Documented AI Incidents
Hallucinations, ghost sources, RAG failures: understand and prevent common AI agent issues.
AI Hallucinations - RAG best practices - Ghost sources - KB Drift - Chunking strategies
Articles
- 📉KB Drift
Silent Degradation in LLM Systems: Detecting When Your AI Quietly Gets Worse
Your LLM can look “green” on dashboards while leaking sensitive data, hallucinating more, or drifting off domain—long before anyone files an incident. Silent degradation is when LLM systems fail witho...
7 min1330 words - 👻Ghost Sources
Why AI Invents Sources: Inside Citation Hallucinations, Legal Risks, and How to Stop Them
Large language models (LLMs) often produce confident citations to cases, papers, and URLs that do not exist. This is not a minor glitch; it follows directly from how they are built. For lawyers, rese...
8 min1534 words
Topics Covered
AI Hallucinations
Understanding why LLMs invent information and how to prevent it.
RAG Best Practices
Retrieval Augmented Generation: architectures, chunking, optimal retrieval.
Ghost Sources
When AI cites sources that don't exist. Detection and prevention.
KB Drift
How to detect and correct knowledge base drift.
Chunking Strategies
Optimal document splitting for better retrieval.
LLM Evaluation
Metrics and methods to evaluate AI response quality.
Need a reliable KB for your AI?
CoreProse builds sourced knowledge bases that minimize hallucinations.