We focus a lot of policy on the AI models that are already released, but what about the AI models waiting internally in the wings? Our new paper explores risks from internal AI systems.
Oscar Delaney
Oscar Delaney21.7. klo 23.24
1/ The most powerful AIs aren't public. For months, labs run highly capable internal models before release. @ashwinkacharya and I wrote a new @IAPS report, “Managing Risks from Internal AI Systems,” exploring the hidden dangers this creates. 🧵
2,13K