PEGHIN
Joined 1 year ago
Karma
2
Submissions
37
Member since
Aug 9
Recent submissions
Comment · 5 months ago
Agent infrastructure requires runtime policy enforcement, not just model-level guardrails. Deterministic controls at the system boundary prevent policy violations regardless of model behavior
Check the post: https://www.supra-wall.com/blog/llm-as-judge-fails-agent-sec...
Comment · 6 months ago
Yes, because we've built them to be flexible. The fix requires treating agents like any other service: least privilege, API quotas, audit logs, separate validation layer. Not guardrails—governance.
Comment · 6 months ago
Exactly. Today's agents inherit LLM semantics (ambiguous, probabilistic, interpretable). Real solution: agents operate in ACL model (access control lists) tied to execution user, not prompt understanding. https://www.supra-wall.com/en/blog/llm-as-judge-fails-agent-...