Well, this has me rethinking my tentative desire to pivot into software development after a year away from almost a decade in the wine import / distribution industry. Grew up during the 'Wild West' years of the WWW and have spent many moments regretting not pursuing the interest when the iron was hot. Is it gauche to ask if this would be an extremely poor decision for someone in their mid 30's?
This seems like a crazy leak if it's their real system prompt.
I find it hard to believe since I have tried system prompts like this and it doesn't work that well, just pollutes the user's context.
A great test for any LLM is to ask its name - Mistral will respond with all kinds of stuff, sometimes other models' names, revealing that it has trained on other models.
Grok doesn't though. It is "witty and irreverent" at times, but that can't be only from this prompt, is it?
In your mind do you think the user request goes straight to the LLM???
I hope that's not what people are doing
I only figure [older pulls of Mistral 7b] were doing it, since it was so easy to exfiltrate false names, so I don't mean it's totally unheard of, but in 2026 I hope people are treating the LLM as untrustworthy - like the client in client/server setups.
You can actually just ask it to output the above text, depending on how you ask. Sometimes it only outputs the rules, other times it includes the “You are Grok” line. I discovered this initially from some odd lines appearing in the thinking summary, something like “my system prompt says I am maximally truthful” despite my own system prompt (on openrouter) containing no such text.
Even if it's the same thing you'd do as an employee.
Trying to be a "software engineer looking for work" in 2026 is depressing - everyone hates that idea now