Short Stuff
Short Stuff: Hallucination
A short one. Why fluent, confident, completely invented answers are a feature of how these systems work rather than a bug to be patched — and the two habits that catch almost all of them.
Audio for this episode is not attached yet — add an `audioUrl` to the episode file to enable playback
A short one. Why fluent, confident, completely invented answers are a feature of how these systems work rather than a bug to be patched — and the two habits that catch almost all of them.
In this episode
Why the word is wrong
"Hallucination" implies a malfunction. The model is doing exactly what it does; the mismatch is in our expectations.
The citation tell
Fabrications cluster in specifics: names, numbers, page references, dates. The prose around them stays perfect.
Two habits
Ask for sources you can open, and check the ones that would change your decision.
It is not lying. It has no model of the truth to lie about.
Mentioned
- The full written companion piece in the articles archive
- Module material on this topic in the AI Fluency programme
Beyond the Prompt publishes a new episode most weeks. Subscribe wherever you listen, or read the written edition first — both cover the same ground, at different speeds.