Penny Nichols, Troubleshooter

What’s the point of being alive? I’m not being flippant, genuinely, it’s hard to squint through a coffeesip at Penny Nichols, Troubleshooter, and not in your grimace wonder. Because, you see, the game opens with an insult: “# ERPS Dial-Driven Narrative Engine (Player-Facing Version)”. Not only the hubris to call 700 words of low effort garble a narrative engine, not only the sneer at calling the only text that exists in the context of play the player facing version, but most vexingly the realization that we’re not even meant to read what little has been offered to us, since one of the sections of this player facing version is a list of twists to shock us towards conclusions.

That the prompt immediately spoils the game it hopes ChatGPT will magically make is one of the many ways in which Penny Nichols is damned by GIGO. The rest of the prompt consists of nonsensical infinitesimalhearted gestures at RPG mechanics which are more likely to trip up the LLM than produce even the faintest verisimilitude of simulation. Even then, the few details meant to supply our adventure are ridiculous on their face: the color associated with the cost for “sneaky” magic is cyan, the color of a clear sky. I’d be willing to be gaslit into perceiving this irony as a constitutive opposition were any coherent commentary to emerge from the mechanics, not even within the magic colors themselves, I just mean like in general, at all, if there was even the slightest sense of a reflective consciousness.

Similarly confused is the setting, which the prompt insists is “retro-futurist, occult-nuclear” despite initiating play as an insurance agent, muddling us through a magic system with divination and conjuration, culminating the story in smaughoard dragons, and whose narrative style is described as “Scooby-Doo”. None of these vagueries will do anything to ground the hallucinatory expanse of a player cajoling the LLM to generate more interesting elsewheres.

Penny Nichols, as a narrative experience that an LLM could enable, breaks upon contact. Copypasting this prompt into Claude will generate a worse experience than simply typing “Let’s roleplay. I am an insurance agent investigating a claim on Mars.” Everything Penny Nichols adds, the clunkiest skeleton of mechanics, a series of twists it telegraphs, and an inconsistent setting, detracts from the basic back and forth you could have with Claude, whose training set has already stolen everything Penny Nichols hopes to take credit for, including Penny Nichols, a punning name already made in Phoenix Wright.

We’re worried about low effort AI slop avalanching over everything we adore, but actually here is a worse abyss screaming beneath us, the annihilation of the spiritual. Mockery of creative communication has been mechanized. This game was not really written nor really meant to be read nor really capable of being played. IFComp has been, for over three decades, a celebration of a computerized interface between writer and reader animating newly possible interpersonal interplay, but now some bugeyed demon ridicules this tiny community festival by weaponizing hundreds of billions of dollars of hyperscaling dishumanification to erase both sides of the interface. Other entrants have poured their hearts into years of hope in anguish, and someone thought so little of that filigree desire to exist they lampooned it here to disrupt the beautiful electricity as we congregate to care about how we care.

At least in troll entries there’s some interpersonal experience whose bathos puddlesplashes as you nod blankly at Uninteractive Fiction 2, and even in low effort AI slop at least there’s a desire for something to have been made that’s been outsourced though precisely is it the resin of human contact which makes the thing alive, but in this nullity is there nothing, nothing comes from nothing and keeps on coming til the nothingness reigns. Why be anyone? It’s an extremely humiliating process, and, in the end, whatever you you make will be dissimulated into the machine.

Penny Nichols, Troubleshooter

This game consists of instructions to an AI on how to run a game for a human player.

I was excited to see this, because I've often thought when playing an AI-generated game: "I bet the prompt the author used would be so much more interesting than the output I have to read." And here I had the prompt itself!

So I tried playing it twice. In the first, I made myself both player and DM. Instead of AI, I used it as a writing prompt as I explored what might happen with these characters and this setting. I had a lot of fun; I usually struggle to write more than 300 words at a time and 1000 in a day, but I got up to 2270 words in less than an hour. I relied heavily on cliches and tropes but I liked the setting and concept.

I then plugged it into Copilot. Copilot made it look fancier and was much, much faster. Parts of it were interesting and fun to read. It was much more fast paced than my own transcript, and I had been trying to go fast myself. Amusingly, we used a lot of the same cliches and tropes. Where I was most disappointed is that, where I had tried hard to spool out the mysteries and fill in the backstories and characters, the AI just gave away half of the secrets in the first few paragraphs and mostly ignored my companion characters and almost all of the backstory. I felt like it wasn't really making use of the extensive mechanics sheet and was more just giving a series of climactic scenes without real buildup or denouement. It makes me feel like I couldn't personally rely on an LLM to follow my instructions if I were to make such a game myself.

Interesting concept, very glad I just got the prompt instead of having to suffer through pre-generated pages and pages of boring prose and instead got to write my own pages of boring prose.

Every once in a while the question of “what is IF?” comes up, and I have a couple of stock answers: one is that “IF” is a community-based discourse rather than a genre, and another is that “IF” is whatever we IF people are playing and talking about (these are equivalent formulations, just with more or less pretension according to taste). The other one I tend to trot out draws more from how academic disciplines are functionally defined, and holds that anything one can usefully analyze via the approaches IF critics have developed counts as IF.

These are broad definitions by intention, but by that last one, it’s very hard to consider that Penny Nichols, Troubleshooter is IF. See, this isn’t a complete game; rather, it’s a prompt you can paste into an LLM in order for it to create a game-like experience for you. As such, it’s pointless to talk about the stuff I usually do when writing a review: there’s no pre-baked prose whose quality I can assess, no ending I can weigh for thematic resonance, no puzzles that might be more or less fair. It’s all just down to whatever the plagiarism-bot feels like spitting up in the moment – so given that, as well as what I think is a well-founded reluctance to use an LLM unnecessarily, I didn’t actually bother to “play” this game.

There are other approaches to game criticism than the ones prevalent in our little community, though, and given the format Penny Nichols uses, I couldn’t help considering how it would look through the lenses tabletop RPG reviewers use when looking at scenarios. Those folks tend to look at questions like “how well are the scenario’s theme and flavor communicated to the GM so they can run it as intended?”, “are there raw materials here to allow the GM to construct a well-paced adventure”, “are the mechanics well thought-out?”, and “how railroaded is this adventure likely to be in practice?” And these are questions one can ask of the Penny Nichols prompt.

Unfortunately I don’t think it comes out very well on any of them. The prompt is quite short and devoid of any consistent vibe; there’s an underbaked science-fantasy theme that provides some proper nouns but no coherent guidance to a human intelligence as to how to play it. Like, here’s what we/the LLM are told of Penny:

The player character is Agent Penny Nichols, an Insurance Investigator from the Solar Insurance Company on Mercury.

Hue 150 (Divination & Illusion specialist).
Prefers indirect investigation, including cover identities.
Member of the Circle Trigonist faction.
Does that “hue” thing indicate Penny can do magic? What’s a “Trigonist”? Is locating an insurance company on a planet that’s consistently so hot it radiates mostly as a black body an indication that there’s some fraud going on, or are people just dumb? Your guess is as good as mine (and much better than ChatGPT’s); this is slightly better than “make up some bullshit,” but not by much.

As for the “plot” of the scenario itself, there’s more concrete reason to think that tabletop RPG design is the best way to think about this since it explicitly says the story should proceed according to the four-act kishokentetsu structure that was all the rage in RPG circles like five years ago. But the implementation of the structure is incredibly sketchy, not even running to 200 words: basically, there’s a space station studying an artifact, but the artifact has vanished, so you’re sent in to investigate. There’s meant to be a mid-story twist where you can find out that the artifact was a hoax by the lead investigator, because he wanted to get more funding; but then the final twist reveals that the artifact (or the station itself, the prompt isn’t clear) is actually a dragon’s hoard (or maybe the dragon itself?) that created the lead investigator as a psychic projection, in order to get the attention on which dragons (and hoards?) subsist. The resolution requires the player to “contain, banish, or escape before [the dragon] consumes more” (there’s no mention anywhere of the dragon having previously consumed anything).

Look, I’ve run a bunch of tabletop RPG adventures, and not to put too fine a point on it, but this one sucks. Hell, the notes I scribble to myself for scenarios I’ve come up with and already live in my brain contain way more detail about the psychology of the characters, how to construct challenges that are engaging to deal with, ideas about how to manage pacing, and particular bits of dialogue or turns of phrase to incorporate in my narration. Speaking as a reasonably experienced GM, I’d find this prompt worse than useless: it doesn’t give me any of the stuff I’d look to a scenario to provide, and in the time it’d take me to read, understand, and attempt to spackle over the holes of this prompt, I could come up with something far better using only my own creativity.

So that’s my assessment of what the author submitted to the Comp as a “game”, but I was morbidly curious about what could be included in the “walkthrough” file, since of course there’s nothing to walk through. Turns out it’s some commands that (might?) work to complete the scenario under Claude.ai, as well as a sample transcript of the author “playing” the game with ChatGPT. And oh lord, as bad a mood as reading the prompt put me in the transcript was worse.

For one thing, ChatGPT seems to insist on presenting everything as bullet-pointed lists of information and options, with embedded emojis, meaning reading it feels like being trapped in an Axios article (What they’re saying: “this is literally hell,” according to Mike Russo), and also makes me wonder how the author reconciled the “you can type anything and the game will understand it!” promise of LLMs with the reality that it was providing an interface indistinguishable from that of an especially low-effort choice-based game. For another, while the blurb promises that Penny Nichols is a “Star-trek style away mission”, ChatGPT sure seemed to think it’s a high fantasy setting where all your actions involve casting magic spells. And actually the prompt in the transcript isn’t the same as the prompt in the Comp submission!

The transcript at least explains the last of these discrepancies; halfway down, the author realizes that things aren’t going well, and asks ChatGPT to change the rules, then regurgitate a new prompt capturing the alterations. It’s of glancing interest that even after the changes, the transcript remains awful: despite being told to stop prompting with an explicit list of options, ChatGPT keeps doing that; the stilted, buzzword-laden prose make it feel like you’re playing DnD with the worst, most corporate manager you’ve ever had; and there’s nothing resembling an actual conflict or revelation, just flaccid set-pieces and irrelevant revelations following each other in succession until the author declares that he’s won. To be fair, I guess I should note that I didn’t notice any glaring inconsistencies or logical contradictions in what the LLM spat out, which either indicates our forthcoming robot overlords are getting better with the hallucination problem or just that the “writing” was so soporific and arbitrary that there was no central narrative for individual developments to contradict.

But like I said, all those criticisms are only of glancing interest. I repeat: this prompt, which was submitted to the Comp as a thing you could use to get an LLM to play a game with you, is itself the product of an LLM – Penny Nichols, Troubleshooter is a coprophagous ouroboros, creating the very slop it feeds on, of no possible use or value to a human being. In that sense I suppose there’s something potentially meta to the prompt’s “final twist”: “Dragons feed on human attention, and this hoard has been feasting.”

They do, and it is.

Are we inclined to do something about that?

This is not IF.