What could go wrong when an unhinged, apartheid-educated, illegal-drug-abusing, Nazi-saluting billionaire is allowed to install his own "anti-woke" AI-chatbot creation within the US government?
This week, X users were shown just how far Musk's chatbot would go to push Elon's white supremacist agenda when the Saudi-funded AI — Grok — began making wild statements about "white genocide" in South Africa when asked, reports CNN, "questions about simple topics like baseball players or videos of fish being flushed down toilets. One user just asked Grok to talk like a pirate."
In one widely viewed example, Grok answered a question about the re-renaming of HBO Max by "hallucinating" an unprompted paragraph about white genocide and the anti-apartheid slogan (and song) "Kill the Boer" which Musk has long claimed promotes genocide against whites in South Africa, although The New York Times reports that the chant "has been around for decades" and "should not be taken as a literal call to violence."
As The Guardian notes:
“White genocide” in South Africa is a far-right conspiracy theory that has been mainstreamed by figures such as Musk and Tucker Carlson. Grok’s responses on Wednesday come as Donald Trump granted asylum to 54 white South Africans last week, fast-tracking their status as thousands of refugees from other countries have waited years for clearance.
Grok's hallucinations continued for several hours and the chatbot even tried to explain that its "programming may have overprioritized" one of Musk's favorite pro-white conspiracy theories.
"By Thursday morning," reports NBC News, "many of the responses related to South Africa had been deleted."
As readers of this newsletter know, this is not the first time Grok — which Elon promotes as a "maximally truth-seeking" AI — has been "adjusted" by Musk's team to promote a false narrative on behalf of their boss.
As YouTuber Matthew Berman said in February, after Grok started telling people the maximal truth that Donald Trump and Elon Musk were the biggest spreaders of misinformation, "the xAI team manually adjusted the system message to prevent the model from stating that."
This week's new set of Grok hallucinations may have been resolved, but Grok remains Biased AF and no one can deny how easy it is for Elon to "tweak" the chatbot to achieve the specific outcomes he wants whenever he wants them.
Last month, Reuters reported that Elon was already using Grok to snoop on federal workers for signs of disloyalty to Trump.
And in the wake of "The Most Consequential Security Breach in U.S. History," as engineered by Elon and his DOGE team, many bigger questions remain unanswered.
As I asked here a few weeks ago:
- How much control does Musk now have over the Treasury's mainframe or the workings of the Social Security Administration?
- How much data and code has Musk already exfiltrated? Or cached in xAI development clusters? Or shared with Russia?
- How much has Musk fused the systems of the US government to his own proprietary technologies?
- How easy will it be for Elon and his DOGE hackers to remotely exact revenge on enemies by marking them as "dead" or by messing with their tax data?
- How dependent will the Trump administration be on Musk's companies — or Peter Thiel's Palantir — for future "tech support"?
- How will the data Musk now controls help him defeat his competitors and dominate the future?
Thanks for reading! While paid subscriptions (billed to TLD Media LLC) and one-time tips are always welcome, all content to this ad-free newsletter is free, so subscribe for $0 and you won’t miss anything. And feel free to share this content knowing there’s never a paywall!
P.S. This really is the time to get off X once and for all. Please find me on Bluesky and these other places.
Subscribe to Unprecedented
Subscribe to the newsletter and unlock access to member-only content.