AI-driven narrative experiences. Building systems where game writers and AI collaborate to create compelling, emergent storytelling.
Current Focus: MM-KMD — An AI-powered murder mystery game engine exploring the narrative noose.
Why Your LLM NPCs Sound the Same (And How to Fix It)
“Let me tell you, my good friend…” If you’ve built LLM-powered NPCs, you’ve heard this. Your character starts strong, maybe even impressive. But by turn 20, something’s wrong. They’re repeating themselves. The same phrases. The same gestures. The same rhythm. I ran 150 turns of dialogue with an LLM-powered character last week. Here’s what I found: Pattern Frequency “takes a long swig from his glass” 59% of responses “my good friend/man/fellow” 30% of responses “eyes unfocused” 15% of responses “let me tell you” 13% of responses My character, Francis—a boozy ex-politician—couldn’t stop drinking. Not because it was dramatically appropriate. Because the LLM fell into a rut. ...
Blog Post Ideas from MM-KMD & Quantum Context Development Ready to Write (Research Complete) 1. “The Narrative Noose: How Constraint Creates Emergence in AI Storytelling” Status: Ready to write Length: ~2000 words Audience: Game devs, AI researchers, narrative designers Hook: “Freedom without constraint = chaos. Here’s why the best AI stories happen when you tighten the noose.” Key Points: The 5 Constraint System (AUTONOMY, AGENCY, GRAVITY, QUANTUM, CONSCIOUSNESS) Constraint as generator (research-backed from Deep Think synthesis) Why branching narratives fail vs. narrative field physics Real data from 726 development sessions Supporting Evidence: ...