RobinZ comments on Come up with better Turing Tests - Less Wrong

13 Post author: Stuart_Armstrong 10 June 2014 10:47AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (44)

You are viewing a single comment's thread. Show more comments above.

Comment author: RobinZ 10 June 2014 06:18:02PM 2 points [-]

Hmm ... that and a la shminux's xkcd link gives me an idea for a test protocol: instead of having the judges interrogate subjects, the judges give each pair of subjects a discussion topic a la Omegle's "spy" mode:

Spy mode gives you and a stranger a random question to discuss. The question is submitted by a third stranger who can watch the conversation, but can't join in.

...and the subjects have a set period of time they are permitted to talk about it. At the end of that time, the judge rates the interesting-ness of each subject's contribution, and each subject rates their partner. The ratings of confirmed-human subjects would be a basis for evaluating the judges, I presume (although you would probably want a trusted panel of experts to confirm this by inspection of live results), and any subjects who get high ratings out of the unconfirmed pool would be selected for further consideration.