Are You Letting AI Sneak False Facts Into Your Work?

By the end of this micro-course, you will be able to:

• Use the "Research Mode" Super-Prompt to force ChatGPT, Claude, or Gemini to label facts vs. inferences and say "[Unknown]" instead of guessing—stopping hallucinations at the source.
• Apply the Triangulation method to verify every key claim against at least two reputable sources (government sites, peer-reviewed journals) using the 4-step source-checking checklist.
• Tag findings as Confirmed, Unclear, or Likely Wrong with the 3-point system—ending every research session with three checked sources and zero made-up facts in your work.

(NOTE: Detailed Downloadable Guide PDF available. See Lesson Materials. Read Time: 14m 10s)

A video summary highlighting AI hallucination issues with examples like inventing the "Global Remote Work Institute" and citing fake sources such as the "Harvard Remote Work Centre." It points out warning signs such as overly precise figures, vague organisations, and absolute statements that suggest guessing. The workflow includes using a Research Mode prompt, cross-checking one claim against two sources, evaluating sources with a checklist, and classifying results as Confirmed, Unclear, or Likely Wrong. Demonstrates the "Bullshit Detector Test" by asking the AI the same question thrice without Research Mode to find contradictions. Concludes with the Research Mode Super-Prompt, prompting AI to report "Unknown" instead of guessing.

Downloadable Lesson Materials:

AUDIO SUMMARY

• An engaging podcast-style discussion that explores and links various topics.
• Suitable for listening during commuting, exercising, or at times when you prefer not to look at a device.

INFOGRAPHIC BRIEF

• Easily comprehensible at a single glance.
• Save it as your 'Quick Glance' reference material on your mobile device.