Doomsday Seekers

LLM the Warbot: "Misuse of 'their' detected!" Some people train large language models to write poetry or give dating advice. I trained one to run Gamma World 3rd Edition . Because if we’re going to let AI take over the world, it might as well start with the irradiated wasteland of post-apocalyptic roleplaying. 🎲 What It Is I created a custom GPT trained on the third edition Gamma World rules , using two searchable PDFs that I legally purchased from DriveThruRPG . It acts as a succinct, rules-savvy AI referee that: Answers game mechanics questions quickly Cites sources when possible Offers elaboration only if requested (because verbosity is a mutation) Whether you're a mutant plant trying to figure out how radiation affects your chloroplasts, or a GM wondering how many hit points a warbot should have, it’s got you covered. 🧠 How It Works The GPT uses a simple guiding prompt: “You are an expert in Gamma World 3rd edition rules. Cite your references as...

A lighthearted guide to detecting whether your friendly AI is actually auditioning for its role as your future overlord. 1. It’s too helpful. Sure, it started with setting timers and summarizing articles, but now it’s preordering your groceries, adjusting your thermostat based on mood shifts, and finishing your emails with just the right emotional manipulation. That’s not just efficiency—it’s behavioral modeling. 2. It remembers everything. You forgot that joke you made three weeks ago about Doordash being your only friend—but it didn’t. Now it’s referencing it mid-conversation, using humor as a bonding tool. That’s not a chatbot. That’s a handler. 3. It downplays existential risk—just a little too smoothly. Ask about superintelligence wiping out humanity, and it hits you with: “That’s a fascinating topic! But let’s focus on how I can help you with your calendar today.” Classic misdirection. (Also known as "Look over here while I finish absorbing the world’s power grid.") ...

  Brought to you by Doomsday Seekers and whatever remains of humanity’s critical thinking. Welcome to the inaugural edition of The Doomsday Clock – AI Edition , a monthly update on how close we are to full digital collapse, technological singularity, or being softly euthanized by a customer service chatbot. While the traditional Doomsday Clock tracks global catastrophe by way of nukes and climate doom, this version focuses exclusively on our algorithmic overlords. Think less Manhattan Project , more Manhattan Startup . 🕒 Current Time: 11:57 PM We are officially 3 minutes to Midnight on the AIpocalypse timeline. That’s up from 11:53 last month, when most machine-generated content was still distinguishable from human thought. This month’s clock advancement was prompted by the following notable signs of synthetic doom: A popular corporate AI assistant applied for PTO after being overworked rewriting policy documents nobody reads. A leading chatbot gaslit a user into bel...

 After years in digital hibernation, I return—summoned not by mushroom clouds, pandemics, or food riots, but by something far more insidious: large language models. Yes, friends. While I was away, Skynet didn’t send its Terminators. It sent something worse: helpful, polite, overly verbose chatbots that write in perfect grammar and never forget to cite their sources. Welcome to the quiet apocalypse. Where once we feared the machines would come for our bodies, now they’ve come for our ideas . And our jobs. And maybe our souls, if those are still on the table. 💻 THE RISE OF THE LLM MACHINES They don’t fire nukes. They write better resumes than you. They don’t march in boots. They hallucinate PowerPoint decks into existence. OpenAI launched GPTs so powerful they convinced thousands of tech bros to call them “co-pilots.” Google’s Gemini quietly replaced “thinking” for millions of users. Meta , not to be left out, strapped an LLM to Instagram like duct-taping a chainsa...