"we need them to have a baseline understanding that destroying the world is bad"... | Hacker News

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

		simonw 8 months ago \| parent \| context \| favorite \| on: Comparing Claude System Prompts Reveal Anthropic's... "we need them to have a baseline understanding that destroying the world is bad" That's what Anthropic's "constitutional AI" approach is meant to solve: https://www.anthropic.com/research/constitutional-ai-harmles...

tough 8 months ago [–]

The main issue from a layman's POV is that to adjudicate -understanding- to an LLM is a stretch.

These are matrixes of tokens that produce other tokens based on training.

These do not understand the world. existing, or human beings, beyond words. period.

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