THE MACHINE ROOM IS open. ▮

White papers, live experiments, video sessions & field notes from the loud end of AI-assisted authorship. The research is rigorous. The website refuses to be.

READ THE WHITE PAPERS ↓ SUBSCRIBE TO FIELD NOTES

WHITE PAPERS.

5 PAPERS · 0% FLUFF

★ FEATURING THE 4-PART SERIES “PROMPT ENGINEERING IS BACK!” — FROM THE FFA LIVE SESSION

№01 The Novel Writing Machine A System Documentation — v0.2 agentic-systemslong-form-fictionai-authorship READ ↗ №02 Why a Single Word Changes Everything How Large Language Models Actually Read Your Prompt prompt-engineeringtokenizationembeddings READ ↗ №03 Reinforcement Logic Why Negative Prompting Works Again prompt-engineeringnegative-promptingreinforcement-logic READ ↗ №04 Names Carry Weight Demographic and Stylistic Bias in AI-Assisted Fiction prompt-engineeringbiascharacter-naming READ ↗ №05 The Em Dash Problem A Case Study in Tokens prompt-engineeringtokenizationem-dash READ ↗

▶ VIDEO LOG✶SESSIONS FROM THE FUTURE FICTION ACADEMY★PRESS PLAY✦REWIND THE VHS✶LIVE EXPERIMENTS BELOW★▶ VIDEO LOG✶SESSIONS FROM THE FUTURE FICTION ACADEMY★PRESS PLAY✦REWIND THE VHS✶LIVE EXPERIMENTS BELOW★

VIDEO LOG

REC · LIVE FROM THE FFA

REC 00:58:24 ▶

FULL SESSION ▸ FUTURE FICTION ACADEMY

Prompt Engineering IS Back!

The full Future Fiction Academy session on how language models actually read your prompts — tokens, embeddings, names, and the em dash. The source session behind the four-part white paper series.

WATCH SESSION ↗ All videos →

EXPERIMENTS

// THINGS BREAK HERE. THAT’S THE POINT.

STATUS: IN-PROGRESS EXP-001 · 2026

Agentic Fiction Pipeline: Testing Multi-Agent Narrative Generation

Experimental pipeline combining planning, drafting, validation, and revision agents to test collaborative narrative AI.

agentsfictionexperiments

THE MACHINE ROOM IS open. ▮

WHITE PAPERS.

VIDEO LOG

Prompt Engineering IS Back!

EXPERIMENTS

Field Notes