[ulf-77723]

Tell me what you read and I tell you who you are. Even though it might be surprising in which detail the model might give a feedback, it‘s not so hard to do this as a human, or is it?

From my perspective the most interesting thing might be the blind spots or unexpected results. The unknown knows which brings new aha effects

[jaynetics]

It's not hard to do this as a human, at least if that human is trained in gathering and transforming written information.

What makes a huge difference here is the ease and speed. I recently did a similar analysis of my HN posts. I have hundreds of posts, and it took like 30 seconds with high quality results. Achieving this quality level would have taken me hours, and I have some relevant experience.

This certainly opens up some new possibilities - good ones like self-understanding, potentially ambiguous ones in areas such as HR, and clearly dystopian ones ...