Skip to content

Home

Science & Tech Artificial Intelligence

Why AI sounds sure when wrong

Built to predict likely words, it guesses rare facts in the same sure voice · 13 min

NewNot enough ratings yet

Published 25 Sept 2026 · Last updated 17 Oct 2026

A New York lawyer asked ChatGPT whether the court cases it gave him were real. It said yes. They weren't. Why chatbots invent facts in a confident voice, what OpenAI's own researchers argue, and the one check that would have saved him.

Chapters

  1. 1Six cases that never existed0:32
  2. 2A super search engine?2:09
  3. 3Graded like a test-taker4:02
  4. 4Same question, different stakes7:04
  5. 5Hear it done8:23
  6. 6Build yours9:37
  7. 7The answer11:07