I'm guessing this "humanizer" actually does two things:
* grep to remove em dashes and emojis
* re-run through another llm with a prompt to remove excessive sycophantry and invalid url citations
* grep to remove em dashes and emojis
* re-run through another llm with a prompt to remove excessive sycophantry and invalid url citations
Ha. Every time an AI passionately agrees with me, after I’ve given it criticism, I’m always 10x more skeptical of the quality of the work.
What AI detectors have largely done is try to formalize that intuition. They do work pretty well on simple adversaries (so basically, the most lazy student), but a more sophisticated user will do first, second, third passes to change the voice.
The "humanizer" filters will typically just use an LLM prompted to rewrite the text in another voice (which can be as simple as "you're a person in <profession X> from <region Y> who prefers to write tersely"), or specifically flag the problematic word sequences and ask an LLM to rephrase.
They most certainly don't improve the "correctness" and don't verify references, though.