I asked 6 popular AIs these trick questions, and it was a game of hallucination roulette
ID: ad5d4eee-35d9-59b0-b817-8de3e2bebfaf
STIX ID: report--ad5d4eee-35d9-59b0-b817-8de3e2bebfaf
Feed Name: ZDNet Security
**ZDNET** evaluates free versions of ChatGPT, Google Gemini, Microsoft Copilot, Claude, Meta AI, and Grok using six tests (author bibliography, letter counting in 'strawberry', Marvel’s Toro, the fabricated Varghese v. China Southern Airlines case, and two image identifications), finding mixed accuracy with recurring hallucinations (e.g., invented book titles, false legal details, and misidentified images) but overall improvement; the takeaway is to verify AI answers and cross-check facts.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.