Conversation

Notices

1. Ars Technica (arstechnica@mastodon.social)'s status on Friday, 15-Dec-2023 09:18:12 JST Ars Technica

   Do AI improvements call for something better than the Turing test?

   The Turing test focuses on the ability to chat—can we test the ability to think?

   https://arstechnica.com/ai/2023/12/do-ai-improvements-call-for-something-better-than-the-turing-test/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social

   • Shivaprem (shivaprem@mastodon.social)'s status on Friday, 15-Dec-2023 15:30:44 JST Shivaprem

     in reply to

     @arstechnica No, el test de Turing sólo mide la capacidad para confundir a un ser humano. Un ser humano que piensa es además consciente y puede comprender. La máquina puede estar programada para computar de modo que ofrezca respuestas sin tener conciencia ni comprensión.

   • Fubaroque (fubaroque@mastodon.social)'s status on Friday, 15-Dec-2023 17:07:20 JST Fubaroque

     in reply to

     @arstechnica The main problem with the Turing test is that it doesn’t specify how intelligent the person(s) who tries to make the distinction must be.

     At the moment we are trying to do this with “anybody who can run an app”, which sets a pretty low bar, I’d say.