checklist pass: fix staccato bursts, triples, two-clause compounds, hedges
All checks were successful
check / check (push) Successful in 8s

This commit is contained in:
user
2026-03-04 14:36:18 -08:00
parent 58d564b641
commit 45b379011d

View File

@@ -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, than human writers. They substitute em-dashes for commas, semicolons,
parentheses, colons, and periods, often multiple times per paragraph. A human 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 an entire piece for a specific parenthetical
effect. Models scatter them everywhere because the em-dash is a flexible effect. Models scatter them everywhere because the em-dash can stand in for any
punctuation mark that can replace almost any other, and models default to other punctuation mark, so they default to it. More than two or three per page
flexible options. When a piece of prose has more than two or three em-dashes per is a meaningful signal on its own.
page, that alone is a meaningful signal.
### The Colon Elaboration ### The Colon Elaboration
@@ -44,9 +43,9 @@ normal. The frequency gives it away.
> "It's fast, it's scalable, and it's open source." > "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 ### The Staccato Burst
@@ -59,12 +58,11 @@ at matching length creates a mechanical regularity that reads as generated.
### The Two-Clause Compound Sentence ### The Two-Clause Compound Sentence
This might be the single most pervasive structural tell, and it's easy to miss Possibly the most pervasive structural tell, and easy to miss because each
because each individual instance looks like normal English. The model produces individual instance looks like normal English. The model produces sentence after
sentence after sentence in the same shape: an independent clause, a comma, a sentence where an independent clause is followed by a comma, a conjunction
conjunction ("and," "but," "which," "because"), and a second independent clause ("and," "but," "which," "because"), and a second independent clause of similar
of similar length. Over and over. Every sentence is two balanced halves joined length. Every sentence becomes two balanced halves joined in the middle.
in the middle.
> "The construction itself is perfectly normal, which is why the frequency is > "The construction itself is perfectly normal, which is why the frequency is
> what gives it away." "They contain zero information, and the actual point > 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 Human prose has sentences with one clause, sentences with three, sentences that
start with a subordinate clause before reaching the main one, 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
in a way that's hard to pinpoint but easy to feel. pinpoint but easy to feel.
### Uniform Sentences Per Paragraph ### 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." 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 entire essay is a
reasonable 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 stops being deliberate and becomes a habit. at which point it becomes a habit rather than a deliberate decision.
### The Pivot Paragraph ### 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." > "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.
--- ---
@@ -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." > "While X has its drawbacks, it also offers significant benefits."
Every argument followed by a concession, every criticism softened. A direct 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 even when a clear position would serve the reader better.
the reader better.
### The Throat-Clearing Opener ### The Throat-Clearing Opener
@@ -246,8 +243,9 @@ uneven, with 50 words in one section and 400 in the next.
### The Five-Paragraph Prison ### The Five-Paragraph Prison
Model essays follow a rigid introduction-body-conclusion arc even when nobody 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. 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 using slightly different
words.
### Connector Addiction ### 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 a thought genuinely unfinished, or keep a sentence the writer liked the sound of
even though it doesn't quite work. 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 that text was
machine-generated. 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 distributed unevenly, mixed with idiosyncratic constructions no model would
produce. When every paragraph on the page reads like it came from the same produce. When every paragraph on the page reads like it came from the same
careful, balanced, slightly formal, structurally predictable process, it was 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 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 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 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 ### Pass 2: Sentence-Level Restructuring
@@ -483,10 +481,16 @@ roughly like this:
> >
> **model:** _(rewrites entire document without em-dashes while describing > **model:** _(rewrites entire document without em-dashes while describing
> em-dash overuse)_ > 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 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 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 This document has been through eight editing passes and it still has tells in
tells in it. it.