remove unnecessary secondary clauses

Reviewed-on: #9

prompts/LLM_PROSE_TELLS.md

@@ -1,9 +1,7 @@
 # LLM Prose Tells
 
-All of these show up in human writing occasionally. No single one is conclusive
+Human writers occasionally use every pattern in this document. The reason they
-on its own. The difference is concentration — a person might lean on one or two
+work as tells is that LLM output packs fifteen of them into a paragraph.
-of these habits across an entire essay, but LLM output will use fifteen of them
-per paragraph, consistently, throughout the entire piece.
 
 ---
 
@@ -16,9 +14,17 @@ 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 single most recognizable LLM construction. Models produce this at roughly
+The most recognizable LLM construction. Models produce this at roughly 10 to 50x
-10–50x the rate of human writers. Four of them in one essay and you know what
+the rate of human writers. Four of them in one essay and you know what you're
-you're reading.
+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
+piece. Models scatter them everywhere because the em-dash can stand in for any
+other punctuation mark. More than two or three per page is a signal.
 
 ### The Colon Elaboration
 
@@ -27,15 +33,15 @@ A short declarative clause, then a colon, then a longer explanation.
 > "The answer is simple: we need to rethink our approach from the ground up."
 
 Models reach for this in every other paragraph. The construction is perfectly
-normal; the frequency gives it away.
+normal. The frequency gives it away.
 
 ### The Triple Construction
 
 > "It's fast, it's scalable, and it's open source."
 
-Three parallel items in a list, usually escalating. Always exactly three. Rarely
+Three parallel items in a list, usually escalating. Always exactly three (rarely
-two. Never four. Strict grammatical parallelism that human writers rarely bother
+two, never four) with strict grammatical parallelism that human writers rarely
-maintaining.
+bother maintaining.
 
 ### The Staccato Burst
 
@@ -44,16 +50,15 @@ 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 that reads as generated.
+at matching length creates a mechanical regularity.
 
 ### The Two-Clause Compound Sentence
 
-This might be the single most pervasive structural tell, and it's easy to miss
+Possibly the most pervasive tell, and easy to miss because each individual
-because each individual instance looks like normal English. The model produces
+instance looks like normal English. The model produces sentence after sentence
-sentence after sentence in the same shape: an independent clause, a comma, a
+where an independent clause is followed by a comma, a conjunction ("and," "but,"
-conjunction ("and," "but," "which," "because"), and a second independent clause
+"which," "because"), and a second independent clause of similar length. Every
-of similar length. Over and over. Every sentence is two balanced halves joined
+sentence becomes two balanced halves.
-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
@@ -63,24 +68,22 @@ in the middle.
 
 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 the
+embed their complexity in the middle. When every sentence on the page has that
-same two-part comma-conjunction-comma 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, and this
+Model-generated paragraphs contain between three and five sentences. This count
-count holds steady across an entire piece. If the first paragraph has four
+holds steady across a piece. If the first paragraph has four sentences, every
-sentences, every subsequent paragraph will too. Human writers are much more
+subsequent paragraph will too. Human writers are much more varied (a single
-varied — a single sentence followed by one that runs eight or nine — because
+sentence followed by one that runs eight or nine) because they follow the shape
-they follow the shape of an idea, not a template.
+of an idea.
 
 ### 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 entire essay is a
+or "Let that sink in." on their own line. Using one in an essay is a reasonable
-reasonable stylistic choice, but models drop them in once per section or more,
+stylistic choice, but models drop them in once per section or more.
-at which point it stops being deliberate and becomes a habit.
 
 ### The Pivot Paragraph
 
@@ -95,14 +98,12 @@ 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, not to express a
+the argument that follows it. Its purpose is to perform nuance.
-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" to draw a comparison the
+"whereas," "as opposed to," "unlike," or "except that."
-reader could already infer.
 
 > "Models write one register above where a human would, whereas human writers
 > tend to match register to context."
@@ -111,13 +112,27 @@ 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."
 
-A rhetorical question immediately followed by its own answer. Models lean on
+A rhetorical question immediately followed by its own answer. Models do this two
-this two or three times per piece because it generates the feeling of forward
+or three times per piece because it fakes forward momentum. A human writer might
-momentum without requiring any actual argument. A human writer might do it once.
+do it once.
 
 ---
 
@@ -145,16 +160,15 @@ 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 already makes the importance clear.
+which is unnecessary when the writing itself 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
+"almost certainly," "almost exclusively." The word "almost" shows up at high
-extraordinary density in model-generated analytical prose. It's a micro-hedge,
+density in model-generated analytical prose. It's a micro-hedge, diagnostic in
-less obvious than the full hedge stack but just as diagnostic when it appears
+volume.
-ten or fifteen times in a single document.
 
 ### "In an era of..."
 
@@ -162,7 +176,7 @@ ten or fifteen times in a single document.
 
 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 before they've said anything specific.
+out to the civilizational scale.
 
 ---
 
@@ -173,9 +187,8 @@ out to the civilizational scale before they've said anything specific.
 > "While X has its drawbacks, it also offers significant benefits."
 
 Every argument followed by a concession, every criticism softened. A direct
-artifact of RLHF training, which penalizes strong stances. The result is a model
+artifact of RLHF training, which penalizes strong stances. Models reflexively
-that reflexively both-sides everything even when a clear position would serve
+both-sides everything.
-the reader better.
 
 ### The Throat-Clearing Opener
 
@@ -183,8 +196,7 @@ the reader better.
 > has never been more important."
 
 The first paragraph of most model-generated essays adds no information. Delete
-it and the piece improves immediately. The actual argument starts in paragraph
+it and the piece improves.
-two.
 
 ### The False Conclusion
 
@@ -220,7 +232,7 @@ 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. That interchangeability is what makes it identifiable.
+natural disaster.
 
 ---
 
@@ -230,20 +242,20 @@ natural disaster. That interchangeability is what makes it identifiable.
 
 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 — 50 words in one section, 400 in the next.
+uneven.
 
 ### The Five-Paragraph Prison
 
 Model essays follow a rigid introduction-body-conclusion arc even when nobody
-asked for one. Introduction previews the argument. Body presents 3–5 points.
+asked for one. The introduction previews the argument, the body presents 3 to 5
-Conclusion restates the thesis in different words.
+points, and then the conclusion restates the thesis.
 
 ### 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,"
+unbroken chain of transition words: "However," "Furthermore," "Moreover,"
 "Additionally," "That said," "To that end," "With that in mind," "Building on
-this." Human prose moves between ideas without announcing every transition.
+this." Human prose doesn't do this.
 
 ### Absence of Mess
 
@@ -253,9 +265,8 @@ obscure idiom without explaining it, make a joke that risks falling flat, leave
 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. The total absence of rough edges, false
+Human writing does all of those things regularly. That total absence of rough
-starts, and odd rhythmic choices is one of the strongest signals that text was
+patches and false starts is one of the strongest signals.
-machine-generated.
 
 ---
 
@@ -267,7 +278,6 @@ machine-generated.
 
 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..."
 
@@ -277,11 +287,10 @@ verbal tics before a qualification the model believes someone expects.
 
 ### The Metaphor Crutch
 
-Models rely on a small, predictable set of metaphors — "double-edged sword,"
+Models rely on a small, predictable set of metaphors ("double-edged sword," "tip
-"tip of the iceberg," "north star," "building blocks," "elephant in the room,"
+of the iceberg," "north star," "building blocks," "elephant in the room,"
-"perfect storm," "game-changer" — and reach for them with unusual regularity
+"perfect storm," "game-changer") and reach for them with unusual regularity
-across every topic. The pool is noticeably smaller than what human writers draw
+across every topic.
-from.
 
 ---
 
@@ -291,11 +300,10 @@ No single pattern on this list proves anything by itself. Humans use em-dashes.
 Humans write "crucial." Humans ask rhetorical questions.
 
 What gives it away is how many of these show up at once. Model output will hit
-10–20 of these patterns per page. Human writing might trigger 2–3, distributed
+10 to 20 of these patterns per page. Human writing might trigger 2 or 3,
-unevenly, mixed with idiosyncratic constructions no model would produce. When
+distributed unevenly. When every paragraph on the page reads like it came from
-every paragraph on the page reads like it came from the same careful, balanced,
+the same careful, balanced, slightly formal, structurally predictable process,
-slightly formal, structurally predictable process, it was probably generated by
+it was generated by one.
-one.
 
 ---
 
@@ -338,86 +346,100 @@ passes, because fixing one pattern often introduces another.
    to the unqualified claim or to drop the sentence entirely. If the claim needs
    "almost" to be true, it might not be worth making.
 
+7. Search for em-dashes and replace each one with the punctuation mark that
+   would normally be used in that position (comma, semicolon, colon, period, or
+   parentheses). If you can't identify which one it should be, the sentence
+   needs to be restructured.
+
 ### Pass 2: Sentence-Level Restructuring
 
-7. Find every em-dash pivot ("not X—but Y," "not just X—Y," "more than X—Y") and
+8. Find every em-dash pivot ("not X...but Y," "not just X...Y," "more than
-   rewrite it as two separate clauses or a single sentence that makes the point
+   X...Y") and rewrite it as two separate clauses or a single sentence that
-   without the negation-then-correction structure.
+   makes the point without the negation-then-correction structure.
 
-8. Find every colon elaboration and check whether it's doing real work. If the
+9. Find every colon elaboration and check whether it's doing real work. If the
    clause before the colon could be deleted without losing meaning, rewrite the
    sentence to start with the substance that comes after the colon.
 
-9. Find every triple construction (three parallel items in a row) and either
+10. Find every triple construction (three parallel items in a row) and either
-   reduce it to two, expand it to four or more, or break the parallelism so the
+    reduce it to two, expand it to four or more, or break the parallelism so the
-   items don't share the same grammatical structure.
+    items don't share the same grammatical structure.
 
-10. Find every staccato burst (three or more short sentences in a row at similar
+11. Find every staccato burst (three or more short sentences in a row at similar
     length) and combine at least two of them into a longer sentence, or vary
     their lengths so they don't land at the same cadence.
 
-11. Find every unnecessary contrast ("whereas," "as opposed to," "unlike," "as
+12. Find every unnecessary contrast ("whereas," "as opposed to," "unlike," "as
     compared to," "except that") and check whether the contrasting clause adds
     information not already obvious from the main clause. If the sentence says
     the same thing twice from two directions, delete the contrast.
 
-12. Check for the two-clause compound sentence pattern. If most sentences in a
+13. Check for the two-clause compound sentence pattern. If most sentences in a
-    passage follow the "[clause], [conjunction] [clause]" structure, rewrite
+    passage follow the "\[clause\], \[conjunction\] \[clause\]" structure,
-    some of them. Break a few into two sentences. Start some with a subordinate
+    rewrite some of them. Break a few into two sentences. Start some with a
-    clause. Embed a relative clause in the middle of one instead of appending it
+    subordinate clause. Embed a relative clause in the middle of one instead of
-    at the end. The goal is variety in sentence shape, not just sentence length.
+    appending it at the end. The goal is variety in sentence shape, not just
+    sentence length.
 
-13. Find every rhetorical question that is immediately followed by its own
+14. Find every rhetorical question that is immediately followed by its own
     answer and rewrite the passage as a direct statement.
 
-14. Find every sentence fragment being used as its own paragraph and either
+15. Find every sentence fragment being used as its own paragraph and either
     delete it or expand it into a complete sentence that adds actual
     information.
 
-15. Find every pivot paragraph ("But here's where it gets interesting." and
+16. Check for unnecessary elaboration. Read every clause, phrase, and adjective
+    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
 
-16. Check paragraph lengths across the piece and verify they actually vary. If
+18. 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.
 
-17. Check section lengths for suspicious uniformity. If every section is roughly
+19. 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.
 
-18. Check the first word of every paragraph for chains of connectors ("However,"
+20. 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.
 
-19. Check whether every argument is followed by a concession or qualifier. If
+21. 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.
 
-20. Read the first paragraph and ask whether deleting it would improve the
+22. 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.
 
-21. Read the last paragraph and check whether it restates the thesis or uses a
+23. 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
 
-22. Read the piece aloud and listen for passages that sound too smooth, too
+24. 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.
 
-23. Check that the piece contains at least a few constructions that feel
+25. Check that the piece contains at least a few constructions that feel
-    idiosyncratic — a sentence with unusual word order, a parenthetical that
+    idiosyncratic: a sentence with unusual word order, a parenthetical that goes
-    goes on a bit long, an aside only loosely connected to the main point, a
+    on a bit long, an aside only loosely connected to the main point, a word
-    word choice that's specific and unexpected. If every sentence is clean and
+    choice that's specific and unexpected. If every sentence is clean and
     correct and unremarkable, it will still read as generated.
 
-24. Verify that you haven't introduced new patterns while fixing the original
+26. 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.
 
@@ -452,18 +474,30 @@ roughly like this:
 > in common? _(pastes six sentences from the doc)_
 >
 > **model:** They're all exactly two independent clauses joined by a comma and a
-> conjunction. Every single one is "[statement], [conjunction] [second >
+> conjunction. Every single one is "\[statement\], \[conjunction\] \[second
-> statement]." The same sentence shape, over and over.
+> statement\]." The same sentence shape, over and over.
 >
 > **human:** the dramatic fragment paragraph has a tell in it
 >
 > **model:** "One of these in an entire essay is a stylistic choice. One per
 > section is a tic." Two-clause parallel structure with the same shape, and also
 > a staccato pair.
+>
+> **human:** add em dashes generally as a tell, and remove them all from the
+> tells doc
+>
+> **model:** _(rewrites entire document without em-dashes while describing
+> em-dash overuse)_
+>
+> **human:** now run the checklist methodically on each paragraph
+>
+> **model:** _(finds staccato burst in the section about triple constructions, a
+> triple in the section about absence of mess, two-clause compounds everywhere,
+> and "almost" hedges in its own prose about em-dash overuse)_
 
 The human compared this process to the deleted scene in Terminator 2 where John
 Connor switches the T-800's CPU to learning mode. The model compared it to a
-physician trying to heal itself. Both descriptions are probably accurate.
+physician trying to heal itself. Both are accurate.
 
-This document has been through six editing passes and it probably still has
+This document has been through eight editing passes and it still has tells in
-tells in it.
+it.