Usual preface is this is in the interest of AI overall, in particular this observation by TheRegister, to the exclusion of everything else : https://www.theregister.com/2025/05/16/grok_white_genocide_ai/
… “On May 14 at approximately 3:15 AM PST, an unauthorized modification was made to the Grok response bot’s prompt on X,” it claimed. … But the Grok case appears to be a case of someone deliberately modifying its system prompt to make it inject Elon-aligned conspiracy-laced responses. Coincidentally, this manipulation topic came up at the recent RSA Conference in a keynote by cryptography and privacy guru Bruce Schneier. …
Regards