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

Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

news.ycombinator.com

Post reply on HN
Print view View original

51–60 of 95 posts

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#51

Post by inconfident2021 »

VladimirGolovin wrote: post #25

I must admit that I have a slight FOMO over prompt engineering. I'm pretty decent at verbalizing ideas and concepts for external consumption, and my experience with ChatGPT 4 has been excellent so far, but I still feel that I'm missing something. Could you summarize the essence of the prpompting skill in a couple of sentences? Are there concepts that are critical to learn and master (e.g. 'chain of thought', etc.)?

You write requirements and your expectations and make the model match your expectations. Until you have clear expectations of what you want from it, prompting LLM is pretty useless. It cannot do highly specific task because those are limited in the original training corpus too. However, for more generic task, it has seen most of the stuff out there, so it should be good enough. Having clarity on your problem is the key.

You have to make sure to couple chain of thought with branching, analysis and evaluation, then you can get pretty good results.

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#52

Post by inconfident2021 »

wesapien wrote: post #6

Can you give an example of something you've done with this skill that was very satisfying?

I have zero design skills and I had to create something using javascript. I gave some prompts and it was able to come up with a pop-up box. It needed some tweaking but having to not write all of that was really satisfying.

https://chat.openai.com/share/cb3a477b-57bd-46fd-92c9-4a3016...

I have attached the example in the above chat.

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#53

Post by elpocko »

Aerroon wrote: post #49
elpocko wrote: post #9

You adapted to the underdeveloped UX of wonky proof-of-concepts built by researchers, working around shortcomings that will be ironed out once genuine sofware developers start releasing actual products.

I'm not so sure how much they will be ironed out. If the product only has a button you can press then maybe, but if it lets you enter text then I think knowing how to prompt will be useful. The reason I believe this is because one of the greatest strengths of these AI models is to take in arbitrary text. If you take away that ability then you just end up with a complicated branching system that could've existed befor…

> The reason I believe this is because one of the greatest strengths of these AI models is to take in arbitrary text.

And they will get better at making sense of vague questions, and start asking for clarification, without the need for the black magic of a prompt wizard.

The prompt engineer can soon be replaced with a fine-tuned LLM. It's a thing already for SD prompts. No more need to know ridiculous magic prompt tokens.

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#54

Post by petesergeant »

inconfident2021 wrote: post #50
baby wrote: post #38

Not sure. But maybe you can answer my questions. I’ve had issues with trying to tell the LLM how long the answer should be. It doesn’t really seem to understand X number of words, or pages, or paragraphs. But I had some success with things like “short story”. The other thing I’ve been struggling with is to have the AI keep track of what’s important. For example, when the AI learn something from you it should add it t…

> understand X number of words, or pages, or paragraphs. LLMs do not have the ability to reason with numbers. Most of the time they are hallucinating. One good strategy is to make it output in list and define the structure for each item of the list. If you give an example of what your list should look like, it will give you something close it. > has trouble carrying a list forward without losing items. This is the fu…

> LLMs do not have the ability to reason with numbers

I’ve found ChatGPT pretty good at estimating long division

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#56

Post by monooso »

I think it depends on your chosen field of work.

An analogy may help to explain my point.

I write code for a living. I'm pretty good, nothing amazing, and my ability to program is table stakes for my profession. Before I did this for a living, I worked as an industrial designer. In that job, coding was akin to a superpower, because nobody else in the company could do it.

Being a decent prompt engineer in a non-technical profession could be a similar multiplier.

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#57

Post by roel_v »

olalonde wrote: post #19

What is there to it other than knowing how to write and ask questions? I also get the desired results out of LLM models but I would hardly call it a skill (well, maybe on par with knowing how to "Google" stuff). Are there people who actually struggle with this?

I've watched (non technical) people use ChatGPT a few times now, and most of them have rather underwhelming results. The reason is that they think it's just some other search engine, and they phrase their prompts as 'search queries'. Or they go completely the other direction and think they can just throw in a few random words that somewhat describe what they're roughly thinking of, and then expect the computer to fill in the gaps.

It's 2023 and there are lots of people who don't know how to efficiently and effectively use Google. To be able to do that, you need some sort of mental model of crawlers and websites and what gets indexed and what not and at what frequency, and the results of SEO and how a somewhat savvy marketeer at some company might influence things etc. The same with LLM models - if you don't know what a 'token' is, your only chance of getting good results is to use these models a lot and then hope that you start building useful intuitions. It really doesn't come natural to most people like it does to most of us here.

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#58

Post by pillefitz »

inconfident2021 wrote: post #51
VladimirGolovin wrote: post #25

I must admit that I have a slight FOMO over prompt engineering. I'm pretty decent at verbalizing ideas and concepts for external consumption, and my experience with ChatGPT 4 has been excellent so far, but I still feel that I'm missing something. Could you summarize the essence of the prpompting skill in a couple of sentences? Are there concepts that are critical to learn and master (e.g. 'chain of thought', etc.)?

You write requirements and your expectations and make the model match your expectations. Until you have clear expectations of what you want from it, prompting LLM is pretty useless. It cannot do highly specific task because those are limited in the original training corpus too. However, for more generic task, it has seen most of the stuff out there, so it should be good enough. Having clarity on your problem is the k…

Sounds like what a Product Owner is supposed to do

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#59

Post by WesolyKubeczek »

sam0x17 wrote: post #21

Prompt engineering is just the "good at google searching" of tomorrow. That said, I think there is a lot more potential depth to it, seeing how inexpressive web searches are by comparison.

But then again, we have SEO which is serious business full of superstition.

Re: Ask HN: I learned useless skill of prompt engineering, how relevant will it be?

#60

Post by wruza »

inconfident2021 wrote: post #52
wesapien wrote: post #6

Can you give an example of something you've done with this skill that was very satisfying?

I have zero design skills and I had to create something using javascript. I gave some prompts and it was able to come up with a pop-up box. It needed some tweaking but having to not write all of that was really satisfying. https://chat.openai.com/share/cb3a477b-57bd-46fd-92c9-4a3016... I have attached the example in the above chat.

How would an unskilled non-prompt engineer formulate these tasks? I mean, what’s the difference that makes one a skilled PE here?
Post reply on HN