remove redundant adjectives

prompts/LLM_PROSE_TELLS.md

@@ -14,19 +14,19 @@ 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 single most recognizable LLM construction. Models produce this at roughly 10
+The most recognizable LLM construction. Models produce this at roughly 10 to 50x
-to 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, often multiple times per paragraph. A human
-writer might use one or two in an entire piece for a specific parenthetical
+writer might use one or two in a piece for a specific parenthetical effect.
-effect. Models scatter them everywhere because the em-dash can stand in for any
+Models scatter them everywhere because the em-dash can stand in for any other
-other punctuation mark, so they default to it. More than two or three per page
+punctuation mark, so they default to it. More than two or three per page is a
-is a meaningful signal on its own.
+signal.
 
 ### The Colon Elaboration
 
@@ -56,11 +56,11 @@ at matching length creates a mechanical regularity that reads as generated.
 
 ### The Two-Clause Compound Sentence
 
-Possibly the most pervasive structural tell, and easy to miss because each
+Possibly the most pervasive tell, and easy to miss because each individual
-individual instance looks like normal English. The model produces sentence after
+instance looks like normal English. The model produces sentence after sentence
-sentence where an independent clause is followed by a comma, a conjunction
+where an independent clause is followed by a comma, a conjunction ("and," "but,"
-("and," "but," "which," "because"), and a second independent clause of similar
+"which," "because"), and a second independent clause of similar length. Every
-length. Every sentence becomes two balanced halves joined in the middle.
+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
@@ -77,17 +77,17 @@ pinpoint but easy to feel.
 ### Uniform Sentences Per Paragraph
 
 Model-generated paragraphs contain between three and five sentences. This count
-holds steady across an entire piece. If the first paragraph has four sentences,
+holds steady across a piece. If the first paragraph has four sentences, every
-every subsequent paragraph will too. Human writers are much more varied (a
+subsequent paragraph will too. Human writers are much more varied (a single
-single sentence followed by one that runs eight or nine) because they follow the
+sentence followed by one that runs eight or nine) because they follow the shape
-shape of an idea, not a template.
+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 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
-at which point it becomes a habit rather than a deliberate decision.
+point it becomes a habit.
 
 ### The Pivot Paragraph
 
@@ -123,9 +123,9 @@ still says everything it needs to, the contrast was filler.
 Models keep going after the sentence has already made its point, tacking on
 clarifying phrases, adverbial modifiers, or restatements that add nothing.
 
-> "A person might lean on one or two of these habits across an entire essay, but
+> "A person might lean on one or two of these habits across an essay, but LLM
-> LLM output will use fifteen of them per paragraph, consistently, throughout
+> output will use fifteen of them per paragraph, consistently, throughout the
-> the entire piece."
+> 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
@@ -173,10 +173,10 @@ which is unnecessary when the writing itself already makes the importance clear.
 
 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, less obvious
-less obvious than the full hedge stack but just as diagnostic when it appears
+than the full hedge stack but just as diagnostic when it appears ten or fifteen
-ten or fifteen times in a single document.
+times in a single document.
 
 ### "In an era of..."
 
@@ -493,9 +493,9 @@ roughly like this:
 >
 > **human:** the dramatic fragment paragraph has a tell in it
 >
-> **model:** "One of these in an entire essay is a stylistic choice. One per
+> **model:** "One of these in an essay is a stylistic choice. One per section is
-> section is a tic." Two-clause parallel structure with the same shape, and also
+> a tic." Two-clause parallel structure with the same shape, and also a staccato
-> a staccato pair.
+> pair.
 >
 > **human:** add em dashes generally as a tell, and remove them all from the
 > tells doc