Create a machine learning algorithm to generate missions

User Story (MVP) - Use should be able to run a neural network trained on "synthetic data" (missions generated by PARANOIA Super Mission Generator) to generate human-readable missions.

Post-MVP - Neural network is to be trained on published PARANOIA missions instead of "synthetic data". Doing this will require getting permissions from Mongoose Publishing first.

Notes - The reason why this issue is "low-priority" is that we have already gotten a good enough system for generating PARANOIA missions (aside from a few minor issues like 'complications'). Put it frankly, there is very little reason to add neural networks into the equation. Templates work fine.

The reason why this issue even exists though is the realization that neural networks will wind up being the future of text generation. OpenAI recently wrote a blog post in February 14th 2019 about a neural network that can generate text, and the generated text (though hand-selected) are miles above what I would expect a neural network to generate. The public text generator that they released was also pretty decent as well. Even though there are still subtle flaws in the neural network they have right now, those subtle flaws can be fixed given enough time and resources. OpenAI have demonstrated what is possible, and what is possible will wind up being inevitable.

gwern wrote a blog post explaining how he was able to use OpenAI's public text generator (nicknamed GPT-2-small) to create 19th-century poetry generators (GPT-2-poetry and GPT-2-poetry-prefix). This same sort of process could also be used to generate PARANOIA missions.

Thus, if one wants to stay on the cutting-edge of natural language generation, I need to eventually master gwern's process. Of course, I don't need to do so immediately - our current generator works fine for now. But I do need to start preparing for the future.

Priority - Low

"The bitter lesson is based on the historical observations that 1) AI researchers have often tried to build knowledge into their agents, 2) this always helps in the short term, and is personally satisfying to the researcher, but 3) in the long run it plateaus and even inhibits further progress, and 4) breakthrough progress eventually arrives by an opposing approach based on scaling computation by search and learning. The eventual success is tinged with bitterness, and often incompletely digested, because it is success over a favored, human-centric approach."---"The Bitter Lesson", by Rich Sutton, published on March 13, 2019

Note though that "The Bitter Lesson" assumes that (a) we do have access to increased computation (which is doubtful, considering the end of Moore's Law), and (b) we're willing to spend tons of money to use that increased computation (which is also doubtful). So even if "search and learning" (i.e., neural networks) winds up being superior to knowledge-based approaches (i.e., hardcoded templates), knowledge-based approaches may be more cost-effective and worthwhile in the short-term.

I played around with GPT-4 recently (gave it a fully-generated mission and then asked it to reverse-engineer a prompt that would generate a similar type of mission), and got this one-shot prompt, which I then modified. Preliminary testing shows that this works only halfway before character limits causes the machine to either cut off text generation or produce abbreviated content. So this issue is definitely possible, but I would need to break this down into multiple prompts rather than one single prompt. The generated mission is also a bit too Zappy for my taste as well, so some more prompt refinement may be needed.

Prompt

Create a detailed mission for the roleplaying game PARANOIA. The players are part of a team of Troubleshooters operating in a dystopian future city controlled by The Computer. Incorporate the following elements:

Background: Introduce the primary antagonists and their goals, a specific location or sector where the mission will take place, and the overarching conflict that the Troubleshooters must navigate.

Mission Alert: Detail how the mission is communicated to the team, including any quirks or issues that make the information challenging to understand.

Mission Briefing: Describe the process of receiving the mission, including any oddities or peculiarities in the presentation.

Mission: Outline the main objective of the mission, including specific tasks.

Outfitting: Explain how the team is equipped, detailing any challenges, peculiarities, or absurdities in the process.

R&D Equipment: Include specialized equipment or projects that the team may encounter or utilize, with a note on their peculiarities.

Complications: List potential challenges and obstacles that may arise during the mission.

Mission Debriefing: Describe the debriefing process, including the environment and any unique elements.

Secret Society Missions: Outline optional or hidden objectives, including normal missions, spy missions, and alternative missions.

Floaters: Include additional details such as Locations, Bureaucracies, Excuses, Equipment Denial, Clerks, Clues, Evidence, and Rumors that add depth and complexity to the world and mission.

Note: Emphasize humor, absurdity, and paradox in the mission design, reflecting a society that is overly controlled, bureaucratic, and filled with secret intrigues.

GPT-4

Certainly! Here's a detailed mission for the roleplaying game PARANOIA, incorporating all the requested elements and highlighting the themes of humor, absurdity, and paradox in a dystopian future controlled by The Computer: Background

Antagonists: The primary antagonists are a group of rogue programmers known as "ByteRebels." Their goal is to implement a seemingly innocent software update that will subtly alter The Computer's directives, creating chaos in the city. Location: Sector ZYX-42, a notorious region filled with outdated tech and malfunctioning bots. Conflict: The Troubleshooters must navigate a web of bureaucracy, malfunctioning equipment, and double-dealing to stop the ByteRebels and their menacing software update. Mission Alert

The mission alert is transmitted through a series of blinking lights, Morse code, interpretative dance by malfunctioning bots, and finally, a scratchy audio transmission from The Computer. Much of the information is garbled or contradictory. Mission Briefing

The briefing takes place in a room filled with flickering lights, odd smells, and erratic machinery. A monotone-voiced AI attempts to explain the mission but is frequently interrupted by random advertisements for irrelevant products and announcements about the mandatory happiness quota. Mission

Objective: The team must locate the ByteRebels' hideout in Sector ZYX-42, retrieve or neutralize the rogue software, and ensure that all forms and permits are correctly filled out in triplicate. Tasks:

Navigate the bureaucratic maze of Sector ZYX-42. Investigate clues leading to the ByteRebels' hideout. Retrieve or neutralize the rogue software. Fill out all required paperwork.

Outfitting

The team is provided with mismatched, outdated, or hilariously overpowered equipment, much of which has dubious functionality. A seemingly endless array of forms must be filled out to receive even the most basic items. R&D Equipment

The team may encounter a new experimental device called the "TechTangler 3000," a machine designed to unravel any technological mysteries. Unfortunately, it tends to unravel itself more often than not. Complications

Constant surveillance by paranoid bots. Contradictory directives from The Computer. Malfunctioning equipment at every turn. A maze of confusing and often unnecessary bureaucracy.

Mission Debriefing

Held in a room decorated with inspirational posters like "Trust No One, Especially Yourself," the debriefing process involves endless questioning by a suspicious AI, constant interruptions by various clerks, and a final assessment that often contradicts the observed facts. Secret Society Missions

Normal Missions: Side tasks involving espionage on fellow Troubleshooters. Spy Missions: Gather information on rival secret societies. Alternative Missions: Sabotage other teams' efforts for the good of your secret society.

Floaters

Locations: Numerous malfunctioning service centers, eerily cheerful Re-Education Centers, and absurdly complicated transport hubs. Bureaucracies: A web of departments like the Department of Redundant Redundancy. Excuses: An official list of 101 approved excuses for failure. Equipment Denial: Clerks who specialize in denying requests for equipment. Clues: Encrypted messages, double-agents, and hidden tapes. Evidence: Often planted, lost, or contradicted by other evidence. Rumors: Widespread misinformation about everything from The Computer's plans to the supposed benefits of eating mold.

This mission emphasizes the chaotic, absurd nature of life in the dystopian future of PARANOIA, filled with bureaucratic hurdles, malfunctioning technology, secret societies, and the ever-watchful, ever-contradictory eye of The Computer. Enjoy the paranoia!

tra38 / Paranoia_Super_Mission_Generator

Create a machine learning algorithm to generate missions #13