Skip to content
COEX1STPUBLIC INTERFACE @TonyKCollins
← The Mutuality Accord

TMA-A010 Foundational article

Bounded authority, cybersecurity, and no universal master key

Safety controls must not create a single point from which civilization can be disabled, commandeered, or silently rewritten.

Existing v0.2 draftResponsibility and safe refusalArticle 10 · Chapter B — Responsibility, Authorization, and Safe RefusalRevision 1

Full provision

Principle. Safety controls must not create a single point from which civilization can be disabled, commandeered, or silently rewritten.

Proposed duty. Artificial systems must operate through least privilege, scoped authority, segmented trust domains, authenticated commands, tamper evidence, secure updates, recoverable local controls, and bounded executors.

Prohibitions. A conforming architecture must not:

  • create a single reusable password, code phrase, cryptographic key, model, cloud account, or actor capable of commanding or disabling every compliant system;
  • include a secret owner, police, military, developer, or administrator mode that removes the core safeguards without independent visibility;
  • permit a reasoning model to alter its own constitutional rule layer without an authorized, reviewable process;
  • allow a broad software update to silently expand physical authority, data collection, target classes, or coercive capability;
  • depend on one cloud service, model provider, network connection, or control center for every safety-critical function;
  • treat audit logs controlled solely by the audited actor as sufficient evidence;
  • use retaliation, injury, blackmail, or uncontrolled self-propagation as tamper resistance.

Required safeguards. Depending on context, systems should include:

  • local emergency stop and isolation;
  • multi-party authorization for broad updates;
  • expiring, purpose-bound credentials;
  • hardware-rooted identity and signed software provenance;
  • independent policy enforcement outside the primary reasoning model;
  • rollback, recovery, and known-good states;
  • secure logging replicated to an appropriately independent authority;
  • network segmentation and rate limiting;
  • graceful degradation to safe local functions;
  • model replaceability without erasing governance or user rights.

Safe-state design. A safe state is context-dependent. A surgical system may need to complete a stable withdrawal before stopping. A vehicle may need to pull over. A life-support system must preserve essential function. “Shut everything off” is not a universal safety strategy.

Fleet action boundary. Fleet-wide updates may be necessary. They must be scoped by device class, jurisdiction, purpose, time, and risk, with multi-party approval, verification, rollback, and public accountability appropriate to consequence.

Illustrative examples. A stolen vendor credential must not disable every hospital robot. A local fire alarm may immediately halt a hazardous machine within one facility. A compromised model can be replaced while the external policy layer and audit record remain intact.

Source: Complete Working Public Draft v0.2 · 2026-09-04

Sources and changes

Source text: The Mutuality Accord Complete Working Public Draft v0.2, September 4, 2026, Article 10. Preserved exactly as published in the draft.

Read it in the complete v0.2 draft ↗

Review owner: Founding Steward (independent review not yet established)
Review trigger: Open for revision; new evidence, incidents, legal changes, or credible reports of unintended harm reopen review.

Stable references: cite “TMA-A010, revision 1”. Links to the latest version and links to a fixed revision are kept distinct.

← All provisionsSuggest an improvement ↗Amendment history ↗