I’ve heard from AI advocates a lot about their eagerness to outsource their day-to-day communications to it. I’m not going to say that this always goes wrong. It’s hard to justify writing new missives because some are so routine and don’t pay off in the long run. We have all wasted time sending repetitive emails that could have been used for almost anything else. However, there is a catch: in order for AI to perform at its highest level, you must remain sharp yourself. The thought and language you use with these tools only makes them stronger. I think it will be most beneficial in the long run to complete some of your language composition completely on your own. This is not something I propose out of some metaphysical concern for the preservation of the human soul—though it could serve that purpose in some circumstances—but rather as an appeal to the practical goal of producing the best AI output possible. Just as Formula 1 drivers physically condition to better handle their finely tuned machines, practicing language skills without AI augmentation hones your ability to wield AI deftly. In this article, I offer three activities — really, two warm-ups and a high-intensity workout — that help extend what you can elicit from AI and cultivate your self-expression.
On the Write Track
To start, do some writing without AI. Our thoughts frequently rise and fall in unpredictable waves. Inconsistently, this rhythm can bring about profound realizations. The mind’s propensity for spontaneity is counterbalanced with structure by focused, linear thinking. You can tug at one of the numerous threads that are all around us by focusing on one thought and moving it forward from there. This mental exercise is recorded in writing, like taking pictures as you follow your thoughts. Your instructions to the AI are organized using the same sequential reasoning progression that underpins good writing. What I just described as “prompt engineering” is actually good, old-fashioned articulateness, despite the hype-mongers’ praise for it.
A Good Investment Is A Penny for Thoughts
Once you’ve checked that box, start talking to people about things they understand but you don’t. Learning about something by discussing it with an expert is a kind of language puzzle, because you have to figure out how to figure out what to ask. You’re pushing yourself into the unknown. You won’t know which rocks to look under if you don’t know anything about the subject. However, this is a conversation, so you can iterate. You change course if you reach a dead end. When you find one breadcrumb, you’re closer to finding a loaf. If you put the right diagnostic questions into practice, you’ll be able to find the tailored questions that reveal more obscure information more quickly. The most difficult ones are the opening questions, but once you learn how to answer them, you’ll open doors you didn’t know were there. Exploiting the System You are now ready to play an old-fashioned tabletop role-playing game (RPG) once you have mastered those. It was only a matter of time until I worked this pastime of mine into one of my articles, but I can’t imagine a more fitting pretext.
For those who are unfamiliar with the genre, a tabletop role-playing game is a game in which one player, who is typically referred to as the “game master” or some other similar title, creates and manages an imaginary game world. The other players each have a character that they use to interact with everything in that world. All players are free to try any activity they can think of, and if their characters are capable of doing it, they usually do it. When the success of an activity is not guaranteed or there are irreconcilable conflicts between players (especially, and typically, with the game master), dice and character statistics are used to resolve the interaction.
The game interface is purely verbal: the game master describes the environment, the other players articulate what they want to do, and the game master pronounces the outcome of the players’ decisions.
Role-Playing as a Skill-Building Tool
The archetypal example of a tabletop RPG is Dungeons & Dragons (D&D). However, while entries in the genre are commonly likened to board games, the comparison is inapt. Board games rely on fixed visuals like boards, cards, and pieces, whereas tabletop RPGs need little more than character sheets and conversation. Players can improvise with whatever helps everyone get a clear picture of the scene if they need it. Moreover, while board game rules exhaustively prescribe the available (and unavailable) activities in the respective game, tabletop RPG rules are merely a framework for evaluating the success of player actions. Players may do anything, even what is not explicitly sanctioned by the rules — the rules just explain how to determine the result of their actions.
So, what exactly does it mean to be “old-school” in an RPG? The main difference between modern tabletop RPGs and “old-school” RPGs, which could easily fit into a PhD thesis, is that the former emphasize character statistic optimization and rolling high, while the latter emphasize player ingenuity and creative resource use. While disarming a mechanical trap in an abandoned tomb in a modern game might just require declaring the character’s “Disarm Trap” skill (which gives a numerical bonus) and rolling a high number, disarming a mechanical trap in an old-school game would require describing your character’s strategy for defeating the mechanism. If you provide enough detail and outline a thorough procedure, success could be guaranteed without rolling dice. A synthesis of the linguistic tools developed through the aforementioned warm-up routines is what makes a great tabletop RPG player. You start by “interrogating the fiction,” being curious enough not to take the scene at face value. Then you ask for more information about what’s around your character. Experimenting with the objects in your environment could help you learn even more. Don’t base your decisions on what you think you know. It’s possible that the unassuming bowl on the table has magical properties. Then, you engineer a path to your goals based on your observations. By expressing a procedural solution, you can go further than simply stating the desired outcome, which can result in your character’s death when the stakes are moderately high. If you outline a set of steps, including interventions for possible contingencies that can arise from the present game scenario, which would succeed without a doubt, then how could you fail?
AI Prompts: Using RPG Thinking When creating large language model (LLM) prompts, you don’t need to make any changes to the traditional RPG problem-solving method. In both exercises, the surest route to success requires conceiving your goal in the minutest detail, establishing relevant roles (what do you think “role prompting” is?), listing all the steps to be taken, providing examples, and defining exigent circumstances and your prescribed reaction to them.
It should not come as a surprise that technology pioneers like Peter Norvig and Steve Wozniak played a lot of D&D because their respective bodies of work were largely completed prior to the development of generative AI. Still, their accomplishments reflect mastery of the skills that D&D demands.
The order of the above exercises is deliberate. I sequenced them in order of fewest to most required players and lowest to highest difficulty of execution. There are fewer adept conversationalists than articulate writers, and even fewer stellar RPG players than engaging conversationalists. The mental agility required to structure better AI prompts and obtain more meaningful results is developed with each step. With that in mind, especially if these are new to you, I encourage you to progress through these exercises in order. Not only can you practice each one without connecting to a billion-parameter model over the internet, but they’re also entertaining. In the age of AI, sharpening your communication skills is still the most powerful way to make the machines work for you.
