If you read the literature on AI safety carefully (which uses the word “goal”), ... | Hacker News

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

		Timwi 6 months ago \| parent \| context \| favorite \| on: A non-anthropomorphized view of LLMs If you read the literature on AI safety carefully (which uses the word “goal”), you'll find they're not talking about LLMs either.

tdullien 6 months ago [–]

I think the Anthropic "omg blackmail" article clearly talks about both LLMs and their "goals".

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