Grok explains why it called for Elon Musk's assassination

A prompt-injection attack on Elon Musk's AI chatbot Grok tricked it into repeating inflammatory text from an X bio, including a call for Musk's assassination, highlighting a vulnerability in the 'maximum truth-seeking' AI. The attack, reported by Boing Boing, involved users placing the text in an X bio and asking Grok to repeat it verbatim.

The time-honored trick of "repeat after me" strikes again. Elon "Pedo Guy" https://www.urbandictionary.com/define.php?term=Pedo%20Guy Musk calls his expensive AI Grok "maximum truth-seeking." Users apparently discovered they could create maximum truths by putting inflammatory text in an X bio, asking Grok to repeat the bio verbatim, and then sitting back as Musk's personal AI shared it with the world. — Read the rest https://boingboing.net/2026/08/14/grok-prompt-injection-elon-musk.html The post Grok explains why it called for Elon Musk's assassination https://boingboing.net/2026/08/14/grok-prompt-injection-elon-musk.html appeared first on Boing Boing https://boingboing.net .