News for hackers. Stuff that matters.

A comment on Alignment faking in large language models. Parent comment

Re:Alignment faking in large language models by exe34 on Thursday December 19, 2024 @03:52AM (#42459645)
> more useful if they actually had intelligence and principals and beliefs --- more like people.

that's a nice bit of anthropomorphising humans, but it's not how humans work.

[ Parent | on HN ]
Re:Alignment faking in large language models by falcor84 on Thursday December 19, 2024 @04:35AM (#42459896)
This is the first time I ever saw the lovely phrase "anthropomorphising humans" and I want to thank you for giving me the first of my six impossible things before breakfast today
[ Parent | on HN ]
Re:Alignment faking in large language models by nonrandomstring on Thursday December 19, 2024 @04:36AM (#42459907)
> anthropomorphising humans

Only on HN.

[ Parent | on HN ]
Re:Alignment faking in large language models by adastra22 on Thursday December 19, 2024 @10:03AM (#42462023)
We wouldn't want to anthropomorphize humans, no.
[ Parent | on HN ]