hallucination
4 free lessons tagged hallucination across AI, Business. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
Abstention: Building a System That Can Say It Does Not Know
The most valuable behaviour an AI system can have is refusing to answer when it should not. This lesson covers calibration and why stated confidence is unreliable, selective prediction and the coverage-accuracy trade, conformal methods that give guarantees, designing abstention users accept, and measuring all of it in production.
Grounding and Detection: Catching It Before the User Does
Since a model cannot judge its own output, detection has to compare it against something external. This lesson covers grounding through retrieval and why it reduces rather than eliminates the problem, then the detection methods that work: self-consistency sampling, entailment checking against sources, claim decomposition, and chain-of-verification.
What a Hallucination Is, and Why It Happens
Hallucination is not a bug that will be patched out. This lesson covers why a next-token predictor produces confident falsehoods, the dual-axis taxonomy separating intrinsic from extrinsic and factuality from faithfulness, why fluency carries no signal about truth, and the theoretical result that the problem cannot be fully eliminated.
Governance, Risk, and Continuous Measurement
Responsible AI is a practice, not a slogan. This lesson covers the EU AI Act's four risk tiers and what each requires, model monitoring and drift detection, hallucination rates and human-in-the-loop design, guardrail KPIs, and how to run governance as a measured, auditable discipline rather than a compliance checkbox.