How does cross-model consensus reduce AI hallucination, and can you prove which models agreed?

Cross-model consensus reduces AI hallucination by requiring several independent models to agree before a high-risk action proceeds, since they rarely invent the same falsehood. In a SIOS each vote and disagreement is written to a post-quantum signed ledger, so you can prove which models agreed.Originally published at https://mickai.co.uk/articles/cross-model-consensus-you-can-prove-sealed-multi-model-agreement. Mickai is a Sovereign Intelligence Operating System; the Open Audit Record signs every artificial intelligence action before it executes, post-quantum and offline-verifiable. 104 filed UK patent applications, Mickai LTD (Companies House 17166618).