers are always paired up on the basis of opposing personality traits, and Life On Mars features possibly the most explosive pairing in any book, movie or TV series ever.

DEVS

Written by Alex Garland, produced by FX and broadcast by the BBC, DEVS is a cyber thriller about quantum computer programmers working for a secretive tech company. Lily (Sonoya Mizuno) gets herself hired in order to investigate her boyfriend's disappearance, while CEO Forest (Nick Offerman, channeling Jeff Bridges) tries to control... well, everything. DEVS features beautiful, chilling set design and lighting which underscores some intense performances and a neat sci-fi concept.

What We Do In The Shadows

This American TV series spins off the original New Zealand movie, set in the same reality but featuring a new household of flat-sharing vampires living on Staten Island. It's only broadcast by the BBC but could easily pass for a britcom, with shades of Being Human and The Office, featuring The I.T. Crowd's Matt Berry and introducing the brilliant concept of energy vampires. Funny and dark.

Fort Salem

One more American TV series brought to the UK and broadcast on the BBC, Fort Salem is set in an alternate timeline where the Salem trials ended with the witches agreeing to become the U.S. Army. Cut to the present day where three witch cadets, Raelle, Tally and Abigail chant their way through their military training under the shadow of General Sarah Alder, learning how to use sound-based magic and who to trust, as the army gears up to fight the Spree, a terrorist witch faction.

His Dark Materials

I have saved the best until last. This non-Doctor-Who fantasy series, based on the books of Philip Pullman, is a georgeous adaptation, innovative in the way the plot is re-worked for television, and at the same time extremely faithful to the characters, settings and overall story. It's more faithful and more magical than the 2007 movie, and unlike the movie the antiestablishment theme is not diluted. The icing on the cake is the casting and acting - Dafne Keen as Lyra, Ruth Wilson as Mrs. Coulter, James McAvoy as Asriel and Lin-Manuel Miranda as Lee Scoresby.

Eleven Great Sci-Fi and Fantasy Shows On The BBC That Aren't Doctor Who - Part 1

Can you have too much Who?

Even as a lifelong fan of the BBC's flagship sci-fi drama, I'm aware that one of the risks of pouring so much investment and energy in to one show is that it can eclipse other shows, particularly other science fiction and fantasy. So it's worth reminding ourselves that, believe it or not, there are occasionally programmes shown on the BBC channels that aren't Doctor Who. And no, I'm not talking about Torchwood. Here, to prove my point, are eleven BBC sci-fi or fantasy shows that are not even a tiny bit Doctor Who.

I should add that some of the shows here are produced by the BBC, often in collaboration with other networks, while others are produced elsewhere and were broadcast by the BBC thereby demonstrating their excellent taste in programme purchasing. I'll try to make it clear which is which.

This is part 1 of the article. You can read part 2 here.

Good Omens

Adaptation of Neil Gaiman and Terry Pratchet's novel about the unlikely friendship between an angel (Michael Sheen) and a devil (David Tennant) both of whom prefer living on Earth to Heaven or Hell respectively. Co-produced by BBC and Amazon and broadcast in 2019 and 2020, this show is funny, inventive and satisfyingly bonkers, and despite starring David Tennant it is definitely not Doctor Who.

War Of The Worlds

Since H.G.Wells first invented the alien invasion trope there have been rather a lot of adaptations of War Of The Worlds. I have a soft spot for the 1953 movie, and would probably describe the Jeff Wayne musical version as my favourite. I'm less fond of the £2 coin adaptation featuring the four-legged Tripod. I really like the BBC's 2019 miniseries. Instead of setting it in the present day, it's a period drama set in the early 1900s. The story loosely follows much of the novel, but centres on George (Rafe Spall) and his scandalous girlfriend Amy (Eleanor Tomlinson) thereby increasing the number of lead female characters from zero to one. We all know the Martians lose, and how, so a good adaptation of WOTW needs to add something original. This series uses flashforwards to show the aftermath of the war - a world still grieving and still on its' knees many years after the Martian defeat.

Tracks

This might be one of the best things the BBC has ever done. Five series of audio dramas, or if you prefer, fiction podcasts, starring Romola Garai as Helen, a GP who is drawn in to a series of conspiracies after she witnesses a horrific plane crash - and rises to the challenge. Written by Matthew Broughton, each series is an intelligent biomedical thriller very much in the vein of Michael Crichton or Robin Cook.

Missions

Broadcast on the BBC in 2018, this is a sci-fi drama about tech tycoons Meyer and Goldstein, who are not at all inspired by Elon Musk and Jeff Bezos, their privately-funded expeditions to Mars and the surprising discoveries they make on the surface. The series follows Jeanne Renoir (Hélène Viviès), the psychologist trying to keep the crew of Meyer's expedition sane; but as this is a French drama, she must also be having an affair with the married captain.

Dracula

Two out of three ain't bad. A completely new BBC adaptation of Dracula written by Mark Gatiss and Steven Moffat, starring Claes Bang as Dracula, and combining the wit and inventiveness of Sherlock with the sumptuous gothic shenanigans of the Hammer Christopher Lee/Peter Cushing series of movies. I loved the first two episodes, set in Dracula's Transylvania castle and then on board a ship sailing for England, and the rivalry between Dracula and his nemesis Sister Agatha (Dolly Wells) which runs through the series. The third episode which brings Dracula into a completely different setting is a gamble, and I found it less satisfying although there's still a lot to enjoy.

To be continued...

I'll Take The High Road [Review: Cloudpunk]

It's a rainy night in Nivalis. You're a recently arrived immigrant and a newly signed-up courier for the slightly illegal delivery company Cloudpunk, delivering parcels to customers around the city guided by the mysterious and melancholy Control. You're penniless and alone apart from your flute and your naive, excitable AI companion Camus the dog. And you have a flying car. It's a cheap pile of junk, handles terribly, and guzzles fuel, but it's still a flying car.

The star of adventure game Cloudpunk is the setting - Nivalis, a massive sprawling neon-infused megacity that you can explore freely in your HOVA or on foot. It's a huge voxellated environment, insanely detailed and full of character. The architecture is extraordinary, and it's alive with activity. HOVAs whip past you along the powered highways or take shortcuts between buildings, and the streets are full of strangers and robots - most minding their own business, but a few who will converse with you, leading to discoveries or side-quests. Even if there were no game element simply exploring the city would be an absolute pleasure. Cloudpunk is basically the game version of every flying car fantasy ever, particularly the neo-noir settings of the Blade Runner films, the Fifth Element or Revenge of the Sith, and it also reminded me strongly of other adventure games I've enjoyed - particularly Omicron: The Nomad Soul, and Anachronox, both of which also feature futuristic cities, free exploration and flying cars.

The main story is told through a series of missions usually taking you from a pickup point to a customer. Rania's conversations with her customers reveal the nature of Nivalis and of this future society, as well as clues leading to a mystery about the city's past. Your meetings with customers are like short stories - you get a brief glimpse of their personalities and lives before moving on to another story.

As a game Cloudpunk is easy. You don't have to learn the Nivalis equivalent of The Knowledge - nav points guide you through Nivalis to your destination. There aren't any time limits on the missions, and there don't seem to be any ways to die or lose - even your encounters with robot gang members and other unsavoury characters don't seem to turn violent. Most of the missions are pretty linear, although occasionally you are offered a moral choice in how you complete them. Fuel this costs money, and you don't earn much as a courier, so getting enough money to buy fuel and repair damage is a challenge, and you'll need to work very hard to upgrade your HOVA or pimp your apartment. Simply flying around the city will eventually use up all your cash, although there are a few alternative ways to make money, such as picking up abandoned items and selling them to merchants.

It's always interesting playing a non-violent game. Again comparing to Nomad Soul's beat-em-up and FPS sequences, they added challenge and peril to the game, but detracted from the story, and often caused frustration when I wanted to continue with the story, explore the setting or just enjoy the David Bowie soundtrack, not repeat the action sequence hundreds of times because it was slightly too hard. Those action sequences could have been removed without detracting from the game - as Cloudpunk proves. Cloudpunk also has a more modern outlook in all aspects of its' writing - Rania often finds herself challenging NPCs about their cultural assumptions and attitudes. And I have been playing for several hours and the plot has not lead me to either a red light district or a strip club - unlike every single other noir-inspired book, movie or game.

To sum it up, Cloudpunk is a beautiful, joyful world to explore, and it's an experience first and game second. While I should be delivering parcels non-stop, it's tempting and equally rewarding just to wander around immersing myself in the scenery and taking selfies.