Vote on which of Hacker News' challenges for AI have been met

Re:Vote on which of Hacker News' challenges for AI have been... by andai on Friday October 02, 2026 @07:09AM (#49932162)

Thanks for sharing.

I think non-RLHF'd LLMs (i.e. pretrained text completion models) sound natural enough to pass the Turing test, but I don't know if anyone has tested them for that. (Also I'm not sure how to come by base models without post-training crap, even the "base" models of recent releases start spamming assistant-type text constantly, i.e. they're clearly putting it in the pretraining data.)

If I'm right on that then we hit that benchmark like five years ago.

The egg thing, probably 2030-ish.

[ Parent | on HN ]

Re:Vote on which of Hacker News' challenges for AI have been... by Kim_Bruning on Friday October 02, 2026 @09:15AM (#49933212)

Do consider the answer given by the Claude model family to be good enough?

The Claude answer is 'neutral', which is sure to anger people at either extreme of the AI debate (and does).

[ Parent | on HN ]

Re:Vote on which of Hacker News' challenges for AI have been... by lostmsu on Saturday October 03, 2026 @02:25PM (#49946534)

> non-RLHF'd LLMs sound natural enough to pass the Turing test

No, they will entirely forget things you ask them to remember in the beginning of a conversation. That requires at least an ability to compact context.

[ Parent | on HN ]