I Built a Hate Speech Detector That Actually Knows the Difference Between Offensive and Hateful

Article automatically generated from technical news.

Most hate speech models get this wrong: they treat "this movie sucked ass" and "heil hitler" as the same category. They're not. One is someone venting. The other is an ideological statement. Conflating them makes content moderation either useless (too permissive) or annoying (bans people for swearing). So when I built AuricErgeson/hate-speech-detector, I started with that distinction as a hard requirement. Three classes, not two The model outputs neither, offensive, or