6 Commits

Author SHA1 Message Date
user
ef08f42d84 methodical checklist pass: fix staccato bursts, triples, two-clause compounds, almost hedges, probably hedges throughout
All checks were successful
check / check (push) Successful in 11s
2026-03-04 14:35:45 -08:00
user
e09360b46d remove hedge from final line
All checks were successful
check / check (push) Successful in 6s
2026-03-04 14:31:19 -08:00
user
c4ae355189 restore em-dash in pivot section heading (it's an example)
All checks were successful
check / check (push) Successful in 6s
2026-03-04 14:29:26 -08:00
user
985c48bf19 replace semicolons with periods
All checks were successful
check / check (push) Successful in 11s
2026-03-04 14:27:50 -08:00
user
318da3666c add em-dash overuse tell, remove all em-dashes from prose, checklist now 25 items
All checks were successful
check / check (push) Successful in 11s
2026-03-04 14:24:50 -08:00
user
729fea84de update LLM prose tells: add compound sentence, almost-hedge, unnecessary contrast, lol section
All checks were successful
check / check (push) Successful in 11s
2026-03-04 14:21:22 -08:00

View File

@@ -1,8 +1,9 @@
# LLM Prose Tells
Every pattern in this document shows up in human writing occasionally. They
become diagnostic only through density. A person might use one or two across an
entire essay, but LLM output packs fifteen into a single paragraph.
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.
---
@@ -119,21 +120,6 @@ 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."
@@ -403,54 +389,50 @@ passes, because fixing one pattern often introduces another.
delete it or expand it into a complete sentence that adds actual
information.
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
16. 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
18. Check paragraph lengths across the piece and verify they actually vary. If
17. 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.
19. Check section lengths for suspicious uniformity. If every section is roughly
18. 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.
20. Check the first word of every paragraph for chains of connectors ("However,"
19. 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.
21. Check whether every argument is followed by a concession or qualifier. If
20. 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.
22. Read the first paragraph and ask whether deleting it would improve the
21. 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.
23. Read the last paragraph and check whether it restates the thesis or uses a
22. 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
24. Read the piece aloud and listen for passages that sound too smooth, too
23. 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.
25. Check that the piece contains at least a few constructions that feel
24. 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.
26. Verify that you haven't introduced new patterns while fixing the original
25. 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.