OpenAI model for masking personally identifiable information (PII) in text

Re:OpenAI model for masking personally identifiable informat... by flashdesk on Sunday April 26, 2026 @02:12AM (#47907820)

This is where stochastic approaches start to feel a bit uncomfortable.

Even small mistakes can make something dealing with sensitive data hard to trust. It seems useful as a first pass, but I’d probably still want some deterministic checks or a human in the loop to feel confident using it.

[ Parent | on HN ]

Re:OpenAI model for masking personally identifiable informat... by fathermarz on Sunday April 26, 2026 @02:18AM (#47907849)

I built a community tool for exactly this, based on privacy first principals but around the what. It’s workflow based and not “put your sensitive data into ChatGPT and hope it captures the right stuff”. Mostly built for security folks but anyone can use it

Check it out: https://redact.cabreza.com

[ Parent | on HN ]