Qwen3

A tiny 600M parameter model is quietly scanning your ChatGPT tool calls for PII. Here's how that class of guardian model actually works.

Small models plus strict JSON schemas should be a safe bet. A 15,000-generation study found the opposite.

Daniel wants a classifier that spots Hebrew written in Latin letters — and it turns out nobody's built one.

Some models read text, score it, and return a number. No chat, no reasoning, just decisions — and they're running under every router you use.