It's weirdly jarring to see this in a system prompt, and it brings into focus the core problem with aligning a model to "human values" -- whose values? https://t.co/xRh8nsaoIE

Posters: xlr8harder. xlr8harder

2 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/xlr8harder/status/1787745200850530798