4 Commits
Author SHA1 Message Date
sneak 7eae7dcc6c Merge pull request 'LLM prose tells: fix first paragraph' (#10) from llm-prose-tells-final into main
check / check (push) Successful in 5s
Reviewed-on: #10
2026-03-04 23:47:00 +01:00
user 6401aa482f trim first paragraph
check / check (push) Successful in 11s
2026-03-04 14:45:16 -08:00
user e45ffacd80 restructure first paragraph
check / check (push) Successful in 5s
2026-03-04 14:43:16 -08:00
user c8ad5762ab rewrite first paragraph, add unnecessary elaboration tell
check / check (push) Successful in 3s
2026-03-04 14:42:15 -08:00
+2 -4
View File
@@ -1,9 +1,7 @@
# LLM Prose Tells
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.
Human writers occasionally use every pattern in this document. The reason they
work as tells is that LLM output packs fifteen of them into a paragraph.
---