Live data from Hacker News

GPT-Prompt-Engineer

github.com

121–130 of 166 posts

Re: GPT-Prompt-Engineer

#121

Earlier quoted context omitted.

Prompt "engineering" is just writing prayers to forest faeries. Whilst BASIC/JavaScript/etc are all magic incantations to a child, a child will soon figure out there's underlaying logic, and learn the ability to reason about what code does, and what certain changes will do. With prompts, it's all faerie logic. There is nothing to learn, there are only magic incantations that change drastically if the model is updated…

In "The Information," James Gleick discusses a concept related to our current discourse. In the days when computers were merely an array of switching circuits, luminaries such as Claude Shannon believed that "thinking" could be captured in a structured format of logical representation. However, even with formally composable languages like JavaScript, a semblance of unpredictability — akin to the "faerie logic" metaph…

It's not so much about formal logic, but general predictability.

even with formally composable languages like JavaScript, a semblance of unpredictability — akin to the "faerie logic" metaphor — still persists

And they're ridiculed for it, and as you state, we design around them or replace such systems entirely.

making continual interaction with them unavoidable

Technology is never unavoidable or "inevitable". We can choose not to use it, or when to use it.

The notion that we can pass a set of code or words through them once and expect a flawless result is simply illogical.

Yet that is what we expect when we put these systems into production use, especially when many proposed use cases are user-facing and subject to injection attacks.

Whether it be the writing of adcopy, the processing of loan applications, or generating code, mistakes in these tasks have very real consequences.

Re: GPT-Prompt-Engineer

#123

Isn’t engineering an exact science while prompt engineering is completely not? Although, even software engineering being an exact science, it is a funny one: most of us don’t get certified as like, let’s say, mechanical engineers do. Would they say we are engineers? So perhaps the “engineer” term got overloaded in recent years?

Prompt "engineering" is just writing prayers to forest faeries. Whilst BASIC/JavaScript/etc are all magic incantations to a child, a child will soon figure out there's underlaying logic, and learn the ability to reason about what code does, and what certain changes will do. With prompts, it's all faerie logic. There is nothing to learn, there are only magic incantations that change drastically if the model is updated…

It’s so refreshing to see someone actually write this about prompt writing. It makes an extremely refreshing change from Twitter AI influencers posting their ridiculous prose as some marvel of harnessing LLMs.

Re: GPT-Prompt-Engineer

#124
post #35

Earlier quoted context omitted.

Creating a computer to find "the ultimate answer to life, the universe and everything", getting a cryptic answer and then creating an even bigger and more complicated computer to find the question is a pretty good satire of generative ai based chatbots of exponentially increasing model size.

Don't remember if it made it into the book, but from the radio series my favorite is the scene where they end up in a nightclub filled with dancing mannequins sprayed with sweat in order to convince people it was popular and come in.

> a nightclub filled with dancing mannequins sprayed with sweat

That's pretty much how I see every nightclub, to be fair...

I loved illegal raves when I was in college. Paying big bucks to listen to loops triggered by some influencer feels like a surreal parody...

Re: GPT-Prompt-Engineer

#125

Earlier quoted context omitted.

In "The Information," James Gleick discusses a concept related to our current discourse. In the days when computers were merely an array of switching circuits, luminaries such as Claude Shannon believed that "thinking" could be captured in a structured format of logical representation. However, even with formally composable languages like JavaScript, a semblance of unpredictability — akin to the "faerie logic" metaph…

It's not so much about formal logic, but general predictability. even with formally composable languages like JavaScript, a semblance of unpredictability — akin to the "faerie logic" metaphor — still persists And they're ridiculed for it, and as you state, we design around them or replace such systems entirely. making continual interaction with them unavoidable Technology is never unavoidable or "inevitable". We can…

I don't disagree we can choose to use it or not, but my point was more meant to indicate that, if we want a good experience with LLMs, we have to continue to interact with them to achieve good results.

Reminds me of raising kids...

Re: GPT-Prompt-Engineer

#126

Isn’t engineering an exact science while prompt engineering is completely not? Although, even software engineering being an exact science, it is a funny one: most of us don’t get certified as like, let’s say, mechanical engineers do. Would they say we are engineers? So perhaps the “engineer” term got overloaded in recent years?

Prompt "engineering" is just writing prayers to forest faeries. Whilst BASIC/JavaScript/etc are all magic incantations to a child, a child will soon figure out there's underlaying logic, and learn the ability to reason about what code does, and what certain changes will do. With prompts, it's all faerie logic. There is nothing to learn, there are only magic incantations that change drastically if the model is updated…

This was magical really made my day. Thanks for this.

Re: GPT-Prompt-Engineer

#127

Earlier quoted context omitted.

There is a paper on arxiv saying that GPT4 correlation with human evaluators on a variety of tasks with strongly positive. I am also uncomfortable with it, but using GPT4 as a grader is not as bad as you think.

That's definitely begging the question. If you're prepared to accept that GPT-4 can answer questions just as well as humans can, why do you even need to do prompt engineering?

Humans benefit from good communication too. For example, annual U.S. deaths from medical errors is in the hundreds of thousands. Much of it is due to miscommunication. Is this akin to poor human-to-human prompt engineering? Of course, humans will rush and not attempt better communication, and you can take all the time you wish with an AI. And AI will continue to incorporate better prompt engineering that you won't have to write out. But there will always be a continuum from good to bad for communication, and communication outcomes.

Re: GPT-Prompt-Engineer

#128
post #33
post #15

Earlier quoted context omitted.

Looks more like science here. Run a bunch of experiments and see which does better. But literally the first sentence of the readme is "Prompt engineering is kind of like alchemy."

> Run a bunch of experiments and see which does better. That's empiricism. Scientific method implies formulating falsifiable theoretical claims, producing meaningful analysis of experimental conditions, publishing peer-reviewed and reproducible results.

Does the scientific method include peer review? I thought that was a recent phenomenon.

Re: GPT-Prompt-Engineer

#129

Earlier quoted context omitted.

That's definitely begging the question. If you're prepared to accept that GPT-4 can answer questions just as well as humans can, why do you even need to do prompt engineering?

Humans still need 'prompt engineering' to answer questions more accurately though. * What's the best way to get to Radio Shack from here? is not the same as * What's the easiest way to get to Radio Shack from memory when riding a bicycle from here?

Easiest way to get to Radio Shack on a bicycle is to ride that bike down to Doc Brown’s house, charge the Delorean up to 1.21 gigawatts, and go back in time.
Post reply on HN