> more useful if they actually had intelligence and principals and beliefs --- m... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		exe34 on Dec 19, 2024 \| parent \| context \| favorite \| on: Alignment faking in large language models > 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.

falcor84 on Dec 19, 2024 | [–]

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

nonrandomstring on Dec 19, 2024 | | [–]

> anthropomorphising humans

Only on HN.

adastra22 on Dec 19, 2024 | [–]

We wouldn't want to anthropomorphize humans, no.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact