Ask HN: Why aren’t LLMs used for email spam detection?

Of all the use cases LLMs are being pushed into, spam filtering seems like one of the most useful. Yet, I’m getting more spam in my Gmail inbox than ever (most of it AI-generated). Google just raised Google Workspace prices to account for the value “added” by Gemini, except it didn’t solve the most obvious problem that annoys everyone: spam. Am I missing something?