1. Hemingway's iceberg theory requires what condition from the author to function as a technique (not simply as omission)?
Correct. The technique requires authorial knowledge of the full iceberg. Omitting something you don't know is simply an absence; deliberately omitting something you know fully creates subtext that gives the visible surface its weight.
Not quite. Hemingway's requirement is authorial knowledge — the writer must know the full submerged content for the visible tip to carry that weight. Simple ignorance or oversight is not iceberg theory.
2. Brandon Sanderson identified what as the fundamental problem with using AI tools for his Cosmere universe?
Correct. Sanderson's specific concern was that models would violate established rules of his magic systems even when given the books as context — the world-state memory problem.
Sanderson identified world-state memory as the core problem: AI models would contradict established magic system facts within a single session, even when given his books as context.
3. In Dwarf Fortress , which of the following produces the compelling emergent stories players share?
Correct. Dwarf Fortress simulates history through rules. Players find and retell the emergent sequences as stories — the developers authored the simulation, not the narratives.
Dwarf Fortress generates history through simulation rules. Players discover and retell the resulting sequences as compelling narratives — emergence, not hand-authoring or AI generation.
4. Why is human sensitivity reading irreplaceable by AI for cultural review of drafts?
Correct. AI can flag surface stereotypes but cannot replicate embodied cultural knowledge — the history, tone, and community-specific textures of what registers as offensive or reductive.
The limitation is experiential: AI can catch obvious stereotypes but cannot simulate the lived experience that makes human sensitivity readers able to recognize subtler cultural failures.
5. Ross Goodwin's 1 the Road (2018) was generated by:
Correct. Sensors (camera, GPS, clock, microphone) fed data to an RNN that typed continuously on a receipt printer mounted in the car traveling New York to New Orleans.
1 the Road used real-time sensor inputs — camera, GPS, clock, microphone — feeding an RNN that printed the novel in real time during the road trip.
6. In the Disco Elysium example, what does the lesson use Revachol's waterfront to illustrate?
Correct.
The lesson uses Revachol to show how geography cascades into social, economic, and political narrative logic.
7. "Regression to Mean" as an AI narrative tendency describes:
Correct. Without constraint, AI generates the statistically average continuation from its training — producing generic, competent-but-undistinctive narrative.
Regression to Mean means AI gravitates toward the most probable (average) continuation from its training data, producing generic output without deliberate prompting toward distinctiveness.
8. The Zarya of the Dawn U.S. Copyright Office decision established that:
Correct. The decision split copyright along the expressive-choice line: Kashtanova retained copyright on the text (her human choices) but not on the Midjourney images (accepted without human expressive modification).
The ruling split copyright along the expressive-choice line: human-authored text and arrangement = copyrightable; AI-generated images accepted without human modification = not copyrightable.
9. The "Named Persistence" principle in procedural narrative design refers to:
Correct. Names and remembered histories transform procedurally generated units into entities players invest in — the minimal unit of narrative attachment.
Named Persistence means giving procedural entities names and histories — transforming random units into characters players care about, which is the minimal condition for narrative investment.
10. What does the U.S. Plain Writing Act (2010) most directly demonstrate about audience-centered writing?
Correct. The act was driven by documented evidence that inaccessible government prose was generating unnecessary follow-up calls and citizen confusion at scale — a quantifiable cost of audience-calibration failure.
The Plain Writing Act's significance is that it proved audience mismatch has measurable costs — reduced follow-up calls, less confusion — making clear that writer-centered prose imposes real burdens on readers.
11. The "diamond" or nested branch structure achieves what balance?
Correct. The nested/diamond structure opens divergent paths then converges back — local divergence, shared destination. It's the compromise structure that gives readers meaningful choices without the exponential writing cost of fully parallel branching.
Not quite. The diamond/nested structure is a compromise: divergence locally (real choices, different paths) but convergence at a shared node (managing writing overhead). It contrasts with linear branches (always converge quickly) and parallel branches (never converge).
12. Jennifer Lepp's documented 2023 AI co-writing practice involved:
Correct. Lepp used a deliberate partition: AI for structural elements (outlines, dialogue scaffolding), solo work for scenes requiring genuine emotional subtext. Her output tripled while reviews remained stable.
Lepp's documented approach was a deliberate partition: AI for plot outlines and dialogue scaffolding, solo writing for emotional subtext. This allowed tripled output without quality decline.
13. The "Tool Equivalence" position on AI disclosure argues that:
Correct. The Tool Equivalence position holds that AI assistance is analogous to spell-check or Scrivener — writing infrastructure that doesn't require disclosure any more than those tools do.
Tool Equivalence holds that AI is infrastructure like spell-check — writers don't disclose using Scrivener or autocorrect, and AI assistance needn't be disclosed either.
14. What is a Consistency Audit in the context of AI-assisted world-building?
Correct.
A Consistency Audit uses AI to find internal contradictions in an established world description.
15. What does a character bible establish before writing begins?
Correct. A character bible captures the five foundational elements: backstory, core wound, dominant desire, fear, and behavioral tells.
Not quite. A character bible establishes backstory, core wound, dominant desire, fear, and behavioral tells — the structural foundation, not dialogue or plot.
16. What unique advantage does AI have over humans when performing developmental editing on a long document?
Correct. AI can compare paragraph 12 against paragraph 2 without fatigue or the anchoring bias humans develop after multiple re-readings.
AI's structural advantage is holding the whole document without fatigue or anchoring bias — not factual knowledge or emotional judgment.
17. The Sudowrite AI writing tool's "character voice" feature was built around asking users for:
Correct. Sudowrite's feature asked for sample dialogue, confirming the lesson's principle that actual lines — not personality descriptions — are what anchors an AI to a specific voice.
Sudowrite's feature required sample dialogue before generating in-voice text — operationalizing the lesson's principle that sentence-level examples outperform personality descriptions.
18. AI Dungeon launched in 2019 using which language model?
Correct. AI Dungeon launched using GPT-2, later upgrading to GPT-3 which significantly improved narrative coherence.
AI Dungeon launched with GPT-2 in 2019, later upgrading to GPT-3 which improved coherence substantially.
19. The "lost in the middle" problem (Liu et al., 2023) describes:
Correct. Liu et al.'s research showed that even large-context-window models degrade at recalling facts buried in the middle of context. For interactive narrative, this means critical state information should be injected at the top (or bottom) of prompts, never buried mid-context.
Not quite. "Lost in the middle" is a finding from AI research — models reliably recall information at the beginning and end of their context window but show degraded recall for information in the middle. This is a technical constraint that affects how you should structure state injection prompts.
20. What is the correct first step of the voice-lock technique?
Correct. The first step is to provide voice samples and let AI generate its own observations — you then review and correct that inventory before any editing begins.
Voice-lock starts with providing voice samples so AI can identify features — not editing first, not asking for a bio-based description, and not listing features yourself without AI confirmation.