Hacker Newsnew | past | comments | ask | show | jobs | submit | mkaramuk's commentslogin

i don't. just thought someone else might be interested in

But you have zero evidence this is actually the real system prompt.

LLMs are really good at repeating text that they've just seen. Very occasionally they'll mix up a word or two, but it's not at all challenging for them to regurgitate text from a previous section of input.

I have yet to see a documented example of a system prompt leak that was NOT the real system prompt. Have you seen one?


yeah, just assumed it is.

The chatbot craze in microcosm.

I think it's worth elaborating.

Loosely, LLMs give plausible responses. And LLMs are really good at writing confident-sounding responses.

LLM output is as if someone is replying with the sole purpose of appearing helpful and knowledgeable.

I wouldn't trust opinions on LLMs from people who are entirely positive or entirely negative: the technology is just too mixed for that. I'd say it's useful for someone to have had a bad experience with LLMs (e.g. LLMs being confidently wrong), as well as making use of LLMs for things they're powerful at. (e.g. "small" programming tasks).


btw i am not sure this is the whole system prompt or only a portion of it. since it is too short, i assume it is partial.

I wonder if there's formatting that's been stripped; because when I tried to read it, it looked like I was hitting headings and had to guess at possible line breaks.

Thanks, it really made my morning looking at it.


i copied and pasted the part that looked like the system prompt. because of manual copy-paste the formatting is gone. sorry for that.

I have connected yt music app then asked about what playlists do i have then it dumped that and continued with an explanation about it couldn't list the playlist but have a idea about what type of musics i listen.

Since the content was irrelevant, i called it as "randomly".


I had something similar w gemini in gmail. I asked it a question and it just dumped out the instructions. Oddly, it didn't give me an answer - just the dumped instructions

Hey this context is more importante than the prompt itself, make it more clear in the post! As this hints to a way to reproduce the output and likely estimate if it's an hallucination or not

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: