Ishu Agrawal

Localized reading

Oznaczanie odpowiedzi na X napisanych przez AI

Original post / EN

I used Jev to flag AI replies on X. I defined common AI-writing signals as the positive criteria for a Noul question that returns the probability of whether a reply is machine-generated. Things like a "not X, but Y" phrasing or an explanatory framing. And a Chrome extension