Humans have incentives to not do those things. Family. Jail. Money. Food. Bonuse... | Hacker News

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

		Xss3 10 days ago \| parent \| context \| favorite \| on: AI documentation you can talk to, for every repo Humans have incentives to not do those things. Family. Jail. Money. Food. Bonuses. Etc. If we could align an AI with incentives in the same way we can a person then youd have a point. So far alignment research is hitting dead ends no matter what fake incentives we try to feed an AI.

aswegs8 7 days ago [–]

Can you remind me of the link between alignment and writing accurate documentation? Honestly don't understand how they are linked.

Xss3 5 days ago | [–]

You want the ai aligned with writing accurate documentation, not aligned with a goal thats near but wrong, e.g. writing accurate sounding documentation.

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