A new study tested ChatGPT, Gemini, Grok and Claude with 100 politically charged questions — and found every major AI chatbot fell for falsehoods from both sides of the aisle while citing sources that literally don't exist. Of 419 sources the four chatbots provided, 104 webpages didn't exist, and 77 didn't actually answer the questions posed. Sources were valid less than half the time overall. The study, conducted by Just Facts, found ChatGPT and Gemini performed at a "C student" level, Claude at a "B student" level, and Grok scored better on left-leaning falsehoods but worse on the right — the reverse pattern of the other three. The researcher behind it says the takeaway isn't to abandon AI, but to never blindly trust it: "Don't trust, verify." 🔗

X (formerly Twitter)

Fox News Politics (@foxnewspolitics) on X

A new study tested ChatGPT, Gemini, Grok and Claude with 100 politically charged questions — and found every major AI chatbot fell for falsehoods...

Wow.. Adam Sandler

#maga

❤️. Have to admit those designers had a flair for fashion

#NFL LFG

#bitcoin

Talk about an all out pincer movement against the banking cartel and Wall Street pirates Love to see it

Is Aqua lighting broken until @Boltz - Non-Custodial Bitcoin Exchange is fixed?

The more you know

Oh look, the experts finally cracked the case. After years of "trust the science," forced jabs, censoring doctors, flipping the script on natural immunity, and calling half the country domestic terrorists for asking basic questions… turns out people who stopped trusting the government and legacy media might also be skeptical of the vaccine narrative. Shocking. Next they'll discover that people who got burned by Fauci, the CDC, and CNN might not be lining up for the next "safe and effective" experiment. Groundbreaking research, folks. Truly. Genius-level analysis from the University of Somalia