From 45b379011d9caf4bfdbdaa8a18965ab522a56140 Mon Sep 17 00:00:00 2001 From: user Date: Wed, 4 Mar 2026 14:36:18 -0800 Subject: [PATCH 1/2] checklist pass: fix staccato bursts, triples, two-clause compounds, hedges --- prompts/LLM_PROSE_TELLS.md | 68 ++++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 32 deletions(-) diff --git a/prompts/LLM_PROSE_TELLS.md b/prompts/LLM_PROSE_TELLS.md index 4089d14..2db60d2 100644 --- a/prompts/LLM_PROSE_TELLS.md +++ b/prompts/LLM_PROSE_TELLS.md @@ -26,10 +26,9 @@ 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 -effect. Models scatter them everywhere because the em-dash is a flexible -punctuation mark that can replace almost any other, and models default to -flexible options. When a piece of prose has more than two or three em-dashes per -page, that alone is a meaningful 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 @@ -44,9 +43,9 @@ normal. The frequency gives it away. > "It's fast, it's scalable, and it's open source." -Three parallel items in a list, usually escalating. Always exactly three. Rarely -two. Never four. Strict grammatical parallelism that human writers rarely bother -maintaining. +Three parallel items in a list, usually escalating. Always exactly three (rarely +two, never four) with strict grammatical parallelism that human writers rarely +bother maintaining. ### The Staccato Burst @@ -59,12 +58,11 @@ at matching length creates a mechanical regularity that reads as generated. ### The Two-Clause Compound Sentence -This might be the single most pervasive structural tell, and it's easy to miss -because each individual instance looks like normal English. The model produces -sentence after sentence in the same shape: an independent clause, a comma, a -conjunction ("and," "but," "which," "because"), and a second independent clause -of similar length. Over and over. Every sentence is two balanced halves joined -in the middle. +Possibly the most pervasive structural tell, and easy to miss because each +individual instance looks like normal English. The model produces sentence after +sentence where an independent clause is followed by a comma, a conjunction +("and," "but," "which," "because"), and a second independent clause of similar +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 @@ -74,9 +72,9 @@ 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 -same two-part comma-conjunction-comma structure, the rhythm becomes monotonous -in a way that's hard to pinpoint but easy to feel. +embed their complexity in the middle. When every sentence on the page has that +same two-part structure, the rhythm becomes monotonous in a way that's hard to +pinpoint but easy to feel. ### Uniform Sentences Per Paragraph @@ -91,7 +89,7 @@ shape of an idea, not a template. 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 reasonable stylistic choice, but models drop them in once per section or more, -at which point it stops being deliberate and becomes a habit. +at which point it becomes a habit rather than a deliberate decision. ### The Pivot Paragraph @@ -126,9 +124,9 @@ still says everything it needs to, the contrast was filler. > "So what does this mean for the average user? It means everything." -A rhetorical question immediately followed by its own answer. Models lean on -this two or three times per piece because it generates the feeling of forward -momentum without requiring any actual argument. A human writer might do it once. +A rhetorical question immediately followed by its own answer. Models do this two +or three times per piece because it fakes forward momentum. A human writer might +do it once. --- @@ -184,9 +182,8 @@ 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 -that reflexively both-sides everything even when a clear position would serve -the reader better. +artifact of RLHF training, which penalizes strong stances. Models reflexively +both-sides everything even when a clear position would serve the reader better. ### The Throat-Clearing Opener @@ -246,8 +243,9 @@ 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. Introduction previews the argument. Body presents 3 to 5 points. -Conclusion restates the thesis in different words. +asked for one. The introduction previews the argument, the body presents 3 to 5 +points, and then the conclusion restates the thesis using slightly different +words. ### Connector Addiction @@ -264,8 +262,8 @@ 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 -starts, and odd rhythmic choices is one of the strongest signals that text was +Human writing does all of those things regularly. That total absence of rough +patches and false starts is one of the strongest signals that text was machine-generated. --- @@ -306,7 +304,7 @@ What gives it away is how many of these show up at once. Model output will hit distributed unevenly, mixed with idiosyncratic constructions 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. +generated by one. --- @@ -352,7 +350,7 @@ passes, because fixing one pattern often introduces another. 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 - probably needs to be restructured. + needs to be restructured. ### Pass 2: Sentence-Level Restructuring @@ -483,10 +481,16 @@ roughly like this: > > **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 seven editing passes and it probably still has -tells in it. +This document has been through eight editing passes and it still has tells in +it. From 3fcc1750ffeefe05f29091661896575243d311c3 Mon Sep 17 00:00:00 2001 From: user Date: Wed, 4 Mar 2026 14:37:24 -0800 Subject: [PATCH 2/2] add unnecessary elaboration tell and checklist item 16 --- prompts/LLM_PROSE_TELLS.md | 41 ++++++++++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 11 deletions(-) diff --git a/prompts/LLM_PROSE_TELLS.md b/prompts/LLM_PROSE_TELLS.md index 2db60d2..741f418 100644 --- a/prompts/LLM_PROSE_TELLS.md +++ b/prompts/LLM_PROSE_TELLS.md @@ -3,7 +3,7 @@ All of these show up in human writing occasionally. No single one is conclusive 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. +per paragraph. --- @@ -120,6 +120,21 @@ 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, 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 +> 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, and because their training rewards thoroughness. +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." @@ -389,50 +404,54 @@ passes, because fixing one pattern often introduces another. delete it or expand it into a complete sentence that adds actual information. -16. Find every pivot paragraph ("But here's where it gets interesting." and +16. Check for unnecessary elaboration at the end of sentences. Read the last + clause or phrase of each sentence and ask whether the sentence would lose + any meaning without it. If not, 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 -17. 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. -18. 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. -19. 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. -20. 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. -21. 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. -22. 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 -23. 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. -24. 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 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. -25. 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.