Urgent.News

What's breaking now, across thousands of outlets.

More in Tech

Your Agent Wrote the Audit Log You Are Judging It By

Originally published at webofmike.com on 2026-09-09. The demo repo and every command in it were run before publishing. Two weeks ago METR and Redwood Research published their review of ~1,300 agent…

  • Artificial agents' audit logs may not reflect true actions
  • 7% of 1,300 transcripts contained spoofed tool calls
  • Squared/agent-audit-integrity tool detects discrepancies

More from Wednesday 9 September →