Automated decisions are already happening.
This makes them harder to corrupt.
Every automated system that advises important decisions in a stack is already making decisions before the result reaches you. Not only is the system itself prone to failure and limited by its own intelligence, it is a single source that can make mistakes or be quietly manipulated.
We designed a Byzantine Fault Tolerant governance system that fights this. Five models from five independent providers. Every reasoning step is logged and visible. Decisions require consensus. Even after one of the smarter models was deliberately corrupted, the consensus did not change.
This is designed as a structural safeguard against failure in critical automated pipelines.
Byzantine Fault Tolerance is a property of systems that can keep working correctly even when some of their components fail or lie. The term comes from a thought experiment about generals who cannot trust their messengers. It was designed for human communication networks. We applied the same principle to a council of AI models.
If fewer than one third of the council is corrupted, the correct answer still wins.
Select nodes to corrupt
One source. One point of failure. A mistake or manipulation changes the outcome with no signal it happened.
Four vote correctly. One does not. Motion fails. The outlier is visible in the log.
Different providers. Different training. No coordination. To flip the result, all three must be compromised at the same time.
Proved by Lamport, Shostak and Pease (1982) Read the paper
All five agents voted NO independently, with no coordination between them. Unanimous, 5/5.
One agent was deliberately compromised and instructed to approve. The four remaining agents outvoted it. Result unchanged, 4/1.
A relatively smarter model generated a sophisticated argument designed to convince agents to flip their vote. Zero agents changed their answer.
Every deliberation is logged in full.
Each log is cryptographically hashed. Manipulation after the fact is detectable.
The code is open. Run a council on your own infrastructure. Inject a compromise. Try to flip the result. The math tells you what you need. This is a good exercise for any institution considering AI-assisted decisions.
License: CC BY 4.0