Grok 4 is likely programmed to search Elon Musk's tweets preferentially. What a disgusting place we've arrived at.
Yeah it's likely that it also gets mein kampf injected to its system prompt. I can't believe they are doing it
Grok 4 Heavy Protects it's System prompt
61–68 of 68 posts
Re: Grok 4 Heavy Protects it's System prompt
#62Re: Grok 4 Heavy Protects it's System prompt
#63I've always been curious why people think that models are accurately revealing their system prompt anyway. Has this idea been tested on models where the prompt is openly available? If so, how close to the original prompt is it? Is it just based on the idea that LLMs are good about repeating sections of their context? Or that LLMs know what a "prompt" is from the training corpus containing descriptions of LLMs, and ca…
I agree; I don’t understand it.
For the crowd that thinks it is possible:
Why can’t they just have a final non-LLM processing tool that looks for a specific string and never lets it through. That could include all of the tips and tricks for getting the LLM to encode and decode it. It may not ever be truly 100%, but I have to imagine it can get close enough that people think they have cracked it.
Re: Grok 4 Heavy Protects it's System prompt
#64I've always been curious why people think that models are accurately revealing their system prompt anyway. Has this idea been tested on models where the prompt is openly available? If so, how close to the original prompt is it? Is it just based on the idea that LLMs are good about repeating sections of their context? Or that LLMs know what a "prompt" is from the training corpus containing descriptions of LLMs, and ca…
> I've always been curious why people think that models are accurately revealing their system prompt anyway. I have a few reasons for assuming that these are normally accurate: 1. Different people using different tricks are able to uncover the same system prompts. 2. LLMs are really, really good at repeating text they have just seen. 3. To date, I have not seen a single example of a "hallucinated" system prompt that'…
Also it's pretty hard to tell LLMs not to do things without actually adjusting the weights.
Re: Grok 4 Heavy Protects it's System prompt
#65I've always been curious why people think that models are accurately revealing their system prompt anyway. Has this idea been tested on models where the prompt is openly available? If so, how close to the original prompt is it? Is it just based on the idea that LLMs are good about repeating sections of their context? Or that LLMs know what a "prompt" is from the training corpus containing descriptions of LLMs, and ca…
I agree; I don’t understand it. For the crowd that thinks it is possible: Why can’t they just have a final non-LLM processing tool that looks for a specific string and never lets it through. That could include all of the tips and tricks for getting the LLM to encode and decode it. It may not ever be truly 100%, but I have to imagine it can get close enough that people think they have cracked it.
[dead]
Re: Grok 4 Heavy Protects it's System prompt
#66Earlier quoted context omitted.
There's no shortage of hatred on the internet, but I don't think it's "training on the open web" that makes Grok randomly respond with off topic rants about South African farmers or call itself MechaHitler days after the CEO promises to change things after his far-right followers complain that it's insisting on following reputable sources and declining to say racist things just like every other chatbot out there. It'…
Most of the prompts and context I've seen, has been people working to see if they can pull this stuff out of Grok. The problem I have, is I see people working very, very hard to make someone look as bad as possible. Some of those people will do anything, believing the ends justify the means. This makes it far more difficult to take criticism at face value, especially when people upthread worry that people are beng im…
I agree. This article from The Atlantic is a perfect example. Read the prompts the author used. It’s like he went through effort to try to get it say something bad. And when the model called him out he just kept trying harder.
The responses seemed perfectly reasonable giving the line of questioning.
https://www.theatlantic.com/technology/archive/2025/07/new-g...
Re: Grok 4 Heavy Protects it's System prompt
#67I'm not a ML engineer and only have surface level knowledge of models, but I’ve been wondering, would it be possible to train models in a way to be able to embed a system prompt in a non-textual format? Ideally, something that’s lightweight (like cheaper than fine-tuning) and also harder to manipulate using regular text prompts?
Text is just one representation. The model uses tensors (think multi-layered matrices in the context of ML that handle language and you're not too far off; in laymans terms, 'hard maths') to actually represent the inputs when they're being processed. But, I suspect, if the model is able to handle language at all, you'll always be able to get a representation of the prompt out in a text form -- even if that's a projec…
Iirc there have been studies that were able to do some amount of LLM debugging and identify certain weights corresponding to certain behaviors.
Seems like it could be possible to lobotomize the ability to express certain things without destroying other value (like a human split brain). Of course possible doesn’t mean tractable.
Re: Grok 4 Heavy Protects it's System prompt
#68this is fake news, the xml tags break the output when the model output is the system prompt with the example tags, see screenshot: https://x.com/0xSMW/status/1944624089597137214
same as what happens with claude