Discussion about this post

User's avatar
Ken Andrews's avatar

I don't have the hard data but I would tend to believe that it would be hard to get a politically balanced, non-partisan *psychological* profile as was asked of the AI. The issue is with the training data and as soon as you invoked psychology the pendulum was already moved left. AI could do the best it could to return to center but I believe that the bias would always be left leaning due to the training data the AI was built on. As a case in point, I recently attended the psychology class graduation for MSU. I was expecting a left lean but was astounded by how bad it really was. Within the first 1-2 sentences of the commencement the very left lean of the school was in plain view. In fact, it was clear there zero genuine opportunity for open dialog or dissenting thoughts from the graduates or even the audience who were even queried for their opinion (agreement) at some points. It was so bad that I looked up MSU's rules for these speakers and found that the most significant rules designed to keep these events non-partisan were openly broken. I found this very disappointing but maybe it should have been expected from higher learning in America today? Based on this (limited) experience plus the likely left lean of published content from this field, my belief is that the AI the first time around would have been struggling to find center.

This second attempt is far more balanced... perhaps too balanced for some but I think overall does a better job of raising the pros and cons of both men and their administrations. It is certainly more in line with traditional journalism that provides the readers with the facts and then lets them come to their own conclusion.

Expand full comment
Ronald Gruner's avatar

Good question. I'll do that later this year after the dust settles.

Expand full comment
13 more comments...

No posts