The Ideological Turing Test


Over at Popehat they presented an interesting article about the Ideological Turing Test. The regular Turing Test says that a computer passes if you can interact with it and you don’t know you’re interacting with a computer instead of a human. One of the closest things we have right now are the chat bots whose eventual goal is to get you to some website. Well, the Ideological Turing Test tests:

whether a political or ideological partisan correctly understands the arguments of his or her intellectual adversaries: the partisan is invited to answer questions or write an essay posing as his opposite number. If neutral judges cannot tell the difference between the partisan’s answers and the answers of the opposite number, the candidate is judged to correctly understand the opposing side.

It came about because:

response to Paul Krugman’s claim that, in the context of US politics, liberals understand conservatives (and libertarians) better than conservatives (and libertarians) understand liberals. Borrowing the idea of the Turing test used to judge whether machines can pass themselves off as human, Caplan suggested the ideological Turing test as a way to impartially test Krugman’s claim: whichever side understands the other better would perform better on an ideological Turing test.

I think it’s a pretty neat idea. I don’t think it would work with politicians because they are usually purposely trying to obscure and lie about the other side so that they don’t have to actually defend their positions. What I wonder is whether the Ideological Turing Test is setup correctly, however. It involves a neutral party judging whether the liberal is doing a good job being a conservative and vice versa. However, I think that may lend itself too easily to Straw Man Arguments, where the person exaggerates the position of the other side to make it easier to refute them. Both sides might be able to succeed with caricatures of the other. What I think is a MUCH better Ideological Turing Test is to have liberals judge whether the conservatives were correct and conservatives judge whether the liberals are correct. Of course, in order to make it a fair evaluation you’d have to have a mix of real and imposter articles so that the judge wouldn’t score the opposition incorrectly out of spite. At any rate, I think this could actually be a fun game or competition. I would surely enjoy reading the results of a competition in which people tried to show how well they understood the other’s position. As a bonus, I wonder if putting oneself in the fame of mind of the enemy in order to understand what they believe would not also engender a true understanding of how they feel and might lead to people realizing the other side usually isn’t actually evil or dumb.