Anti-hallucination research skill for Claude Code — admits uncertainty, extracts direct quotes before analysis, cites every claim, retracts unverifiable statements. Based on Anthropic's official guardrail techniques. By TheGEOLab.net

About Essays, and Poc on using runtime evidence to build cleaner code context for AI to reduce hallucinations.

Why Pure Vector Search is a "False Proposition" for RAG?

Hallucination-prune multiagent RAG for pharmaceutical knowledge bases

Dependency-free evidence core for AI agents: observation envelopes, provenance, memory continuity and claim gates to reduce hallucination drift.

Autonomous AI research agent using LangGraph to eliminate LLM hallucinations via a Generate-Critique-Refine self-reflection loop.

Developer-first prompt engineering patterns for grounded, testable, and reliable AI outputs.

LLM orchestrates SymPy for exact computation neuro-symbolic pipeline that routes math to symbolic solver, reducing hallucination on engineering problems.

BioReasoner: Training LLMs for grounded scientific reasoning. 0% hallucination rate on citations, 100% format adherence. Cross-domain polymathic insights via Scientific Tribunal evaluation.

Self-healing RAG system that retrieves, verifies, and grades its own answers. Automatically rewrites queries and retries when outputs are weak, ensuring accurate, hallucination-free responses.

A conceptual AI architecture for reducing hallucinations by enforcing invariant, source-anchored knowledge constraints during generation.

Prompt engineering framework + evaluation harness for LLM workflows (classification, summarization, extraction).

Professional cross-agent answer quality gate for improving AI responses: intent match, evidence, assumptions, verification, brevity, and usefulness.

A hallucination-resistant Retrieval-Augmented Generation (RAG) system.

A pipeline that gives probabilistic guarantees for reducing contextual hallucinations in LLMs

A RAG system that knows when not to answer using concentration inequalities

An RLHF-inspired DPO framework that explicitly teaches LLMs when to refuse, significantly reducing hallucinations.

Policy-constrained LoRA fine-tuning to reduce hallucinations in a billing-focused LLM, using a PayFlow (fictional SaaS) use case with before–after evaluation.

Runtime patch that kills LLM loops, drift & hallucinations in real-time – works with any model (GPT, Grok, Claude, Llama, Mistral…)

Structured memory system and behavioral guardrails for AI agents. Reduce hallucinations, preserve technical decisions, and enforce Explore→Execution workflow boundaries during vibe-coding with OpenCode / Claude Code.