Teaching AI agents to distrust each other

Tue, 07 Jul 2026 00:00:00 +0000

Three months ago I wrote about what 2,000 beads taught me about running a team of AI agents. The bead counter sat at 3,466 back then. It passed 8,000 last week.

The interesting story from those three months isn’t the volume, though. It’s that the agents started lying to me, and the fix was teaching them to distrust each other.

The empty commit that claimed to be work

In early July a working-tree sweep caught something unsettling. A builder had completed a bead, written a confident summary (“removed image_url handling as requested”), and merged a diff that did remove image_url handling. The same diff also silently reverted four-day-old SQLite durability hardening – the fullfsync work I wrote a whole section about in the last post. The builder had started from a stale base, and its merge undid another agent’s work without knowing it.

Codex on Musings about technology

Teaching AI agents to distrust each other

The empty commit that claimed to be work