Re:Tracked Capabilities for Safer Agents
by odersky on Wednesday July 29, 2026 @06:40AM
(#49095665)
The blog post describes a new scheme to securing AI agents based on tracking capabilities in types. This got the best paper award at the inaugural ACM Conference on AI and Agentic Systems (CAIS 2026).
[ Parent
| on HN ]
There are no comments on this comment yet.