I fact-checked ChatGPT with Bard, Claude, and Copilot - and this AI was the most confidently incorrect

Summary

1. The experiment’s results varied greatly between chatbots.
2. Many of the responses looked impressive, but were often completely or partially wrong.
3. The article’s author recommends always doing your own fact-checking.

References

• Media Check: ZDNet - Media Bias Fact Check (HIGH CREDIBILITY)
• Collections | The Runway (airforce.gov.au)
• ADDITIONAL READING RAAF RUNWAY (PME)
• RAAF RUNWAY: RATIONALE, GUIDELINES, LEARNING OUTCOMES, ETC.