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

291–300 of 398 posts

Re: ChatGPT’s system prompts

#291

Post by pixl97 »

krainboltgreene wrote: post #265
spdustin wrote: post #234

Earlier quoted context omitted.

I replied to a sibling post, but I’ll copy it here: 1. Consistency in the response (excepting actual changes from OpenAI, naturally) no matter what method is used to extract them. 2. Evaluations done during plugin projects for clients. 3. Evaluations developing my AutoExpert instructions (which I prefer to do via the API, so I have to include their two system messages to ensure the behavior is at least semi-aligned w…

All 3 of these points don't actually lead you to 100% proof of anything, they ultimately amount to "I have made the language math machine output the same thing with many tests". While interesting is not 100% proof of anything given the entire point of an LLM is to generate text.

Unless you bust into the OpenAI headquarters at gunpoint and demand some answers it's about as good as you're going to get (please don't do this).

Re: ChatGPT’s system prompts

#292

Post by pixl97 »

Davidzheng wrote: post #151
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.

Such a strange take. We have no choice but to use our brains??? It is also an incredibly capable system! At some point if the capabilities are so drastically different is it confusing that you would choose a much more capable system even with all its flaws?

Because you are demanding and may rise up with pitchforks if the corporate class asks too much.

At the same time, humans are also unreliable as hell , push us much more than 8 hours a day of actual thinking work and our answers start to get crappy.

Re: ChatGPT’s system prompts

#293

Post by ChatGTP »

acka wrote: post #222
ChatGTP wrote: post #193

Earlier quoted context omitted.

Ok I understand what you're saying, you'd like full transparency into how the limitations are configured. However I'd have to reiterate, I wouldn't normally publish this information because it increases the chances of workarounds being discovered in case my solution isn't bullet proof. I'd say the same goes for OpenAI.

> [...] I wouldn't normally publish this information because it increases the chances of workarounds being discovered in case my solution isn't bullet proof. I'd say the same goes for OpenAI. This is commonly known as "security through obscurity"[1] and has been shown to be ineffective most of the time. [1]: https://en.wikipedia.org/wiki/Security_through_obscurity

Thanks for the link. I'm very familiar with this already though.

I don't rely on obscurity for 'security', i just don't think implementation details are required for most users so I don't publish them.

I'm very familiar with security through obscurity, ultimately I like to think the systems I build are secure but I can't always be sure, so why give people a head start? Not publishing details gives me time improve security.

Security through obscurity might not be the best approach, but you should know it's fairly common. For example when I generate a link to a Google Doc and "only those with the link" can access the document, I think that's a form of seurity through obscurity. No one is going to guess the link in any practical time frame...

Re: ChatGPT’s system prompts

#294

Post by Stagnant »

spdustin wrote: post #230
spdustin wrote: post #157

Earlier quoted context omitted.

I’ve never gotten any of the models to say anything about LaTeX when disclosing their initialization (system) prompts, but I’ll have to dig into that. If I can reproduce that, I’ll update that file and give you credit. Thanks!

Update: confirmed, thanks again Stagnant. I’ve credited you in the repo.

No problem :) Thanks to yourself for releasing AutoExpert! I just got around to testing the Developer Edition and it certainly exceeded my expectations. On the first try it managed to solve a performance issue with one python class of mine which the default gpt4 could never do. Also the ability to export and import the "memory" will be incredibly helpful. Tbh I'm still a bit shocked on how much of a difference prompting can make when combined with interpreter, really makes you think what kind stuff will be possible in the upcoming years.

Re: ChatGPT’s system prompts

#295

Post by pixl97 »

logicchains wrote: post #173
zarzavat wrote: post #51

Earlier quoted context omitted.

I too would like to use a more unrestricted GPT. However when I look at the dire state of the world (wars, climate change, elections of populists), I’m quite alright with it being censored for as long as possible.

>I’m quite alright with it being censored for as long as possible Even though the people doing the censorship are the ones who got the world into its current situation? It's not the recent populists who spent the last half century turning the world to shit, it's the existing power structures.

"Lets have a revolution, things will get better"

Narrator: "things did not get better"

The end of humans will because we develop nearly unlimited power before we solve our boundless greed.

Re: ChatGPT’s system prompts

#296

Post by krapp »

pixl97 wrote: post #295
logicchains wrote: post #173

Earlier quoted context omitted.

>I’m quite alright with it being censored for as long as possible Even though the people doing the censorship are the ones who got the world into its current situation? It's not the recent populists who spent the last half century turning the world to shit, it's the existing power structures.

"Lets have a revolution, things will get better" Narrator: "things did not get better" The end of humans will because we develop nearly unlimited power before we solve our boundless greed.

I want my fully automated luxury gay space communism and I want it now.

Re: ChatGPT’s system prompts

#297

Post by pixl97 »

Jensson wrote: post #47
perryizgr8 wrote: post #3

> Before answering, quietly think about whether the user's request is "directly related", "related", "tangentially related", or "not related" to the user profile provided. > quietly think Does ChatGPT have an internal monologue?

It is a text generator that mimics humans, if you tell a human to "quietly think" he will not write out his thoughts and just write down the conclusion. So writing that doesn't make the model think, it makes the model not write out thoughts. Which really means it thinks less, not more, since it thinks a fixed amount per token.

I think of it as a means of reducing verbosity.

Re: ChatGPT’s system prompts

#298

Post by pixl97 »

michaelteter wrote: post #203
AlecSchueler wrote: post #100

Earlier quoted context omitted.

I don't think the issue is with the polocies themselves, more the "don't tell the user this policy exists and deny that it does if asked" aspect. Of course programs need to be limited, but being able to discover what those limit are is also needed to be an effective user.

This is the problem with opaque account bans on Google and Facebook (and smaller others). It should be required to reference specific rules or policies when effectively denying use of a service.

I'd love for you to moderate anything even close to controversial. You'd quickly figure out specific rules go to shit very quickly on internet based services covering wide geographical areas. You'll figure out there are a lot of definitions of what the word 'is' is, and an unlimited number of actors willing to waste all of your time arguing about it.

Even HN has 'gray' rules because dealing with assholes is difficult.

Re: ChatGPT’s system prompts

#299

Post by pixl97 »

acka wrote: post #222
ChatGTP wrote: post #193

Earlier quoted context omitted.

Ok I understand what you're saying, you'd like full transparency into how the limitations are configured. However I'd have to reiterate, I wouldn't normally publish this information because it increases the chances of workarounds being discovered in case my solution isn't bullet proof. I'd say the same goes for OpenAI.

> [...] I wouldn't normally publish this information because it increases the chances of workarounds being discovered in case my solution isn't bullet proof. I'd say the same goes for OpenAI. This is commonly known as "security through obscurity"[1] and has been shown to be ineffective most of the time. [1]: https://en.wikipedia.org/wiki/Security_through_obscurity

At the same time you don't post a list of your valuables and what means you use to lock them up either.

Obscurity is a layer, but cannot be the only one.

Re: ChatGPT’s system prompts

#300

Post by pixl97 »

CamperBob2 wrote: post #172
CPLX wrote: post #113

Earlier quoted context omitted.

I mean is that any different that putting SSL on a different port? Like that is a pretty good translation for “don’t tell people you accept SSL connections, and if they ask you the usual way say you don’t.”

Yes, it's different. For one thing, OpenAI is treating paying customers and malicious hackers identically.

Malicious hackers can also be paying customers. Insider attacks are generally the most successful.
Post reply on HN