5 points | by jcbe 14 hours ago ago
2 comments
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.
It offered a free demo, but it wanted me to subscribe first, so I declined.
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.
It offered a free demo, but it wanted me to subscribe first, so I declined.