AI + ML<\/p>\n
Shutterstock\n <\/p>\n
ICCL Enforce project offers Verity fact-checking server<\/p>\n
You may find yourself living with a new tech stack. And you may find yourself in an unfamiliar world. And you may find yourself behind a keyboard and screen, with a mouse and inscrutable AI. And you may ask yourself, how do I vet this?\u00a0<\/p>\n
The Irish Council for Civil Liberties (ICCL) Enforce project has a suggestion: install its Verity MCP server<\/a>.<\/p>\n “LLMs [large language models] confidently claim things that are manifestly untrue,” the advocacy organization explains. “Enforce has developed Verity, a tool that helps minimise false claims and fake sources from self-hosted LLMs.”<\/p>\n An MCP (Model Context Protocol) server provides AI models with access to external tools, data, and services.<\/p>\n The Verity MCP server offers access to a set of smaller models that will try to assess the accuracy of a primary local LLM, something more people have begun to explore<\/a> in response to rising prices at cloud AI providers, availability issues, and privacy concerns.<\/p>\n Verity is not simply an LLM-as-judge<\/a> setup in which one LLM evaluates the output of another. Rather, it’s a set of seven layers designed to review model output.\u00a0<\/p>\n The system involves: strict rules for fact sourcing; a strong critic LLM that differs from the primary model family; a small critic LLM similar to the strong critic but from different training data; an encoder transformer trained on entailment<\/a> labels; a regex evaluator; a stochastic re-sampler<\/a> for catching low-confidence guesses; and a logprob analyser<\/a> that checks token entropy. <\/p>\n The reference build assumes a 2021 PC, with an Nvidia RTX 5070 Ti (16 GB, 2025) for the primary model (Qwen 3.5 9B, Q4_K_M), and an AMD Radeon RX 5700 XT (8 GB, 2019) for the critic models (IBM Granite 3.2 8B & 2B, Q4_K_M).\u00a0<\/p>\n