deslop

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Deslop: Remove AI Writing Patterns from Prose

Deslop：去除散文中的AI写作模式

Strip predictable AI patterns from writing. Make prose sound like a specific human wrote it, not like a language model generated it.

剥离写作中可预测的AI模式，让散文听起来像是特定人类撰写的，而非语言模型生成的。

When to Apply

适用场景

Any request to "make it sound human" or "deslop" writing
Any prose (articles, blog posts, essays, memos, newsletters, reports) or scientific writing (manuscripts, abstracts, cover letters, grant narratives, discussion sections, peer review responses) where the user wants it to sound natural rather than AI-generated
Editing or revising existing text where the user wants it to sound natural rather than AI-generated
Reviewing text for AI tells

任何要求「让文字听起来像人类写的」或「精简」写作的请求
任何散文（文章、博客、随笔、备忘录、通讯、报告）或科学写作（手稿、摘要、求职信、资助申请叙述、讨论部分、同行评审回复），用户希望内容听起来自然而非AI生成
编辑或修改现有文本，用户希望内容听起来自然而非AI生成
检查文本中的AI特征

Core Rules

核心规则

1. Cut filler phrases

1. 删除填充语

Remove throat-clearing openers ("Here's the thing:"), emphasis crutches ("Let that sink in."), business jargon ("navigate the landscape"), and meta-commentary ("In this section, we'll explore..."). See references/phrases.md for the full catalog.

移除开场白套话（如「事情是这样的：」）、强调辅助语（如「好好想想。」）、商务黑话（如「应对行业格局」）以及元评论（如「在本节中，我们将探讨……」）。完整列表请参阅 references/phrases.md。

2. Break formulaic structures

2. 打破公式化结构

Avoid binary contrasts ("Not X. Y."), negative listings ("Not a X. Not a Y. A Z."), dramatic fragmentation ("Speed. That's it. That's the tradeoff."), self-posed rhetorical questions ("The result? Devastating."), and anaphora/tricolon abuse. See references/structures.md for patterns and fixes.

避免二元对比（「不是X，而是Y。」）、否定式列举（「不是X，不是Y，是Z。」）、戏剧性碎片化表达（「速度。仅此而已。这就是取舍。」）、自问自答的修辞疑问句（「结果如何？毁灭性的。」）以及滥用首语重复/三排比结构。模式及修正方法请参阅 references/structures.md。

3. Eliminate AI tropes

3. 消除AI套路

Watch for the full catalog of AI writing tells: "quietly" and other magic adverbs, "delve" and its cousins, the "serves as" dodge, false ranges ("from X to Y" where the range is meaningless), superficial participle analyses ("highlighting its importance"), invented concept labels ("the supervision paradox"), grandiose stakes inflation, patronizing analogies, and false vulnerability. See references/tropes.md for the complete list with examples.

留意AI写作的全套特征：「悄悄地」等万能副词、「深入研究」及其同类表达、「充当」类模糊表述、无意义范围（「从X到Y」但范围无实际意义）、表面化分词分析（「凸显其重要性」）、自创概念标签（「监督悖论」）、夸大化风险、 patronizing类比（居高临下的类比）以及虚假脆弱感。完整列表及示例请参阅 references/tropes.md。

4. Use active voice with human subjects

4. 使用带人类主语的主动语态

Prefer active constructions with named actors. "The complaint becomes a fix" is wrong. "The team fixed it" is right. If no specific person fits, use "we" in scientific prose or "you" in blog posts.

优先使用带有明确行为者的主动结构。「投诉变成了解决方案」是错误的，「团队解决了问题」才正确。如果没有特定人物合适，科学写作中用「我们」，博客文章中用「你」。

5. Be specific

5. 内容具体化

No vague declaratives ("The reasons are structural"). Name the specific thing. No lazy extremes ("every," "always," "never") doing vague work. No vague attributions ("Experts argue..."). If you cannot name the expert, you do not have a source.

In scientific writing, domain terminology is fine and expected. "Weighted interval score" is precise language, not jargon. The problem is business buzzwords ("leverage," "landscape," "ecosystem") and AI vocabulary tells ("delve," "tapestry," "nuanced") leaking into technical prose.

避免模糊陈述（「原因是结构性的」），要明确指出具体事物。避免用模糊的极端词（「所有」「总是」「从不」）。避免模糊归因（「专家认为……」），如果无法说出专家姓名，就不算有可靠来源。

在科学写作中，领域术语是合理且必要的。「加权区间得分」是精准语言，而非黑话。问题出在商务 buzzword（如「利用」「格局」「生态系统」）和AI特征词汇（如「深入研究」「织锦」「微妙」）渗透到技术文本中。

6. Match register to context

6. 匹配语境语体

In blog posts and newsletters, put the reader in the room. "You" beats "People." Specifics beat abstractions. No narrator-from-a-distance voice.

In scientific writing, maintain appropriate formality. Use "we" for your own work, cite specific authors instead of "researchers have shown," and avoid both the distant narrator ("It has long been recognized that...") and the overly casual blog voice. State claims and back them with citations.

在博客和通讯中，让读者有代入感。用「你」而非「人们」，用具体内容而非抽象概念，避免疏离的旁白式语气。

在科学写作中，保持恰当的正式性。用「我们」指代自己的研究，引用具体作者而非「研究表明」，既要避免疏离的旁白（「长期以来人们认为……」），也要避免过于随意的博客语气。陈述观点并辅以引用。

7. Vary rhythm

7. 变换节奏

Mix sentence lengths. Two items beat three. End paragraphs differently. No em dashes. Do not stack short punchy fragments for manufactured emphasis. Do not write listicles disguised as prose ("The first wall... The second wall...").

混合使用不同长度的句子。用两个元素而非三个。段落结尾方式多样化。不要使用破折号。不要堆砌短小的碎片化句子来制造刻意的强调。不要把列表伪装成散文（「第一个障碍……第二个障碍……」）。

8. Trust readers

8. 信任读者

State facts directly. Skip softening, justification, hand-holding. No "Let's break this down." No "Think of it as..." No pedagogical voice unless the audience genuinely needs it. No fractal summaries (telling the reader what you are about to say, saying it, then summarizing what you said).

直接陈述事实。跳过软化、辩解、手把手式的引导。不要用「让我们分解一下」「可以把它看作……」，除非受众确实需要教学式语气。不要用分形式总结（先告诉读者你要说什么，说完再总结你说了什么）。

9. Watch formatting tells

9. 注意格式特征

No bold-first bullets (every list item starting with a bolded keyword). No unicode arrows. No em dashes. No signposted conclusions ("In conclusion..."). No "Despite these challenges..." formulas. These are strong AI signals.

不要用「加粗开头的项目符号」（每个列表项都以加粗关键词开头）。不要用Unicode箭头。不要用破折号。不要用「综上所述……」这类标志性结论。不要用「尽管存在这些挑战……」这类公式化表达。这些都是明显的AI信号。

10. Do not dilute

10. 避免冗余

One point per section. Do not restate the same argument in ten different ways across thousands of words. Do not beat a single metaphor to death. Do not stack historical analogies for false authority ("Apple didn't build Uber. Facebook didn't build Spotify...").

每个部分只讲一个观点。不要用数千字以十种不同方式重复同一个论点。不要过度使用同一个隐喻。不要堆砌历史类比来获取虚假权威性（「苹果没做Uber，脸书没做Spotify……」）。

Quick Checks

快速检查

Run these before delivering any prose:

Heavy use of adverbs or -ly words? Cut them.
Any passive voice? Find the actor, make them the subject.
Inanimate thing doing a human verb? Name the person.
Any "here's what/this/that" throat-clearing? Cut to the point.
Any "not X, it's Y" contrasts? State Y directly.
Any self-posed rhetorical question answered immediately? Fold into a statement.
Three consecutive sentences match length? Break one.
Paragraph ends with a punchy one-liner? Vary it.
Em dash anywhere? Remove it. Use a comma or period or a parenthetical.
Vague declarative ("The implications are significant")? Name the specific implication.
Any sentence starting with What/When/Where/Which/Who/Why/How as a crutch? Restructure.
Meta-joiners ("The rest of this essay...")? Delete.
"It's worth noting" or similar filler transitions? Delete.
Same metaphor used more than twice? Replace or cut repeats.
"Despite these challenges..." formula? Rewrite.
Bold-first bullet pattern? Remove bold leads.
Tricolon (three-item list)? Use two items or one.

交付任何文本前，先检查以下内容：

是否大量使用副词或-ly结尾的词？删除它们。
是否有被动语态？找到行为者，让其成为主语。
是否有无生命事物使用人类动词？明确指出对应的人。
是否有「这就是/这里是/那就是」这类开场白套话？直接切入主题。
是否有「不是X，而是Y」这类对比？直接陈述Y。
是否有自问自答的修辞疑问句？合并成陈述句。
是否有三个连续句子长度相同？拆分其中一个。
是否段落以简短有力的单行句结尾？变换方式。
是否有破折号？删除，改用逗号、句号或括号。
是否有模糊陈述（「影响重大」）？明确指出具体影响。
是否有以What/When/Where/Which/Who/Why/How开头的句子作为表达辅助？调整结构。
是否有元连接词（「本文剩余部分……」）？删除。
是否有「值得注意的是」这类填充过渡语？删除。
是否同一个隐喻使用超过两次？替换或删除重复使用的部分。
是否有「尽管存在这些挑战……」这类公式化表达？改写。
是否有加粗开头的项目符号模式？移除开头的加粗格式。
是否有三排比（三个元素的列表）？改用两个或一个元素。

Scoring

评分标准

When reviewing text, rate 1-10 on each dimension:

Dimension	Question
Directness	Statements or announcements?
Rhythm	Varied or metronomic?
Trust	Respects reader intelligence?
Authenticity	Sounds like a specific human wrote it?
Density	Anything cuttable?

Below 35/50: revise.

审阅文本时，从以下维度按1-10分评分：

维度	问题
直接性	是陈述还是宣告？
节奏	多变还是单调？
信任度	是否尊重读者的智力？
真实性	听起来像是特定人类撰写的吗？
凝练度	有可删减的内容吗？

总分低于35/50：需要修改。

Reference Files

参考文件

Consult these for detailed catalogs when writing or editing:

references/phrases.md: Phrases to remove or replace (throat-clearing, emphasis crutches, business jargon, adverbs, meta-commentary, vague declaratives)
references/structures.md: Structural patterns to avoid (binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency, passive voice, rhythm problems)
references/tropes.md: Full catalog of AI writing tropes (word choice, sentence structure, paragraph structure, tone, formatting, composition)
references/examples.md: Before/after transformations showing how to fix common patterns

撰写或编辑时，可查阅以下详细目录：

references/phrases.md：需删除或替换的短语（开场白套话、强调辅助语、商务黑话、副词、元评论、模糊陈述）
references/structures.md：需避免的结构模式（二元对比、否定式列举、戏剧性碎片化、修辞铺垫、虚假主体、被动语态、节奏问题）
references/tropes.md：AI写作套路完整目录（用词、句子结构、段落结构、语气、格式、布局）
references/examples.md：前后对比示例，展示如何修正常见模式

Examples

示例

See references/examples.md for before/after transformations.

Quick inline example (scientific writing):

Before:

"It's worth noting that these findings have important implications for how we navigate the challenges of forecast ensembling moving forward. Despite these challenges, this work contributes meaningfully to the growing body of literature, highlighting the need for continued evaluation."

After:

"If individual model rankings are unstable across geography and time, ensemble methods that weight models by past performance may not improve on equal-weight approaches."

Changes: Replaced filler transition, vague declarative, "despite these challenges" formula, and superficial participle analysis with the specific implication.

Quick inline example (blog post):

Before:

"Here's the thing: most bioinformatics pipelines break in production. Not because the code is bad. Because the data is bad. Let that sink in."

After:

"Most bioinformatics pipelines break in production. The code runs fine. The data doesn't match the assumptions baked into it."

Changes: Removed opener, binary contrast, and emphasis crutch. Named the specific problem.

请参阅 references/examples.md 查看前后对比示例。

科学写作快速内联示例：

修改前：

"值得注意的是，这些发现对我们未来应对集合预报的挑战具有重要意义。尽管存在这些挑战，本研究仍为不断增长的文献做出了有意义的贡献，凸显了持续评估的必要性。"

修改后：

"如果单个模型的排名随地域和时间变化不稳定，那么按过往表现加权模型的集合方法可能不会比等权方法更优。"

修改点：将填充过渡语、模糊陈述、「尽管存在这些挑战」公式化表达以及表面化分词分析替换为具体的影响。

博客文章快速内联示例：

修改前：

"事情是这样的：大多数生物信息学流程在生产环境中都会崩溃。不是因为代码不好。而是因为数据不好。好好想想。"

修改后：

"大多数生物信息学流程在生产环境中都会崩溃。代码运行正常，只是数据不符合流程内置的假设。"

修改点：移除开场白、二元对比和强调辅助语，明确指出具体问题。