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

31–40 of 95 posts

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

#31

Post by SargeDebian »

soco wrote: post #23
samuell wrote: post #16

I think one can do an analogy with search engines. I noticed that a lot of people are terrible with search engines. They would carefully try to craft a combination of keywords that they hope will answer their problem. I have pretty much always been able to find the answers I need quickly, by using a few ideas I see not that many around me use, such as trying to imagine in what context the answer might be answered (wh…

The only point where I disagree is "the search engines have gotten a lot better over the last say 5-10 years". My impression is rather the opposite.

For most people, finding the result they're looking for is probably easier, partially because they're not that picky, and because things like integrating Google Maps into Google makes finding places easier. For a specific group (concentrated here on HN) finding the exact right result has become more difficult, in part because search engines no longer strictly adhere to some operators.

In parallel, the internet just changed, which means "the best result" may just be a worse one. In part because of search engines, and SEO. If you want a recipe, now the best recipe may just be the one that has a long description of the author's relationship with their mother who used to cook this dish, which you have to skip, because of SEO.

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

#32

Post by tudorw »

scantis wrote: post #8

Strictly in my opinion, prompting is just a transformation from concise to verbose. You have a short statement, with a description of your problem and the answer is a long text. Sometimes we prefer verbose, sometimes concise. Sometimes a word already has all the meaning we need, another time we need a long description and examples. Depends on our level of knowledge. So from my limited point of view, you excell at mov…

Good summary, as an exercise in the precise use of language it excels.

It is a patient listener and it's response can help one reflect on the inherent weight and biases of words within a language.

I would also like to add that in 1996 being able to use a search engine was very much a skill someone would hire you for!

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

#33

Post by TheAceOfHearts »

I think even learning to effectively integrate LLMs and other AI tools into your workflows can be a massive boon in both capabilities and productivity. It can change how you approach certain problems.

There's tons of small tricks and techniques to tease out vastly superior responses. When you're prompting for fairly generic or high level things it doesn't feel like there's that much difference in prompt style, but once you're trying to tease out highly specialized behavior there's tons of room for magic.

One of the tricks I've picked up on is that too many instructions and details often become a hindrance, so you need to figure out which parts to cut out and re-organize while still managing to get a high quality output.

Sometimes it's all about finding just the perfect words to describe exactly what you want. You can play around with variants and synonyms and get a feel for how the output is shaped.

Every model has quirks and preferences as well, so it takes a bit of playing around until you get a feel for how it interacts with your inputs. Admittedly a lot of this feels more like a vibe check than a science.

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

#34

Post by spupy »

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 seen few people go really overboard with their prompts. RPG-like personality sheets with points assigned to various traits (personality rubric? skill graph?), convoluted graphs of ineligible task descriptions, lots of other stuff that makes little sense to a human. I personally don't think these make any noticeable difference, but people deep into that type of prompting would tell me I just don't get how ChatGPT works.

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

#35

Post by tudorw »

tudorw wrote: post #32
scantis wrote: post #8

Strictly in my opinion, prompting is just a transformation from concise to verbose. You have a short statement, with a description of your problem and the answer is a long text. Sometimes we prefer verbose, sometimes concise. Sometimes a word already has all the meaning we need, another time we need a long description and examples. Depends on our level of knowledge. So from my limited point of view, you excell at mov…

Good summary, as an exercise in the precise use of language it excels. It is a patient listener and it's response can help one reflect on the inherent weight and biases of words within a language. I would also like to add that in 1996 being able to use a search engine was very much a skill someone would hire you for!

I use it as a code partner too, it's very good for that, cursor.so is built from the ground up with an accelerated GPT4 option, it was a really useful assistant to extend what I knew to the extent that I could implement what I wanted and it worked.

Ignore at your peril...

A stepping stone to AGI, yes. in the same way inventing the bolt is a step to building a spaceship. A novel sort of database, something akin to a multi-dimensional topological manifold from which you can navigate a latent space by supplying constraints in the form of words, images and text... fascinating.

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

#36

Post by tudorw »

Kiro wrote: post #27
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?

When you want very specific output you need a lot of boilerplate with rules, worded in a way where it can't be misinterpreted by the model. I need to do a lot of trial and error before I get the desired output consistently and I presume that a good prompt engineer would get there faster.

This is my experience, a single ambiguous word can create undesired gorilla, output. It's susceptible to all sort of unintentional outcomes whe,n simple thing;s that are wrong with text can render it co nfused.

or as GPT4 put's it;

When using models like mine, clarity in input is essential to get desired outputs. But even with clear input, there's no guarantee the output will always be perfect. However, the idea is to keep improving and iterating to get better over time.

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

#38

Post by baby »

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 to a list (if producing a json output, the object can contain a list of things it knows about you). But it doesn’t always seem to understand it learned something personal from you, and has trouble carrying a list forward without losing items.

The last one is about correcting the user. I want to speak chinese to the AI and I want it to correct me. And if I use english words within my chinese I want it to help me translate them as well. It can’t do none of these things. It’s like it doesn’t seem to realize that chinese and english are two different languages.

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

#39

Post by tudorw »

tudorw wrote: post #36
Kiro wrote: post #27

Earlier quoted context omitted.

When you want very specific output you need a lot of boilerplate with rules, worded in a way where it can't be misinterpreted by the model. I need to do a lot of trial and error before I get the desired output consistently and I presume that a good prompt engineer would get there faster.

This is my experience, a single ambiguous word can create undesired gorilla, output. It's susceptible to all sort of unintentional outcomes whe,n simple thing;s that are wrong with text can render it co nfused. or as GPT4 put's it; When using models like mine, clarity in input is essential to get desired outputs. But even with clear input, there's no guarantee the output will always be perfect. However, the idea is t…

The iteration point is important, interacting with the model to have it outline the kinds of information which would assist it in building it's internal model of your 'question', meta-programming with it is fun and constructive.

GPT4;

Absolutely! Iterative interaction is key. By refining and rephrasing queries, users can guide the model towards a more accurate or desired response. Each successive interaction serves as a form of feedback that can help clarify ambiguities or nuances that might have been missed in an initial query.

Engaging with the model in a meta-programming manner, or in essence "programming the way it thinks," is indeed an intriguing way to understand its strengths and limitations. It can also be a valuable method for users to hone their ability to communicate with AI and enhance the results they receive.

This iterative dialogue not only helps users get more precise information but also provides insights into the model's underlying logic and reasoning. The fun part is navigating these intricacies and understanding how subtle changes in phrasing or context can yield different outcomes. It's a dance of human-machine collaboration, where both parties learn and adapt to each other.

Post reply on HN