Hopefully_Anonymous comments on A Premature Word on AI - Less Wrong

9 Post author: Eliezer_Yudkowsky 31 May 2008 05:48PM

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

Comments (68)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Hopefully_Anonymous 01 June 2008 07:16:50PM -1 points [-]

Recoving Irrationalist. I just tried out Eliza (I tried it like most of us, years ago pre-internet). It impressed me a lot compared to modern competition-winners like jabberwocky. If entered into the same competition I think it should rightfully beat them.

However, I don't know if Eliza would fool a median 8 year old over the course of 1 hour (it's different from fooling some adults over the course of a couple minutes). My convo with Eliza (unfortunately the first 10 lines or so got erased, but it's similar to what remained):

"* What's your name? > Names don't interest me. * Names interest most humans. > That is quite interesting. * Names interest most humans. > Do you expect a different answer by repeating yourself? * I'm testing the limits of your intelligence, creativity, or programming. > Do you believe it is normal to be testing the limits of my intelligence, creativity, or programming? * I'm testing the limits of your intelligence, creativity, or programming. > Come, come, elucidate your thoughts. * I think that fhhgk dkfgh dhfkg djfjg. > Do you doubt you that fhhgk dkfgh dhfkg djfjg? * Yes, I doubt that you can discern between gibberish and real words. > We were discussing you, not me."