Goalposts

Hacker News has set AI a lot of challenges over the years. Which ones has it met?

2022 Junenradov

About whether language models fooling some people means they are close to passing the Turing test.

A minority of the population will always be gullible and easily fooled. So what. Some people were already fooled by the original ELIZA program back in 1966. I would only count a Turing test pass if it can convince a jury of multiple educated examiners after a conversation lasting several hours.

An AI convinces a jury of multiple educated examiners that it is human after a conversation lasting several hours.

Has this happened?

Yes 24 (21%)Not sure 29 (25%)No 64 (55%)

Votes cast 1–2 October 2026: 100,590 votes from 9,694 people.