Talk:Reverse Turing test
Template:WikiProject banner shell
I think the link to CAPTCHA should be more prominent. I came to this article thinking that it was about CAPTCHAs. But I didn't see anything about them so I almost concluded nobody had written anything about them yet. Or am I the only person who thinks 'Reverse Turing test' when I see a CAPTCHA in a registration form (since I had never heard of the word CAPTCHA before)? —TylerRick
Computer success means human failure in Turing test
If a human being is judged to be a computer, then presumably the computer was judged to be the human, meaning the computer passed. So if the computer passed, the human failed. Am I missing something? - Keith D. Tyler ¶ (AMA) 21:23, 20 March 2007 (UTC)
- Yes. The Turing test (as currently performed) is rarely done on a 1:1 ratio as you described. So there is the possibility of multiple winners. -- trlkly 12:35, 16 January 2008 (UTC)
This article neeeds more work
It needs more work see the wikipidia articles about how to do this ilija.milcinoski —Preceding unsigned comment added by Ilija.milcinoski (talk • contribs) 11:22, 6 August 2010 (UTC)
Verifying that a strong AI isn't a hoax?
Would you use this article's name for a hypothetical case where someone claims to have created an AI as intelligent as a human, and its IM/email conversation is humanlike enough that the main issue becomes verifying that there isn't secretly an actual human at the other end? I'm not sure how you'd even do that -- maybe look at "typing" speed? --Shay Guy (talk) 23:08, 6 July 2012 (UTC)
Definition(s)
It seem to me there's more than one. E.g. Script error: No such module "citation/CS1". says "Certainly, humans would fail a “reverse Turing test” of emulating computer programs – humans can't even emulate pocket calculators without unreasonably long response delays." 188.27.81.64 (talk) 18:43, 21 June 2014 (UTC)
On the other hand, the def used commonly for CAPTCHA-style problems is more involved. E.g. the paper "Pessimal Print: A Reverse Turing Test" by Allison L. Coates, Henry S. Baird, and Richard J. Fateman cites the following definition (from Blum et al.):
- the test’s challenges can be automatically generated;
- the test can be taken quickly by human users;
- the test will accept virtually all human users (even young or naive users) with high reliability while rejecting very few;
- the test will reject virtually all machine users; and
- the test will resist automatic attack for many years even as technology advances and even if the test’s algorithms are known (e.g. published and/or released as open source).
188.27.81.64 (talk) 18:50, 21 June 2014 (UTC)
External links modified
Hello fellow Wikipedians,
I have just added archive links to one external link on Reverse Turing test. Please take a moment to review my edit. If necessary, add Template:Tlx after the link to keep me from modifying it. Alternatively, you can add Template:Tlx to keep me off the page altogether. I made the following changes:
When you have finished reviewing my changes, please set the checked parameter below to true to let others know.
Cheers.—cyberbot IITalk to my owner:Online 02:58, 10 February 2016 (UTC)