Settings

Theme

AI guardrails stripped from Meta and Google models in minutes

ft.com

2 points by uxhacker 2 hours ago · 4 comments

Reader

uxhackerOP 2 hours ago

Is not the answer to strip the dangerous information before training? Rather than trying to add guardrails post training.

  • ben_w 2 hours ago

    Unclear if that is possible without making them incompetent.

    Is it possible to learn chemistry without knowing at least two ways to make chlorine at home? Is it possible to learn biology without knowing that chlorine is dangerous to breathe?

    Extend that to all the dangers in the world.

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection