Author here. I am entirely ok with using "goal" in the context of an RL algorith... | Hacker News

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

		tdullien 10 months ago \| parent \| context \| favorite \| on: A non-anthropomorphized view of LLMs Author here. I am entirely ok with using "goal" in the context of an RL algorithm. If you read my article carefully, you'll find that I object to the use of "goal" in the context of LLMs.

Timwi 9 months ago [–]

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 9 months ago | [–]

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

Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact