sneak/prompts
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

restore example quotes
All checks were successful
check / check (push) Successful in 5s
Details

Browse Source
This commit is contained in:
user
2026-03-04 14:52:23 -08:00
parent 6438ed22d3
commit 1c70757fb9
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
prompts/LLM_PROSE_TELLS.md
View File

@@ -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 essay, but LLM
> output will use fifteen of them per paragraph, consistently, throughout the
> entire piece."
> "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
@@ -493,9 +493,9 @@ roughly like this:
>
> **human:** the dramatic fragment paragraph has a tell in it
>
> **model:** "One of these in an essay is a stylistic choice. One per section is
> a tic." Two-clause parallel structure with the same shape, and also a staccato
> pair.
> **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