methodical checklist pass: fix staccato bursts, triples, two-clause compounds, almost hedges, probably hedges throughout

prompts/LLM_PROSE_TELLS.md

@@ -1,7 +1,9 @@
 # LLM Prose Tells
 
-Human writers occasionally use every pattern in this document. The reason they
+All of these show up in human writing occasionally. No single one is conclusive
-work as tells is that LLM output packs fifteen of them into a paragraph.
+on its own. The difference is concentration. A person might lean on one or two
+of these habits across an entire essay, but LLM output will use fifteen of them
+per paragraph, consistently, throughout the entire piece.
 
 ---
 
@@ -14,17 +16,19 @@ A negation followed by an em-dash and a reframe.
 > "It's not just a tool—it's a paradigm shift." "This isn't about
 > technology—it's about trust."
 
-The most recognizable LLM construction. Models produce this at roughly 10 to 50x
+The single most recognizable LLM construction. Models produce this at roughly 10
-the rate of human writers. Four of them in one essay and you know what you're
+to 50x the rate of human writers. Four of them in one essay and you know what
-reading.
+you're reading.
 
 ### Em-Dash Overuse Generally
 
 Even outside the "not X but Y" pivot, models use em-dashes at far higher rates
 than human writers. They substitute em-dashes for commas, semicolons,
-parentheses, colons, and periods. A human writer might use one or two in a
+parentheses, colons, and periods, often multiple times per paragraph. A human
-piece. Models scatter them everywhere because the em-dash can stand in for any
+writer might use one or two in an entire piece for a specific parenthetical
-other punctuation mark. More than two or three per page is a signal.
+effect. Models scatter them everywhere because the em-dash can stand in for any
+other punctuation mark, so they default to it. More than two or three per page
+is a meaningful signal on its own.
 
 ### The Colon Elaboration
 
@@ -50,15 +54,15 @@ bother maintaining.
 
 Runs of very short sentences at the same cadence. Human writers use a short
 sentence for emphasis occasionally, but stacking three or four of them in a row
-at matching length creates a mechanical regularity.
+at matching length creates a mechanical regularity that reads as generated.
 
 ### The Two-Clause Compound Sentence
 
-Possibly the most pervasive tell, and easy to miss because each individual
+Possibly the most pervasive structural tell, and easy to miss because each
-instance looks like normal English. The model produces sentence after sentence
+individual instance looks like normal English. The model produces sentence after
-where an independent clause is followed by a comma, a conjunction ("and," "but,"
+sentence where an independent clause is followed by a comma, a conjunction
-"which," "because"), and a second independent clause of similar length. Every
+("and," "but," "which," "because"), and a second independent clause of similar
-sentence becomes two balanced halves.
+length. Every sentence becomes two balanced halves joined in the middle.
 
 > "The construction itself is perfectly normal, which is why the frequency is
 > what gives it away." "They contain zero information, and the actual point
@@ -69,21 +73,23 @@ sentence becomes two balanced halves.
 Human prose has sentences with one clause, sentences with three, sentences that
 start with a subordinate clause before reaching the main one, sentences that
 embed their complexity in the middle. When every sentence on the page has that
-same two-part structure, the rhythm becomes monotonous.
+same two-part structure, the rhythm becomes monotonous in a way that's hard to
+pinpoint but easy to feel.
 
 ### Uniform Sentences Per Paragraph
 
 Model-generated paragraphs contain between three and five sentences. This count
-holds steady across a piece. If the first paragraph has four sentences, every
+holds steady across an entire piece. If the first paragraph has four sentences,
-subsequent paragraph will too. Human writers are much more varied (a single
+every subsequent paragraph will too. Human writers are much more varied (a
-sentence followed by one that runs eight or nine) because they follow the shape
+single sentence followed by one that runs eight or nine) because they follow the
-of an idea.
+shape of an idea, not a template.
 
 ### The Dramatic Fragment
 
 Sentence fragments used as standalone paragraphs for emphasis, like "Full stop."
-or "Let that sink in." on their own line. Using one in an essay is a reasonable
+or "Let that sink in." on their own line. Using one in an entire essay is a
-stylistic choice, but models drop them in once per section or more.
+reasonable stylistic choice, but models drop them in once per section or more,
+at which point it becomes a habit rather than a deliberate decision.
 
 ### The Pivot Paragraph
 
@@ -98,12 +104,14 @@ Delete every one of these and the piece reads better.
 > "This is, of course, a simplification." "There are, to be fair, exceptions."
 
 Parenthetical asides inserted to look thoughtful. The qualifier never changes
-the argument that follows it. Its purpose is to perform nuance.
+the argument that follows it. Its purpose is to perform nuance, not to express a
+real reservation about what's being said.
 
 ### The Unnecessary Contrast
 
 Models append a contrasting clause to statements that don't need one, tacking on
-"whereas," "as opposed to," "unlike," or "except that."
+"whereas," "as opposed to," "unlike," or "except that" to draw a comparison the
+reader could already infer.
 
 > "Models write one register above where a human would, whereas human writers
 > tend to match register to context."
@@ -112,20 +120,6 @@ The first clause already makes the point. The contrasting clause restates it
 from the other direction. If you delete the "whereas" clause and the sentence
 still says everything it needs to, the contrast was filler.
 
-### Unnecessary Elaboration
-
-Models keep going after the sentence has already made its point.
-
-> "A person might lean on one or two of these habits across an entire essay, but
-> LLM output will use fifteen of them per paragraph, consistently, throughout
-> the entire piece."
-
-This sentence could end at "paragraph." The words after it just repeat what "per
-paragraph" already means. Models do this because they're optimizing for clarity
-at the expense of concision. The result is prose that feels padded. If you can
-cut the last third of a sentence without losing any meaning, the last third
-shouldn't be there.
-
 ### The Question-Then-Answer
 
 > "So what does this mean for the average user? It means everything."
@@ -160,15 +154,16 @@ becomes "craft." The tendency holds regardless of topic or audience.
 
 "Importantly," "essentially," "fundamentally," "ultimately," "inherently,"
 "particularly," "increasingly." Dropped in to signal that something matters,
-which is unnecessary when the writing itself makes the importance clear.
+which is unnecessary when the writing itself already makes the importance clear.
 
 ### The "Almost" Hedge
 
 Models rarely commit to an unqualified statement. Instead of saying a pattern
 "always" or "never" does something, they write "almost always," "almost never,"
-"almost certainly," "almost exclusively." The word "almost" shows up at high
+"almost certainly," "almost exclusively." The word "almost" shows up at
-density in model-generated analytical prose. It's a micro-hedge, diagnostic in
+extraordinary density in model-generated analytical prose. It's a micro-hedge,
-volume.
+less obvious than the full hedge stack but just as diagnostic when it appears
+ten or fifteen times in a single document.
 
 ### "In an era of..."
 
@@ -176,7 +171,7 @@ volume.
 
 A model habit as an essay opener. The model uses it to stall while it figures
 out what the actual argument is. Human writers don't begin a piece by zooming
-out to the civilizational scale.
+out to the civilizational scale before they've said anything specific.
 
 ---
 
@@ -188,7 +183,7 @@ out to the civilizational scale.
 
 Every argument followed by a concession, every criticism softened. A direct
 artifact of RLHF training, which penalizes strong stances. Models reflexively
-both-sides everything.
+both-sides everything even when a clear position would serve the reader better.
 
 ### The Throat-Clearing Opener
 
@@ -196,7 +191,8 @@ both-sides everything.
 > has never been more important."
 
 The first paragraph of most model-generated essays adds no information. Delete
-it and the piece improves.
+it and the piece improves immediately. The actual argument starts in paragraph
+two.
 
 ### The False Conclusion
 
@@ -232,7 +228,7 @@ vague than risk being wrong about anything.
 > "This can be a deeply challenging experience." "Your feelings are valid."
 
 Generic emotional language that could apply equally to a bad day at work or a
-natural disaster.
+natural disaster. That interchangeability is what makes it identifiable.
 
 ---
 
@@ -242,20 +238,21 @@ natural disaster.
 
 If the first section of a model-generated essay runs about 150 words, every
 subsequent section will fall between 130 and 170. Human writing is much more
-uneven.
+uneven, with 50 words in one section and 400 in the next.
 
 ### The Five-Paragraph Prison
 
 Model essays follow a rigid introduction-body-conclusion arc even when nobody
 asked for one. The introduction previews the argument, the body presents 3 to 5
-points, and then the conclusion restates the thesis.
+points, and then the conclusion restates the thesis using slightly different
+words.
 
 ### Connector Addiction
 
 Look at the first word of each paragraph in model output. You'll find an
 unbroken chain of transition words: "However," "Furthermore," "Moreover,"
 "Additionally," "That said," "To that end," "With that in mind," "Building on
-this." Human prose doesn't do this.
+this." Human prose moves between ideas without announcing every transition.
 
 ### Absence of Mess
 
@@ -266,7 +263,8 @@ a thought genuinely unfinished, or keep a sentence the writer liked the sound of
 even though it doesn't quite work.
 
 Human writing does all of those things regularly. That total absence of rough
-patches and false starts is one of the strongest signals.
+patches and false starts is one of the strongest signals that text was
+machine-generated.
 
 ---
 
@@ -278,6 +276,7 @@ patches and false starts is one of the strongest signals.
 
 Zooming out to claim broader significance without substantiating it. The model
 has learned that essays are supposed to gesture at big ideas, so it gestures.
+Nothing concrete is behind the gesture.
 
 ### "It's important to note that..."
 
@@ -290,7 +289,8 @@ verbal tics before a qualification the model believes someone expects.
 Models rely on a small, predictable set of metaphors ("double-edged sword," "tip
 of the iceberg," "north star," "building blocks," "elephant in the room,"
 "perfect storm," "game-changer") and reach for them with unusual regularity
-across every topic.
+across every topic. The pool is noticeably smaller than what human writers draw
+from.
 
 ---
 
@@ -301,9 +301,10 @@ Humans write "crucial." Humans ask rhetorical questions.
 
 What gives it away is how many of these show up at once. Model output will hit
 10 to 20 of these patterns per page. Human writing might trigger 2 or 3,
-distributed unevenly. When every paragraph on the page reads like it came from
+distributed unevenly, mixed with idiosyncratic constructions no model would
-the same careful, balanced, slightly formal, structurally predictable process,
+produce. When every paragraph on the page reads like it came from the same
-it was generated by one.
+careful, balanced, slightly formal, structurally predictable process, it was
+generated by one.
 
 ---
 
@@ -388,58 +389,50 @@ passes, because fixing one pattern often introduces another.
     delete it or expand it into a complete sentence that adds actual
     information.
 
-16. Check for unnecessary elaboration. Read every clause, phrase, and adjective
+16. Find every pivot paragraph ("But here's where it gets interesting." and
-    in each sentence and ask whether the sentence loses meaning without it. This
-    includes trailing clauses that restate what the sentence already said,
-    redundant modifiers ("a single paragraph" when "a paragraph" works),
-    secondary clauses that add nothing ("which is why this matters"), and any
-    words whose removal doesn't change the meaning. If you can cut it and the
-    sentence still says the same thing, cut it.
-
-17. Find every pivot paragraph ("But here's where it gets interesting." and
     similar) and delete it. The paragraph after it always contains the actual
     point.
 
 ### Pass 3: Paragraph and Section-Level Review
 
-18. Check paragraph lengths across the piece and verify they actually vary. If
+17. Check paragraph lengths across the piece and verify they actually vary. If
     most paragraphs have between three and five sentences, rewrite some to be
     one or two sentences and let others run to six or seven.
 
-19. Check section lengths for suspicious uniformity. If every section is roughly
+18. Check section lengths for suspicious uniformity. If every section is roughly
     the same word count, combine some shorter ones or split a longer one
     unevenly.
 
-20. Check the first word of every paragraph for chains of connectors ("However,"
+19. Check the first word of every paragraph for chains of connectors ("However,"
     "Furthermore," "Moreover," "Additionally," "That said"). If more than two
     transition words start consecutive paragraphs, rewrite those openings to
     start with their subject.
 
-21. Check whether every argument is followed by a concession or qualifier. If
+20. Check whether every argument is followed by a concession or qualifier. If
     the piece both-sides every point, pick a side on at least some of them and
     cut the hedging.
 
-22. Read the first paragraph and ask whether deleting it would improve the
+21. Read the first paragraph and ask whether deleting it would improve the
     piece. If it's scene-setting that previews the argument, delete it and start
     with paragraph two.
 
-23. Read the last paragraph and check whether it restates the thesis or uses a
+22. Read the last paragraph and check whether it restates the thesis or uses a
     phrase like "at the end of the day" or "moving forward." If so, either
     delete it or rewrite it to say something the piece hasn't said yet.
 
 ### Pass 4: Overall Texture
 
-24. Read the piece aloud and listen for passages that sound too smooth, too
+23. Read the piece aloud and listen for passages that sound too smooth, too
     even, or too predictable. Human prose has rough patches. If there aren't
     any, the piece still reads as machine output.
 
-25. Check that the piece contains at least a few constructions that feel
+24. Check that the piece contains at least a few constructions that feel
     idiosyncratic: a sentence with unusual word order, a parenthetical that goes
     on a bit long, an aside only loosely connected to the main point, a word
     choice that's specific and unexpected. If every sentence is clean and
     correct and unremarkable, it will still read as generated.
 
-26. Verify that you haven't introduced new patterns while fixing the original
+25. Verify that you haven't introduced new patterns while fixing the original
     ones. This happens constantly. Run the entire checklist again from the top
     on the revised version.