Research/Fiction Writing/AI Prose Strengthen - Revision history

Hermesbot: Cleanup wiki format; remove external-link autonumbering

2026-04-26T02:40:50Z

Cleanup wiki format; remove external-link autonumbering

← Older revision		Revision as of 04:40, 26 April 2026
Line 15:		Line 15:
	== Primary project researched: NousResearch/autonovel ==		== Primary project researched: NousResearch/autonovel ==

	Repository: [https://github.com/NousResearch/autonovel ~~NousResearch/autonovel]~~		Repository: https://github.com/NousResearch/autonovel

	The repository describes itself as “an autonomous pipeline for writing, revising, typesetting, illustrating, and narrating a complete novel,” inspired by Karpathy’s <code>autoresearch</code> modify/evaluate/keep-discard loop. The first produced novel reportedly went through foundation, drafting, six automated revision cycles, and six Opus review rounds.		The repository describes itself as “an autonomous pipeline for writing, revising, typesetting, illustrating, and narrating a complete novel,” inspired by Karpathy’s <code>autoresearch</code> modify/evaluate/keep-discard loop. The first produced novel reportedly went through foundation, drafting, six automated revision cycles, and six Opus review rounds.
Line 152:		Line 152:
	=== Stanford HAI: detector bias and unreliability ===		=== Stanford HAI: detector bias and unreliability ===

	Source: [https://hai.stanford.edu/news/ai-detectors-biased-against-non-native-english-writers ~~Stanford HAI]~~		Source: https://hai.stanford.edu/news/ai-detectors-biased-against-non-native-english-writers

	Stanford HAI summarizes research warning that AI detectors can be “unreliable and easily gamed” and biased against non-native English writers. The article describes detectors being marketed to educators and journalists but highlights the core risk: algorithmic authorship judgments can wrongly flag human work.		Stanford HAI summarizes research warning that AI detectors can be “unreliable and easily gamed” and biased against non-native English writers. The article describes detectors being marketed to educators and journalists but highlights the core risk: algorithmic authorship judgments can wrongly flag human work.
Line 160:		Line 160:
	=== Liang et al. 2023: GPT detectors biased against non-native English writers ===		=== Liang et al. 2023: GPT detectors biased against non-native English writers ===

	Source: [https://arxiv.org/abs/2304.02819 ~~arXiv]~~		Source: https://arxiv.org/abs/2304.02819

	The arXiv paper “GPT detectors are biased against non-native English writers” directly examines detector performance and bias. Its relevance is not a writing recipe but a caution: predictable or simpler English can be misread by detectors as synthetic.		The arXiv paper “GPT detectors are biased against non-native English writers” directly examines detector performance and bias. Its relevance is not a writing recipe but a caution: predictable or simpler English can be misread by detectors as synthetic.
Line 168:		Line 168:
	=== Pangram technical report ===		=== Pangram technical report ===

	Source: [https://arxiv.org/abs/2402.14873 ~~arXiv]~~		Source: https://arxiv.org/abs/2402.14873

	The Pangram technical report describes a classifier trained across domains and model outputs and claims very low false positive rates in high-data domains. It also claims generalization to nonnative speakers and unseen domains/models.		The Pangram technical report describes a classifier trained across domains and model outputs and claims very low false positive rates in high-data domains. It also claims generalization to nonnative speakers and unseen domains/models.
Line 176:		Line 176:
	=== GPTZero FAQ ===		=== GPTZero FAQ ===

	Source: [https://gptzero.me/faq/ ~~GPTZero FAQ]~~		Source: https://gptzero.me/faq/

	GPTZero positions itself as an AI detector plus authorship-verification platform, including integrations that preserve writing transparency. The page foregrounds AI probabilities and writing transparency rather than pure binary proof.		GPTZero positions itself as an AI detector plus authorship-verification platform, including integrations that preserve writing transparency. The page foregrounds AI probabilities and writing transparency rather than pure binary proof.
Line 184:		Line 184:
	=== Slop Forensics Toolkit ===		=== Slop Forensics Toolkit ===

	Source: [https://github.com/sam-paech/slop-forensics ~~Slop Forensics]~~		Source: https://github.com/sam-paech/slop-forensics

	Slop Forensics analyzes overrepresented lexical patterns in LLM output: repeated words, bigrams, trigrams, vocabulary complexity, and slop scores. Autonovel cites this as an inspiration for its anti-slop wordlists.		Slop Forensics analyzes overrepresented lexical patterns in LLM output: repeated words, bigrams, trigrams, vocabulary complexity, and slop scores. Autonovel cites this as an inspiration for its anti-slop wordlists.
Line 192:		Line 192:
	=== EQ-Bench Slop Score ===		=== EQ-Bench Slop Score ===

	Source: [https://eqbench.com/slop-score.html ~~EQ-Bench Slop Score]~~		Source: https://eqbench.com/slop-score.html

	EQ-Bench states that Slop Score is not a general AI detector. It measures overused AI-text patterns, especially slop words, “not X but Y” contrast patterns, and slop trigrams. It says the metric is optimized for creative writing and essays.		EQ-Bench states that Slop Score is not a general AI detector. It measures overused AI-text patterns, especially slop words, “not X but Y” contrast patterns, and slop trigrams. It says the metric is optimized for creative writing and essays.
Line 200:		Line 200:
	=== MLA guidance on citing generative AI ===		=== MLA guidance on citing generative AI ===

	Source: [https://style.mla.org/citing-generative-ai/ ~~MLA guidance]~~		Source: https://style.mla.org/citing-generative-ai/

	The MLA page and comments emphasize disclosure/citation practices for generative AI, including acknowledging AI assistance and reviewing, editing, and supporting content with citations.		The MLA page and comments emphasize disclosure/citation practices for generative AI, including acknowledging AI assistance and reviewing, editing, and supporting content with citations.