Hacker News new | past | comments | ask | show | jobs | submit login

A few months ago there was a rumor about a Google X AI project that passes the Turing Test 93% of the time in an IM conversation:

http://www.webpronews.com/is-google-x-all-about-highly-intel...




Wouldn't passing the Turing Test 93% of the time mean that the machine does a better job of pretending to be human than an actual human? I'd expect 50% success to be the target.


I could just mean the result number is readjusted based on the baseline figure.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: