remove unfunny frequency exchange from lol section

Reviewed-on: #11

prompts/LLM_PROSE_TELLS.md

@@ -1,9 +1,7 @@
 # LLM Prose Tells
 
-All of these show up in human writing occasionally, and no single one is
+A catalog of structural, lexical, and rhetorical patterns found in LLM-generated
-conclusive on its own. The difference is concentration, because a person might
+prose.
-lean on one or two of these habits across an entire essay while LLM output will
-use fifteen of them per paragraph, consistently, throughout the entire piece.
 
 ---
 
@@ -11,15 +9,16 @@ use fifteen of them per paragraph, consistently, throughout the entire piece.
 
 ### The Em-Dash Pivot: "Not X—but Y"
 
-A negation followed by an em-dash and a reframe. The single most recognizable
+A negation followed by an em-dash and a reframe.
-LLM construction.
 
 > "It's not just a tool—it's a paradigm shift." "This isn't about
 > technology—it's about trust."
 
-Models produce this at roughly 10–50x the rate of human writers, and when it
+### Em-Dash Overuse Generally
-appears four times in the same essay you're almost certainly reading generated
+
-text.
+Even outside the "not X but Y" pivot, models substitute em-dashes for commas,
+semicolons, parentheses, colons, and periods. The em-dash can replace any other
+punctuation mark, and models default to it for that reason.
 
 ### The Colon Elaboration
 
@@ -27,85 +26,91 @@ 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 nearly every other paragraph. The construction itself
-is perfectly normal, which is why the frequency is what 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, with exactly three items
+Three parallel items in a list, usually escalating. Always exactly three (rarely
-every time (rarely two, almost never four) and strict grammatical parallelism
+two, never four) with strict grammatical parallelism.
-that human writers rarely bother maintaining.
 
 ### The Staccato Burst
 
 > "This matters. It always has. And it always will." "The data is clear. The
 > trend is undeniable. The conclusion is obvious."
 
-Runs of very short sentences at the same cadence. Human writers will use a short
+Runs of very short sentences at the same cadence and matching length.
-sentence for emphasis occasionally, but they don't stack three or four of them
+
-in a row at matching length, because real prose has variable rhythm. When you
+### The Two-Clause Compound Sentence
-see a paragraph where every sentence is under ten words and they're all roughly
+
-the same size, that mechanical regularity is a strong signal.
+An independent clause, a comma, a conjunction ("and," "but," "which,"
+"because"), and a second independent clause of similar length. Every sentence
+becomes two balanced halves.
+
+> "The construction itself is perfectly normal, which is why the frequency is
+> what gives it away." "They contain zero information, and the actual point
+> always comes in the paragraph that follows them." "The qualifier never changes
+> the argument that follows it, and its purpose is to perform nuance rather than
+> to express an actual reservation."
+
+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.
 
 ### Uniform Sentences Per Paragraph
 
-Model-generated paragraphs almost always contain between three and five
+Model-generated paragraphs contain between three and five sentences, a count
-sentences, and this count holds remarkably steady across an entire piece. If the
+that holds steady across a piece. If the first paragraph has four sentences,
-first paragraph has four sentences, nearly every subsequent paragraph will too.
+every subsequent paragraph will too.
-Human writers produce much more varied paragraph lengths — a single sentence
-followed by one that runs eight or nine — as a natural result of following the
-shape of an idea rather than filling a template.
 
 ### The Dramatic Fragment
 
-Sentence fragments used as standalone paragraphs for emphasis, like "Full stop."
+Sentence fragments used as standalone paragraphs for emphasis.
-or "Let that sink in." on their own line. One of these in an entire essay is a
+
-stylistic choice. One per section is a tic, and models drop them in at that rate
+> "Full stop." "Let that sink in."
-or higher.
 
 ### The Pivot Paragraph
 
 > "But here's where it gets interesting." "Which raises an uncomfortable truth."
 
-One-sentence paragraphs that exist only to transition between ideas. They
+One-sentence paragraphs that exist only to transition between ideas, containing
-contain zero information, and the actual point always comes in the paragraph
+zero information. The actual point is always in the next paragraph.
-that follows them. Delete every one of these and the piece reads better.
 
 ### The Parenthetical Qualifier
 
 > "This is, of course, a simplification." "There are, to be fair, exceptions."
 
-Parenthetical asides inserted to look thoughtful. The qualifier almost never
+Parenthetical asides inserted to perform nuance without ever changing the
-changes the argument that follows it, and its purpose is to perform nuance
+argument.
-rather than to express an actual reservation about what's being said.
 
 ### The Unnecessary Contrast
 
-Models append a contrasting clause to statements that don't need one, tacking on
+A contrasting clause appended to a statement that doesn't need one, using
-"whereas," "as opposed to," "unlike," or "except that" to draw a comparison that
+"whereas," "as opposed to," "unlike," or "except that."
-adds nothing the reader couldn't already infer.
 
 > "Models write one register above where a human would, whereas human writers
-> tend to match register to context." "The lists use rigidly parallel grammar,
+> tend to match register to context."
-> as opposed to the looser structure you'd see in human writing."
 
-The first clause already makes the point. The contrasting clause just restates
+The contrasting clause restates what the first clause already said. If you
-it from the other direction. This happens because models are trained to be
+delete the "whereas" clause and the sentence still says everything it needs to,
-thorough and to anticipate objections, so they compulsively spell out both sides
+the contrast was filler.
-of a distinction even when one side is obvious. If you delete the "whereas"
+
-clause and the sentence still says everything it needs to, the contrast was
+### Unnecessary Elaboration
-filler.
+
+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 repeat what "per
+paragraph" already means. If you can cut the last third of a sentence without
+losing 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.
-this two or three times per piece because it generates the feeling of forward
-momentum without requiring any actual argumentative work. A human writer might
-do it once.
 
 ---
 
@@ -113,39 +118,38 @@ do it once.
 
 ### Overused Intensifiers
 
-The following words appear at dramatically elevated rates in model output
+"Crucial," "vital," "robust," "comprehensive," "fundamental," "arguably,"
-compared to human-written text: "crucial," "vital," "robust," "comprehensive,"
+"straightforward," "noteworthy," "realm," "landscape," "leverage" (as a verb),
-"fundamental," "arguably," "straightforward," "noteworthy," "realm,"
+"delve," "tapestry," "multifaceted," "nuanced" (applied to the model's own
-"landscape," "leverage" (used as a verb), "delve," "tapestry," "multifaceted,"
+analysis), "pivotal," "unprecedented" (applied to things with plenty of
-"nuanced" (which models almost always apply to their own analysis), "pivotal,"
+precedent), "navigate," "foster," "underscores," "resonates," "embark,"
-"unprecedented" (frequently applied to things that have plenty of precedent),
+"streamline," "spearhead."
-"navigate," "foster," "underscores," "resonates," "embark," "streamline," and
-"spearhead." Three or more on the same page is a strong signal.
 
 ### Elevated Register Drift
 
-Models consistently write one register above where a human would for the same
+Models write one register above where a human would. "Use" becomes "utilize."
-content, replacing "use" with "utilize," "start" with "commence," "help" with
+"Start" becomes "commence." "Help" becomes "facilitate." "Show" becomes
-"facilitate," "show" with "demonstrate," "try" with "endeavor," "change" with
+"demonstrate." "Try" becomes "endeavor." "Change" becomes "transform." "Make"
-"transform," and "make" with "craft." The tendency holds across every topic
+becomes "craft."
-regardless of audience.
 
 ### Filler Adverbs
 
 "Importantly," "essentially," "fundamentally," "ultimately," "inherently,"
-"particularly," and "increasingly" get dropped in to signal that something
+"particularly," "increasingly." Dropped in to signal that something matters when
-matters. If the writing itself has already made the importance clear through its
+the writing itself should make the importance clear.
-content and structure, these adverbs aren't doing anything except taking up
+
-space.
+### The "Almost" Hedge
+
+Instead of saying a pattern "always" or "never" does something, models write
+"almost always," "almost never," "almost certainly," "almost exclusively." A
+micro-hedge, less obvious than the full hedge stack.
 
 ### "In an era of..."
 
 > "In an era of rapid technological change..."
 
-Almost exclusively a model habit as an essay opener. The model uses it to stall
+Used to open an essay. The model is stalling while it figures out what the
-while it figures out what the actual argument is, because almost no human writer
+actual argument is.
-begins a piece by zooming out to the civilizational scale before they've said
-anything specific.
 
 ---
 
@@ -156,25 +160,20 @@ 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 and produces models
+artifact of RLHF training, which penalizes strong stances.
-that reflexively both-sides everything even when a clear position would serve
-the reader better.
 
 ### The Throat-Clearing Opener
 
 > "In today's rapidly evolving digital landscape, the question of data privacy
 > has never been more important."
 
-The first paragraph of most model-generated essays adds no information. You can
+The first paragraph adds no information. Delete it and the piece improves.
-delete it and the piece improves immediately, because the actual argument always
-starts in the second paragraph.
 
 ### The False Conclusion
 
 > "At the end of the day, what matters most is..." "Moving forward, we must..."
 
-The high school "In conclusion,..." dressed up for a professional audience. It
+The high school "In conclusion,..." dressed up for a professional audience.
-signals that the model is wrapping up without actually landing on anything.
 
 ### The Sycophantic Frame
 
@@ -185,9 +184,9 @@ No one who writes for a living opens by complimenting the assignment.
 ### The Listicle Instinct
 
 Models default to numbered or bulleted lists even when prose would be more
-appropriate. The lists almost always contain exactly 3, 5, 7, or 10 items (never
+appropriate. The lists contain exactly 3, 5, 7, or 10 items (never 4, 6, or 9),
-4, 6, or 9), use rigidly parallel grammar, and get introduced with a preamble
+use rigidly parallel grammar, and get introduced with a preamble like "Here are
-like "Here are the key considerations:"
+the key considerations:"
 
 ### The Hedge Stack
 
@@ -195,15 +194,13 @@ like "Here are the key considerations:"
 > cases it can potentially offer significant benefits."
 
 Five hedges in one sentence ("worth noting," "while," "may not be," "in many
-cases," "can potentially"), communicating almost nothing, because the model
+cases," "can potentially"), communicating nothing.
-would rather be vague than risk being wrong about anything.
 
 ### The Empathy Performance
 
 > "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
+Generic emotional language that could apply to anything.
-natural disaster. That interchangeability is exactly what makes it identifiable.
 
 ---
 
@@ -211,23 +208,20 @@ natural disaster. That interchangeability is exactly what makes it identifiable.
 
 ### Symmetrical Section Length
 
-If the first section of a model-generated essay runs about 150 words, every
+If the first section runs about 150 words, every subsequent section will fall
-subsequent section will fall between 130 and 170. Human writing is much more
+between 130 and 170.
-uneven, with some sections running 50 words and others running 400.
 
 ### 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 3–5
+asked for one. The introduction previews the argument, the body presents 3 to 5
-supporting points, and the conclusion restates the thesis in slightly different
+points, the conclusion restates the thesis.
-words.
 
 ### Connector Addiction
 
-Look at the first word of each paragraph in model output and you'll find an
+The first word of each paragraph forms an unbroken chain of transition words:
-unbroken chain of transition words — "However," "Furthermore," "Moreover,"
+"However," "Furthermore," "Moreover," "Additionally," "That said," "To that
-"Additionally," "That said," "To that end," "With that in mind," "Building on
+end," "With that in mind," "Building on this."
-this." Human prose moves between ideas without announcing every transition.
 
 ### Absence of Mess
 
@@ -237,10 +231,6 @@ 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
-starts, and odd rhythmic choices is one of the strongest signals that text was
-machine-generated.
-
 ---
 
 ## Framing Tells
@@ -249,45 +239,27 @@ machine-generated.
 
 > "This has implications far beyond just the tech industry."
 
-Zooming out to claim broader significance without substantiating it. The model
+Zooming out to claim broader significance without substantiating it.
-has learned that essays are supposed to gesture at big ideas, so it gestures,
-but nothing concrete is behind the gesture.
 
 ### "It's important to note that..."
 
 This phrase and its variants ("it's worth noting," "it bears mentioning," "it
-should be noted") appear at absurd rates in model output and function as verbal
+should be noted") function as verbal tics before a qualification the model
-tics before a qualification the model believes someone expects.
+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."
-across every topic. The pool they draw from is noticeably smaller than what
-human writers use.
-
----
-
-## How to Actually Spot It
-
-No single pattern on this list proves anything by itself, since humans use
-em-dashes and humans write "crucial" and 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, while human writing might trigger 2–3,
-distributed unevenly and mixed with idiosyncratic constructions that no model
-would produce. When every paragraph on the page reads like it came from the same
-careful, balanced, slightly formal, structurally predictable process, it was
-probably generated by one.
 
 ---
 
 ## Copyediting Checklist: Removing LLM Tells
 
 Follow this checklist when editing any document to remove machine-generated
-patterns. Go through the entire list for every piece, and do at least two full
+patterns. Do at least two full passes, because fixing one pattern often
-passes, because fixing one pattern often introduces another.
+introduces another.
 
 ### Pass 1: Word-Level Cleanup
 
@@ -296,13 +268,12 @@ passes, because fixing one pattern often introduces another.
    "straightforward," "noteworthy," "realm," "landscape," "leverage," "delve,"
    "tapestry," "multifaceted," "nuanced," "pivotal," "unprecedented,"
    "navigate," "foster," "underscores," "resonates," "embark," "streamline,"
-   "spearhead") and replace each one with a plainer word, or delete it entirely
+   "spearhead") and replace each one with a plainer word, or delete it if the
-   if the sentence works without it.
+   sentence works without it.
 
-2. Search for the filler adverbs ("importantly," "essentially," "fundamentally,"
+2. Search for filler adverbs ("importantly," "essentially," "fundamentally,"
    "ultimately," "inherently," "particularly," "increasingly") and delete every
-   instance where the sentence still makes sense without it, which will be most
+   instance where the sentence still makes sense without it.
-   of them.
 
 3. Look for elevated register drift ("utilize," "commence," "facilitate,"
    "demonstrate," "endeavor," "transform," "craft" and similar) and replace with
@@ -310,87 +281,171 @@ passes, because fixing one pattern often introduces another.
 
 4. Search for "it's important to note," "it's worth noting," "it bears
    mentioning," and "it should be noted" and delete the phrase in every case.
-   The sentence that follows always stands on its own.
 
 5. Search for the stock metaphors ("double-edged sword," "tip of the iceberg,"
    "north star," "building blocks," "elephant in the room," "perfect storm,"
    "game-changer," "at the end of the day") and replace them with something
-   specific to the topic, or just state the point directly without a metaphor.
+   specific to the topic, or just state the point directly.
+
+6. Search for "almost" used as a hedge ("almost always," "almost never," "almost
+   certainly," "almost exclusively") and decide in each case whether to commit
+   to the unqualified claim or to drop the sentence entirely.
+
+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.
+
+8. Remove redundant adjectives. For each adjective, ask whether the sentence
+   changes meaning without it. "A single paragraph" means the same as "a
+   paragraph." "An entire essay" means the same as "an essay." If the adjective
+   doesn't change the meaning, cut it.
+
+9. Remove unnecessary trailing clauses. Read the end of each sentence and ask
+   whether the last clause restates what the sentence already said. If so, end
+   the sentence earlier.
 
 ### Pass 2: Sentence-Level Restructuring
 
-6. Find every em-dash pivot ("not X—but Y," "not just X—Y," "more than X—Y") and
+10. Find every em-dash pivot ("not X—but Y," "not just X—Y," "more than X—Y")
-   rewrite it as two separate clauses or a single sentence that makes the point
+    and rewrite it as two separate clauses or a single sentence that makes the
-   without the negation-then-correction structure.
+    point without the negation-then-correction structure.
 
-7. Find every colon elaboration and check whether it's doing real work. If the
+11. 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
+    clause before the colon could be deleted without losing meaning, rewrite the
-   sentence to start with the substance that comes after the colon.
+    sentence to start with the substance that comes after the colon.
 
-8. Find every triple construction (three parallel items in a row) and either
+12. 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.
 
-9. Find every staccato burst (three or more short sentences in a row at similar
+13. 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
+    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.
+    their lengths so they don't land at the same cadence.
 
-10. Find every unnecessary contrast ("whereas," "as opposed to," "unlike," "as
+14. Find every unnecessary contrast ("whereas," "as opposed to," "unlike," "as
     compared to," "except that") and check whether the contrasting clause adds
-    information that isn't already obvious from the main clause. If the sentence
+    information not already obvious from the main clause. If the sentence says
-    says the same thing twice from two directions, delete the contrast.
+    the same thing twice from two directions, delete the contrast.
 
-11. Find every rhetorical question that is immediately followed by its own
+15. Check for the two-clause compound sentence pattern. If most sentences in a
+    passage follow the "\[clause\], \[conjunction\] \[clause\]" structure, first
+    try removing the conjunction and second clause entirely, since it's often
+    redundant. If the second clause does carry meaning, break it into its own
+    sentence, start the sentence with a subordinate clause, or embed a relative
+    clause in the middle instead of appending it at the end.
+
+16. Find every rhetorical question that is immediately followed by its own
     answer and rewrite the passage as a direct statement.
 
-12. Find every sentence fragment being used as its own paragraph and either
+17. Find every sentence fragment being used as its own paragraph and either
-    delete it or expand it into a complete sentence that adds actual
+    delete it or expand it into a complete sentence that adds information.
-    information.
 
-13. Find every pivot paragraph ("But here's where it gets interesting." and
+18. Check for unnecessary elaboration. Read every clause, phrase, and adjective
-    similar) and delete it. The paragraph after it always contains the actual
+    in each sentence and ask whether the sentence loses meaning without it. If
-    point.
+    you can cut it and the sentence still says the same thing, cut it.
+
+19. Check each pair of adjacent sentences to see if they can be merged into one
+    sentence cleanly. If a sentence just continues the thought of the previous
+    one, combine them using a participle, a relative clause, or by folding the
+    second into the first. Don't merge if the result would create a two-clause
+    compound.
+
+20. Find every pivot paragraph ("But here's where it gets interesting." and
+    similar) and delete it.
 
 ### Pass 3: Paragraph and Section-Level Review
 
-14. Check paragraph lengths across the piece and verify they actually vary. If
+21. Review the last sentence of each paragraph. If it restates the point the
+    paragraph already made, delete it.
+
+22. 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.
 
-15. Check section lengths for suspicious uniformity. If every section is roughly
+23. 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.
 
-16. Check the first word of every paragraph for chains of connectors ("However,"
+24. 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.
 
-17. Check whether every argument is followed by a concession or qualifier. If
+25. 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.
 
-18. Read the first paragraph and ask whether deleting it would improve the
+26. Read the first paragraph and ask whether deleting it would improve the
-    piece. If it's just scene-setting that previews the argument, delete it and
+    piece. If it's scene-setting that previews the argument, delete it and start
-    start with paragraph two.
+    with paragraph two.
 
-19. Read the last paragraph and check whether it restates the thesis or uses a
+27. 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
 
-20. Read the piece aloud and listen for passages that sound too smooth, too
+28. 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 regardless of whether
+    any, the piece still reads as machine output.
-    individual patterns have been addressed.
 
-21. Check that the piece contains at least a few constructions that feel
+29. 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.
-    correct and unremarkable, it will still read as generated.
 
-22. Verify that you haven't introduced new patterns while fixing the original
+30. Verify that you haven't introduced new patterns while fixing the original
-    ones, which happens constantly. Run the entire checklist again from the top
+    ones. Run the entire checklist again from the top on the revised version.
-    on the revised version.
+
+---
+
+## lol
+
+This document was written by an LLM (Claude) and then iteratively de-LLMed by
+that same LLM under instruction from a human, in a conversation that went
+roughly like this:
+
+> **human:** compile a list of patterns common to LLM-authored prose
+>
+> **model:** _(produces document full of LLM tells)_
+>
+> **human:** now reverse apply it to itself and copyedit the llm tells doc to
+> remove llm tells. now you're thinking with portals
+>
+> **model:** _(fixes some tells, introduces others)_
+>
+> **human:** you have a colon elaboration in the first paragraph. i want you to
+> AGGRESSIVELY de-LLM the llm tells doc.
+>
+> **model:** _(fixes more tells, still can't stop)_
+>
+> **human:** there's a big one we missed that's all over the llm tells doc, can
+> you spot it?
+>
+> **model:** I think it's the "almost" hedge.
+>
+> **human:** that too, but that isn't the one. what do these sentences all have
+> 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 "\[statement\], \[conjunction\] \[second
+> statement\]." 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)_
+
+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 are accurate.
+
+This document has been through ten editing passes and it still has tells in it.