Settings

Theme

Apparently it's easy to detect LLM-generated text now

papers.ssrn.com

5 points by jcbe 4 months ago · 2 comments

Reader

jcbeOP 4 months ago

It's been my understanding since GPT-3 that tools that claim to identify LLM authorship of arbitrary text are basically unreliable.

This apparently is not true anymore: Pangram has a false positive rate below 0.5% and is robust to various adversarial techniques.

  • allears 4 months ago

    It offered a free demo, but it wanted me to subscribe first, so I declined.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection