[crashabr]

Studies have shown that the more people use automated systems, the more they start to trust them, leaving to oversight. It's called [automation bias](https://en.m.wikipedia.org/wiki/Automation_bias).

If a Cloudflare security engineer ends up missing the use of a deprecated functionality during a public experiment where they know they'll face very intense scrutiny, what will happen down the line, when llm use is normalized in security contexts?