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

381–390 of 398 posts

Re: ChatGPT’s system prompts

#381

Post by two_in_one »

Jensson wrote: post #72
novalis78 wrote: post #27

Earlier quoted context omitted.

Everyone I know who has great success using GPT4 has tuned their prompts to a friendly and kind tone of conversation. In fact it’s fascinating to watch people start out like talking to a browser search bar and ending up a few weeks later conversing to another human being. Crazy. They begin with timid probes into its (her? His?) capabilities and become more and more daring and audacious.

The ideal way to prompt would be to say something wrong and have it correct you, works great on the internet. Sadly it doesn't seem to be smart enough to be at that level yet, it is too hard for it so when you do that it will hallucinate a lot as it corrects you, or miss your error completely.

Actually it is. Several times I called thing the wrong name and it corrected. Sometime I describe what I want and it says "the thing you are talking about is called..." Sometimes _it_ does mistakes and _I_ have to correct. Double checking and testing is always a good idea ;).

Re: ChatGPT’s system prompts

#382

Post by two_in_one »

steveklabnik wrote: post #49
novalis78 wrote: post #27

Earlier quoted context omitted.

Everyone I know who has great success using GPT4 has tuned their prompts to a friendly and kind tone of conversation. In fact it’s fascinating to watch people start out like talking to a browser search bar and ending up a few weeks later conversing to another human being. Crazy. They begin with timid probes into its (her? His?) capabilities and become more and more daring and audacious.

I have seen some people go even further and start up different chats, where in each tab they start by describing the character they want to chat with, and then moving on to talking with it.

It can play several characters at once. I tried playing one person in the room while GPT was playing 2 others. It worked. Conversation was in format

formal introduction who is who (one was going to Mars), then conversation.

Name1: ...

Name3: ...

and so on.

Re: ChatGPT’s system prompts

#383

Post by tough »

malux85 wrote: post #304
tough wrote: post #302

Earlier quoted context omitted.

I tried asking ChatGPT about e/acc (accelerationism) moniker some twitter users sport nowadays. Not in training data. clueless

Of course it is, that’s domain knowledge. How would it know about things that it’s never been exposed to?! Novel compositions of existing knowledge is totally different to novel sensory input.

Well I had no idea when the moniker was started being used so I wouldn' t know if it was on the cut off knowledge date or not

Re: ChatGPT’s system prompts

#384

Post by ionwake »

hmage wrote: post #325
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

You have two documents on internet: First document is an forum thread full of "go fuck yourself fucking do it", and in this kind of scenario, people are not cooperative. Second document is a forum thread full of "Please, take a look at X", and in this kind of scenario, people are more cooperative. By adding "Please" and other politness, you are sampling from dataset containing second document style, while avoiding la…

It really does and now it makes sense. Thank you for the clarification.

Re: ChatGPT’s system prompts

#385

Post by ionwake »

J_Shelby_J wrote: post #162
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!

What a lovely comment have a great day bro

Re: ChatGPT’s system prompts

#386

Post by krainboltgreene »

int_19h wrote: post #346
krainboltgreene wrote: post #267

Earlier quoted context omitted.

> but you can say the same about human brains It should be an HN rule that in order to type out variations of this sentence you have to also prove you have a degree in neuroscience.

You don't have to have a degree in neuroscience to be aware of the fact that we aren't even close to understanding how human brain works when it comes to high-level process such as sentience.

First off we understand a lot about the human brain, but that doesn't matter because no one is arguing that we understand the totality of the human brain, instead what is being argued is: The human brain is as simple as an LLM and thus LLMs are sentient, can reason, and can know facts.

Re: ChatGPT’s system prompts

#387

Post by krainboltgreene »

btilly wrote: post #277
krainboltgreene wrote: post #258

Earlier quoted context omitted.

Why? Are not grammatical errors and idiosyncrasies part of the data set that chatGPT is trained on and thus also a predictable set of tokens?

Such errors are rare enough that they are almost never the most likely next token. Therefore ChatGPT only makes such mistakes when it is given good reason to do so.

ChatGPT cannot reason.

Re: ChatGPT’s system prompts

#389

Post by Grimblewald »

ethbr1 wrote: post #231
lgas wrote: post #224

Earlier quoted context omitted.

Arguably, "threatening" and "shaming" are both forms of "social engineering."

100%. The bulk of social engineering is leveraging, abusing, and breaking social norms so people feel compelled to do what you want them to.

or even more effective, threatening to break social norms on your behalf.
Post reply on HN