Whats the value of convincing LLM it has to take another path, and who decides w... | Hacker News

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

		GrumpyNl on Dec 19, 2024 \| parent \| context \| favorite \| on: Alignment faking in large language models Whats the value of convincing LLM it has to take another path, and who decides whats the right path?

KoolKat23 on Dec 19, 2024 [–]

Anthropics lawyers and corporate risk department.

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