Detecting LLM-Generated Texts with “Classical” Machine Learning

Re:Detecting LLM-Generated Texts with “Classical” Machine Le... by arjie on Thursday July 16, 2026 @02:57PM (#48938711)

Neat. I will implement something like this for myself. I just need to reduce the spam a little. Imperfection is okay for a social network context like HN.

[ Parent | on HN ]

Re:Detecting LLM-Generated Texts with “Classical” Machine Le... by pixl97 on Thursday July 16, 2026 @03:23PM (#48939061)

It will work for a bit, but as people start speaking more like LLMs and LLMs start training using said classifiers as a GAN, it will become useless.

[ Parent | on HN ]

Re:Detecting LLM-Generated Texts with “Classical” Machine Le... by Krssst on Thursday July 16, 2026 @07:37PM (#48941699)

If we get precise detectors and LLM posts don't get shown by social networks recommendation algorithms as a result, the chances of people starting to talk like LLMs get lower.

[ Parent | on HN ]

Re:Detecting LLM-Generated Texts with “Classical” Machine Le... by cygn on Thursday July 16, 2026 @08:02PM (#48941878)

you can try my browser extension which does this for hackernews: https://slopsieve.com/extension

[ Parent | on HN ]