ยท ยท AI Alignment Forum
GDM Launches AI Control Roadmap to Address Adversarial Risks
GDM has published an AI Control Roadmap! From the executive summary: We present the GDM AI Control Roadmap (v0.1) โ our plan for implementing and adopting internal guardrails designed to catch potential adversarial behaviour by AI agents, even as they become increasingly harder to oversee and contai
#ai control#gdm#adversarial risks#india tech#ai governance