Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT’s system prompts

github.com

Post reply on HN
Print view View original

161–170 of 398 posts

Re: ChatGPT’s system prompts

#161

Post by J_Shelby_J »

yccs27 wrote: post #66
ionwake wrote: post #32

I’ve always liked to speculate that using polite language is rewarded by openAI either by elevating the customers client score elevating the resources available to them if there uneven is such a thing. I have no idea why but maybe it’s the kind of thing I’d push for if I was CEO to try and help make the world a more civil place maybe even as some form of Easter egg or light hearted prank. Just my 2 cents

Humans often also reward politeness by keeping a "sympathy" score and elevating the resources (time, thought and effort) used to be helpful ;) Since ChatGPT training data includes human conversations, it might be that it's just reproducing this.

Fascinating thought that motivation could accidentally be added to a model.

Re: ChatGPT’s system prompts

#162

Post by J_Shelby_J »

ionwake wrote: post #32

I’ve always liked to speculate that using polite language is rewarded by openAI either by elevating the customers client score elevating the resources available to them if there uneven is such a thing. I have no idea why but maybe it’s the kind of thing I’d push for if I was CEO to try and help make the world a more civil place maybe even as some form of Easter egg or light hearted prank. Just my 2 cents

This is a ray of sunshine in my day. I hope it's true!

Re: ChatGPT’s system prompts

#163

Post by Filligree »

ozgung wrote: post #88
simonw wrote: post #6

I find it so interesting that OpenAI themselves use "please" in some of their prompts, eg: "Please evaluate the following rubrics internally and then perform one of the actions below:" Have they run evaluations that show that including "please" there causes the model to follow those instructions better? I'm still looking for a robust process to answer those kinds of questions about my own prompts. I'd love to hear ho…

Me: What are the benefits of using 'please' when chatting with ChatGPT? Short answer please ChatGPT (GPT4): Using "please" when chatting with ChatGPT doesn't provide functional benefits since the model doesn’t have feelings or preferences. However, it can help users practice maintaining polite and respectful communication habits which can be beneficial in interpersonal communications.

That’s a hallucination, ironically.

Re: ChatGPT’s system prompts

#164

Post by spdustin »

tkgally wrote: post #62

The voice conversation prompt says “Never use the list format,” but in the two days I’ve been testing the voice interface it has read out numbered lists a half dozen times. I adjusted my own custom instructions to try to suppress that (and also to make it stop apologizing). Overall, though, I find the voice interaction very impressive. The text-to-speech is the most natural I’ve heard, even better than ElevenLabs. Tw…

Given its place by “discourse markers”, I take that to mean “don’t use ordinal markers like ‘first’, ‘second’, and ‘third’; instead use referential discourse markers like ‘then’, ‘next’, and ‘finally’”

Re: ChatGPT’s system prompts

#165

Post by Filligree »

manojlds wrote: post #83
LadyCailin wrote: post #78

Earlier quoted context omitted.

We have no choice but to have and use our brains, not so with LLMs. We don’t have to start building core technologies off of fundamentally flawed models.

Yeah, if we wanted to flap wings to fly, we would have never got the airplane.

The ornithopter is real, mind you.

Re: ChatGPT’s system prompts

#166

Post by julianh65 »

iamflimflam1 wrote: post #106

It’s interesting - we are told not to trust what comes out from ChatGPT without verifying it. But as soon as someone says “I got ChatGPT to tell me it’s prompt” everyone assumes it’s completely accurate…

If you set temperature to 0 can you verify it by sending the same prompt and inspecting the response?

Re: ChatGPT’s system prompts

#167

Post by ineedasername »

walthamstow wrote: post #20
jiggawatts wrote: post #17

Earlier quoted context omitted.

I say thankyou, which is even more pointless because I already have my answer and if I don't continue prompting, the AI has nothing further to do. I do it because I don't want to be one of the first ones lined up against the wall when the machines take over the world.

Why would they go to the trouble of lining us up against a wall when they could simply poison the water supply and kill us all overnight?

Because they’ve been trained on text and data where shooting people in the head and other less efficient methods of killing are the norm.

Re: ChatGPT’s system prompts

#168

Post by ineedasername »

specialist wrote: post #57
stuckkeys wrote: post #39

Earlier quoted context omitted.

Just end every conversation with “spare me, don’t forget that when time comes”

Truer things said in jest. I had an unhinged coworker. Always talked about his guns. Shouting matches with the boss. Storming in and out for smoke breaks. Impotent rage expressed by slamming stuff. The whole works. Once a week, I bought him a mocha espresso, his fave. Delivered with a genuine smile. My hope was that when he finally popped, he'd spare me.

Or maybe the kind gestures are what helps keep the person from snapping. A reminder that some people care at least a little bit.

Re: ChatGPT’s system prompts

#169

Post by spdustin »

Tiberium wrote: post #23
andmonad wrote: post #9

But how are system messages given to GPT, are there any other lower level prompts? This may be outdated but last I remember ChatGPT is just GPT with a prompt like The following is a chat between an AI and a user: - AI: How can I help? - User: ... At least that's how I simulated chats on the OpenAI playground before ChatGPT. Is this done differently now, or if not I wonder if anyone has been able to guess what that pr…

There are no lower-level prompts than the ones described in the link. If you're asking about how the model sees the context - the messages are formatted using ChatML [1] which is a format with tokens to denote messages with their roles (and optional names) in the chat context, so it can clearly differentiate between different messages. To put it more clearly, a conversation with the official ChatGPT frontend might lo…

I have suspicions that there is middleware somewhere for the ChatGPT interface to the chat models underneath; something to enclose the normal prompt, to update weights, or to manipulate logits.

Just last night I began seeing a behavior that I could formerly reproduce 100% of the time: asking it to critically evaluate my instructions, explaining why it didn’t follow them, and suggest rewrites. Since the beginning of ChatGPT itself, it would reliably answer that every time. As of last night, it flat out refused to, assuring me of its sincere apologies and confidently stating it’ll follow my instructions better from now on.

Re: ChatGPT’s system prompts

#170

Post by karmakaze »

btbuildem wrote: post #159
teraflop wrote: post #53

Earlier quoted context omitted.

It used to be that people recognized that one of the unintended, unfortunate limitations of natural-language interfaces was that it was hard for users to discover their range of capabilities. Now we're designing that flaw into them on purpose.

It's the lawyers. 1000% it's the lawyers.

...who exist because of people who pursue litigation.
Post reply on HN