Small Models, Big Guardrails: PII Detection in ChatGPT
When ChatGPT asks you to approve a tool call, something has already scanned the outgoing data for usernames, addresses, and other PII — and that something is probably a small language model. This episode digs into the "guardian" class of compact models doing narrow, high-volume security work: PII-Tracer, OpenAI Privacy Filter, GLiNER2-PII, and the consistency problem that makes partial detection worse than it looks. We also untangle a name that doesn't exist, and explain why character-level boundaries matter more than parameter counts. Episode 5481 — myweirdprompts.com/n/5481 (permanent short…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.