I Built a Maze Runner Simulation Where Teenage Sam Altman Survives the Glade December 25, 2025

Source: Dev.to

What happens when you drop a teenage version of Sam Altman into James Dashner’s The Maze Runner universe?
You get a surprisingly addictive, personality‑driven simulation that combines:

• Big Five (OCEAN) personality modeling
• Probabilistic decision making
• Token‑efficient LLM narrative generation
• Health + relationship tracking
• Beautiful console output + matplotlib health graphs

And yes — it is as weird and fun as it sounds.

The Concept in One Sentence

A 16‑year‑old Sam Altman wakes up in the Box.
His survival odds depend (mostly) on how curious, agreeable, and emotionally stable you decide he is.

Why This Even Exists

I wanted to:

• Play with OCEAN personality traits as actual gameplay mechanics
• Use very light LLM calls for flavor text without burning money
• Create something that feels like interactive fan‑fiction but runs in ~200 lines
• Have an excuse to think about teenage Sam Altman solving mazes (don’t ask)

Core Architecture (surprisingly clean for such a silly idea)

Everything is in one gloriously self‑contained file (MVP life):

from dataclasses import dataclass
from typing import Dict
import random

@dataclass
class Character:
    name: str
    age: int
    ocean: Dict[str, float]
    health: float = 100.0
    relationships: Dict[str, float] = None

    def make_decision(self, event_type: str) -> str:
        if event_type == "danger":
            return "explore" if random.random() < self.ocean["O"] else "hide"
        # ... etc

def generate_narrative(...):
    try:
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            max_tokens=85,
            temperature=0.7,
            # …
        )
    except Exception:
        return "Fallback: Sam did a thing. It was probably fine."

The simulation loop is brutally simple:

while sim.run_day():
    pass

At the end it prints a nice table and a health plot.

Personality Really Matters (more than you’d expect)

The high‑Openness version is dramatically more entertaining (and painful) to watch.

LLM Usage — Extremely Paranoid Edition

I wanted narrative flavor without spending $12 on one funny run.

Solution

• Max 85 tokens per generation
• Temperature 0.7 (chaotic but not insane)
• Perfect fallback text that still makes sense
• Only one call per day

Total cost for 50 full runs ≈ $0.04–$0.07 (December 2025 pricing).

Console Output Porn (because we all love pretty terminals)

Day  4  |  Sam is offered a chance to run the Maze with the Runners.
   → Decision: explore
   → Outcome:  positive

   Sam sprinted into the twisting corridors, eyes wide with that terrifying mix of terror and fascination only a true puzzle addict could feel.

   Health: 100   |   Relationships: Newt:0.68  Thomas:0.62  Chuck:0.58

Followed by a clean summary table and a matplotlib line chart of health going up and down like teenage mood swings.

How to Run It Right Now

git clone https://github.com/ilyarah/Maze_Runner_Sam_Altman_Sim_MVP.git
cd Maze_Runner_Sam_Altman_Sim_MVP

pip install openai matplotlib

export OPENAI_API_KEY="sk-..."

python simulation/main.py

Takes ~20–40 seconds per run (mostly waiting for OpenAI).

Future Evil Plans (if I don’t get bored)

• Branching events based on current health/relationships
• Multiple endings (escape / become Keeper / get eaten by Griever)
• GUI with pygame (because why not)
• Sensitivity analysis: how much Openness is too much?
• Replace Sam with other public figures (you know you want)

Final Thoughts

This was one of those projects that started as a dumb joke and somehow became genuinely interesting to watch unfold.

The combination of fixed personality traits + randomness + tiny LLM injections creates emergent stories that feel surprisingly alive for <300 lines of code.

Sometimes the silliest ideas teach you the most about agency, personality modeling, and how little prompting an LLM actually needs to be entertaining.

Give it a spin. Change the OCEAN values. Laugh at teenage Sam getting mauled by a Griever because he was “too curious”.

If you make an even worse version with Elon or Vitalik — please tag me.

Merry Christmas 2025, and may your maze always have an exit. 🌀

What weird simulation should I build next? 👇