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

ChatGPT – Dalle3 System Prompt

twitter.com

Post reply on HN
Print view View original

21–30 of 127 posts

Re: ChatGPT – Dalle3 System Prompt

#21

Post by KineticLensman »

Chabsff wrote: post #13
nuccy wrote: post #4

All these policy prompts remind me laws of robotics by Asimov [1], and definitely our current 'robots' frequently violate them. Asimov's laws are more logical since those are hierarchical with high-to-low prioritization and self-referencing. Can't those LLM/text-to-image model rules be embedded in the training/alighnment process instead of being injected before user input? 1. https://en.m.wikipedia.org/wiki/Three_Law…

If you read Asimov's short stories and novels, you'll find that the point being made over and over again is that despite them sounding ironclad at first, the laws are naïve, futile, fraught with unexpected ambiguity, and ultimately cause more trouble than they solve. People have this idea that Asimov envisioned a world where robotics was based on the rules, but it's the opposite really. He was claiming that there is…

Yes exactly. I also enjoyed charles Stross’s take on the laws of robotics in Saturns Children, an SF which explores the problems that robots face with the laws after humankind has gone extinct.

Re: ChatGPT – Dalle3 System Prompt

#24

Post by famouswaffles »

rickcarlino wrote: post #18

I’ve been suspicious that there was a “translate it to English” instructions in the system for other parts of the app. When generating Korean text, GPT4 has a habit of using “you” and “she” (당신/그녀) in the output, which are rarely used in Korean.

There wouldn't be that kind of instruction for text generation in other languages because that's thing LLMs trained on other languages do natively. Unnatural responses are probably the result of English only rlhf and maybe limited training corpus. at least, asking for natural responses seem to work.

Re: ChatGPT – Dalle3 System Prompt

#25

Post by willsmith72 »

chalsprhebaodu wrote: post #23

As someone who daily tries and fails to get ChatGPT to follow very simple and clear instructions on how to respond, it’s hard to believe that these system prompts work as described.

are you using gpt4? what kind of tasks are you trying to do?

Re: ChatGPT – Dalle3 System Prompt

#26

Post by Zamicol »

tonmoy wrote: post #20

If someone had told me that the policy/instructions to a program/software would be provided in plain English 3 years ago, I would have said they watch too much Sci Fi. Even now I can’t wrap my head around that fact that people give specific instructions to LLMs using “system” prompt in the same manner like you would to an AI like Cortana in Sci Fi. Are you people who use LLMs like this, sure you’re not just figments…

I was thinking exactly the same.

I'm so accustomed to instructing computers by code. It is alien to see backend instructions written in English.

Re: ChatGPT – Dalle3 System Prompt

#27

Post by noduerme »

fassssst wrote: post #5
Racing0461 wrote: post #2

What does #7 mean? All images it generates will be no different than a college brochure front page if it includes people?

It means if you ask for “ideal person” you won’t just get blonde hair and blue eyes.

It says "ALL images of people". My reading is that it should explicitly prepend every reference to people with a (randomly chosen?) gender and ethnicity unless otherwise specified.

So if you type "3 people drinking coffee", the dalle prompt generated would be `a ${getRandomRace()} ${getRandomGender()}, a ${getRandomRace()} ${getRandomGender()} and a ${getRandomRace()} ${getRandomGender()} drinking coffee`.

In other words, yeah, a college brochure.

Re: ChatGPT – Dalle3 System Prompt

#28

Post by cypress66 »

nuccy wrote: post #4

All these policy prompts remind me laws of robotics by Asimov [1], and definitely our current 'robots' frequently violate them. Asimov's laws are more logical since those are hierarchical with high-to-low prioritization and self-referencing. Can't those LLM/text-to-image model rules be embedded in the training/alighnment process instead of being injected before user input? 1. https://en.m.wikipedia.org/wiki/Three_Law…

> Can't those LLM/text-to-image model rules be embedded in the training/alighnment process instead of being injected before user input?

Absolutely. The model would fairly easily learn these rules with enough training even if you don't include such prompt.

But the prompt helps with training stability, and with not hurting other tasks.

Re: ChatGPT – Dalle3 System Prompt

#29

Post by jimmyl02 »

NikolaNovak wrote: post #6

So if these are remotely real... And purely as a user of chatgpt not as an ai/ml/nn person... Don't instructions like this weaken the strength of output? Even when request doesn't directly conflict, there are probably myriad valid use cases when instructions will weakly contradict the request. Plus, doesn't it inject inaccuracy into the chain - e.g. it's assuming model confidently knows which artists are 100yo etc. W…

This is one of the tradeoffs made to make the outputs safer. One of the ideas floating around is that some of the open source models are better simply because they don't undergo the same alignment / safety tuning as the large models by industry labs. It'll be interesting to see how LLMs improve because safety is a requirement but how can it be accomplished without reducing performance.

Re: ChatGPT – Dalle3 System Prompt

#30

Post by sebzim4500 »

chalsprhebaodu wrote: post #23

As someone who daily tries and fails to get ChatGPT to follow very simple and clear instructions on how to respond, it’s hard to believe that these system prompts work as described.

In my experience you kind of just have to lower your standards. i.e. if your system prompt is followed 90% of the time that still a win vs not using one.
Post reply on HN