Comment by gambutin

We test different methods, in section 2, we use LLM agents to agentically identify people. We don't share any code here, but you could try with various freely available agents on yourself.

Any tool that can be used for yourself, can be used for others, which is why the researchers wouldn’t release the code/prompt.

That said, give it a few days and someone will have a proof of concept out.

I'd be interested in testing this on myself also.