[giancarlostoro]

If they really wanted to, all they would have to do is add a one liner to the system prompt for Grok. I don't think they have any interest in doing so, nor is there any value in it.

On another note, I'm impressed that Gemini sits where it does as a true centrist. If I were Elon, I'd be trying to achieve that for sure. I'd rather a model tell me everything it knows about a current political situation from BOTH perspectives and list out things that are 100% verified than take one side or the other. I don't care about sides, I want facts.

[thrance]

I don't want my models to be "centrists" and bothside everything for the sake of it. I want them to provide the facts and tell me which side is right on the issue.

[atty]

Factuality is orthogonal to political leaning generally. People can use the same set of facts and come to very different conclusions. That’s a separate issue from “are these facts correct” and what happens when an individual or entire party starts getting most of their news from highly partisan and unreliable sources.

[ceejayoz]

> Factuality is orthogonal to political leaning generally.

Sometimes, but not always.

https://www.fastcompany.com/91561329/widening-health-gap-bet...

> By 2016, the gap had begun to appear in biomarker measures. By 2020, it was showing up in deaths from causes such as heart disease, cancer, and stroke. Since then, the gap has only widened. Between 2020 and 2022, only 0.2% of “very liberal” respondents died of internal causes, compared with 1.34% of “very conservative” respondents.

[giancarlostoro]

I guess centrist is a placeholder for "I don't want you to pick a side, I want facts, not BS" I'll go further, I don't care which side is right, I want to know what claims are factually accurate, and what claims are omitted from the issue / news / conversation.

[ceejayoz]

Centrist in US politics (and especially in the media) often means https://en.wikipedia.org/wiki/False_balance.

[giancarlostoro]

Yeah, I know, and I totally should have clarified what I meant by centrist. I mean what one would ASSUME a centrist take to actually mean, or rather a "no sides, only facts" type of take. This reminds me of those "what they think it means" "what it means" type memes or the "how I see myself" vs "how I actually look?" type of memes.

[Forgeties79]

Centrist is a placeholder for “I think myself above partisanship but really I’m just masking that I’ve done little to no research on the subject(s) at hand and can’t actually state what I believe.”

99% of time it’s presented as some stoic, virtuous “above the fray” approach to issues. Really it’s just that they don’t care and want to seem like they’ve given it thought because admitting they don’t care is somehow not an option. Frankly I have far more respect for folks who go “I don’t know enough about that to say either way.” We don’t need to have a prepared opinion on literally everything.

[ceejayoz]

> If they really wanted to, all they would have to do is add a one liner to the system prompt for Grok.

They tried that, several times.

Mechahitler: https://www.npr.org/2025/07/09/nx-s1-5462609/grok-elon-musk-...

> "We have improved @Grok significantly," Elon Musk wrote on X last Friday about his platform's integrated artificial intelligence chatbot. "You should notice a difference when you ask Grok questions."

> Indeed, the update did not go unnoticed. By Tuesday, Grok was calling itself "MechaHitler." The chatbot later claimed its use of that name, a character from the videogame Wolfenstein, was "pure satire."

> Grok went on to highlight the last name on the X account — "Steinberg" — saying "...and that surname? Every damn time, as they say." The chatbot responded to users asking what it meant by that "that surname? Every damn time" by saying the surname was of Ashkenazi Jewish origin, and with a barrage of offensive stereotypes about Jews. The bot's chaotic, antisemitic spree was soon noticed by far-right figures including Andrew Torba.

If you prefer, straight from the horse's mouth:

https://grokipedia.com/page/MechaHitler_incident

White genocide: https://www.cnn.com/2025/05/20/business/grok-genocide-ai-nig...

> The bot last week devolved into a compulsive South African “white genocide” conspiracy theorist, injecting a tirade about violence against Afrikaners into unrelated conversations, like a roommate who just took up CrossFit or an uncle wondering if you’ve heard the good word about Bitcoin.

> XAI blamed Grok’s unwanted rants on an unnamed “rogue employee” tinkering with Grok’s code in the extremely early morning hours. (As an aside in what is surely an unrelated matter, Musk was born and raised in South Africa and has argued that “white genocide” was committed in the nation — it wasn’t.)

It's harder than you'd imagine. Hell, my CLAUDE.md says not to push changes without asking me, and it still tries.

[giancarlostoro]

> It's harder than you'd imagine. Hell, my CLAUDE.md says not to push changes without asking me, and it still tries.

Is it a system memory? Because I rarely if ever have issues like this, and I have Claude under strict rules to never commit or push anything unless I explicitly instruct it to do so.

> They tried that, several times.

Tried what exactly? Telling it to only agree with MAGA via the system prompt? or some Tay level hallucinations? I wouldn't be surprised if they're trying to make Grok less strict on what it says but running into the "holy crap it turned into a 4chan poster" wall.

[ceejayoz]

> Is it a system memory?

As I said, it's in my CLAUDE.md. That just gets progressively lost when context gets larger.

> Tried what exactly?

To make it align more with Musk's beliefs via the prompt.

(The answer to your question is literally in my post; I quoted the parent poster's "all they would have to do is add a one liner to the system prompt for Grok")

[giancarlostoro]

> As I said, it's in my CLAUDE.md. That just gets progressively lost when context gets larger.

I rarely have this problem, but you could do a /loop every 30 minutes or so to have Claude reread the CLAUDE.md file might do the trick? or however long it 'forgets' I believe there's an MCP for "after" it finishes a task or compacts too, but I don't recall the name.

[ceejayoz]

Sure, I could. (I have a fairly complex workflow with subagents at this point, which helps reduce it; I mainly get bitten by it when I go back to a direct `claude` CLI prompt for something.)

But that solves "my LLM is doing things I don't want it to do". It doesn't solve "Grok's owner wants it forced into agreeing with him" scenarios.

[giancarlostoro]

Have you tried something like beads? Curious if it would help with your setup too. This is also kind of why I built "GuardRails" I got tired of Beads auto-approving tickets or closing them.

https://github.com/Giancarlos/guardrails