A reply questions OpenAI’s idea of using models to secure models

maier_ak · x · 2026-07-21

The reply argues that "safety-by-design" should not mean outsourcing safety to AI models themselves. It suggests that OpenAI’s approach of asking models to secure models could make for a dystopian sci-fi script rather than a robust safety strategy.

Original post →

More from AGI Musings

AGI Musings channel →