[CobrastanJorji]

An interesting little example of this problem is initial prompting, which is effectively just a permanent, hidden context that can't be cleared. On Twitter right now, the "Grok" bot has recently begun frequently mentioning "White Genocide," which is, y'know, odd. This is almost certainly because someone recently adjusted its prompt to tell it what its views on white genocide are meant to be, which for a perfect chatbot wouldn't matter when you ask it about other topics, but it DOES matter. It's part of the context. It's gonna talk about that now.

[dragonwriter]

> This is almost certainly because someone recently adjusted its prompt to tell it what its views on white genocide are meant to be

Well, someone did something to it; whether it was training, feature boosting the way Golden Gate Claude [0] was done, adjusting the system prompt, or assuring that it's internet search for contextual information would always return material about that, or some combination of those, is neither obvious nor, if someone had a conjecture as to which one or combination it was, easily falsifiable/verifiable.

[0] https://www.anthropic.com/news/golden-gate-claude

[lolinder]

Source [0]. The examples look pretty clearly like they stuck it in the context window, not trained it in. It consistently seems to structure the replies as though the user they're replying to is the one who brought up white genocide in South Africa, and it responds the way that LLMs often respond to such topics: saying that it's controversial and giving both perspectives. That's not behavior I would expect if they had done the Golden Gate Claude method, which inserted the Golden Gate Bridge a bit more fluidly into the conversation rather than seeming to address a phantom sentence that the user supposedly said.

Also, let's be honest, in a Musk company they're going to have taking the shortest possible route to accomplishing what he wanted them to.

[0] https://www.cnn.com/2025/05/14/business/grok-ai-chatbot-repl...

[CobrastanJorji]

When your boss is a crazy, drugged-up billionaire who has ADD and also runs the government, when he tells you to do something, you do it the fast way.

[9dev]

Well, telling an AI chatbot to insist on discussing a white genocide seems like a perfectly Elon thing to do!

[M4v3R]

> This is almost certainly because someone recently adjusted its prompt to tell it what its views on white genocide are

Do you have any source on this? System prompts get leaked/extracted all the time so imagine someone would notice this

Edit: just realized you’re talking about the Grok bot, not Grok the LLM available on X or grok.com. With the bot it’s probably harder to extract its exact instructions since it only replies via tweets. For reference here’s the current Grok the LLM system prompt: https://github.com/asgeirtj/system_prompts_leaks/blob/main/g...

[lenkite]

Probably because it is now learning from a lot of videos posted on X by misc right-wingers showing rallying cries of South African politicians like Julius Malema, Paul Mashatile etc. Not very odd.

As merely 3 of over a dozen examples:

https://x.com/DefiantLs/status/1922213073957327219

https://x.com/PPC4Liberty/status/1922650016579018855

https://x.com/News24/status/1920909178236776755

[micromacrofoot]

nah, llms don't learn like this — they specifically added it to the system prompt

[stevedonovan]

Ah, Elon paying attention to hid companies again!

Context poisoning is not a uniquely LLM problem

[ezst]

The heck??

[CobrastanJorji]

Yeah, things are a little weird on Twitter these days. https://www.nbcnews.com/tech/tech-news/elon-musks-ai-chatbot...