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

Ask HN: Is prompt engineering just snake oil?

news.ycombinator.com

Post reply on HN
Print view View original

111–120 of 206 posts

Re: Ask HN: Is prompt engineering just snake oil?

#111

Post by gnicholas »

I've wondered if some of the value of being a skilled prompt engineer will be eroded as the LLMs get better, especially as they can reply to ask clarifying questions or ask if you want XYZ tweaks (e.g., in the voice of Author X, or from the perspective of an ant, with backlighting).

I'm sure there will always be some people who are better at this than others, but if the interface is sufficiently chatty and 'smart', that could significantly reduce the gap between newbies and seasoned prompters.

Re: Ask HN: Is prompt engineering just snake oil?

#112

Post by vimax »

runjake wrote: post #108
vimax wrote: post #105

Earlier quoted context omitted.

Hard to apply those to software engineering as well.

In most jurisdictions, a professional engineer is essentially a specific legal thing. In most jurisdictions I am aware of, software engineers are not professional engineers. I am sure there are many exceptions. That said, I think all of the above are rather easy to apply to SWE aside from, arguably, the first bullet point.

And I can list counter examples for each.

Civil engineers and architects don’t “move fast and break things” or “fake it til you make it” after a 3 month bootcamp.

Re: Ask HN: Is prompt engineering just snake oil?

#113

Post by criddell »

ozim wrote: post #66
cjbprime wrote: post #11

It's okay; software engineering isn't real either. (In many countries, the word "engineer" is regulated -- you can't call yourself an engineer without professional qualifications and oversight.) https://en.m.wikipedia.org/wiki/Regulation_and_licensure_in_...

Isn't real? You write about people who sling PHP or Javascript spaghetti? I have engineering degree in computer science (I think it is mostly thing in eastern Europe, you have bunch of electronics, math, computer architecture to learn), I worked on automotive software which is I have to say fairly regulated. Where you have to care for things like ISO or MISRA standards in your code. I don't mind people calling themse…

In some jurisdictions, Professional Engineer (P.E.) is a protected title just like Doctor of Medicine (M.D.). You are licensed and can be sued for malpractice and lose your license to practice.

Re: Ask HN: Is prompt engineering just snake oil?

#114

Post by pixl97 »

nodemaker wrote: post #103
ozim wrote: post #66

Earlier quoted context omitted.

Isn't real? You write about people who sling PHP or Javascript spaghetti? I have engineering degree in computer science (I think it is mostly thing in eastern Europe, you have bunch of electronics, math, computer architecture to learn), I worked on automotive software which is I have to say fairly regulated. Where you have to care for things like ISO or MISRA standards in your code. I don't mind people calling themse…

Changing a bunch of bits on a magnetic drive or another media is not like building an airplane that flies or a car that runs! Software engineering is closer to a priest that supposedly can communicate to god than it is to someone that builds a car! I have a CS degree too and people without it are sometimes much better than me at slinging code Actually forget people, you should realize how far this is from engineering…

>on a magnetic drive or another media is not like building an airplane that flies or a car that runs

I ain't sure what century you live in, but it's not the current one...

If I program some bits on my hard drive and now a stepper motor punches thought the side of the mount its bolted too. Or if I say "set the flaps to this pitch in this condition" and that doesn't happen, then something very real, and very bad, happens in the reality we both exist in.

Almost everything complicated that exists today uses electronic control in one way or another. Screwing up the software in that ECU is just as much as of an error as using the wrong metal in its manufacture.

Re: Ask HN: Is prompt engineering just snake oil?

#115

Post by cjbprime »

bob1029 wrote: post #33
sys_64738 wrote: post #21

Earlier quoted context omitted.

An engineer is generally liable for what they sign off on. Software engineering isn't anything like that and all products are filled with legalese to restrict liability.

> all products are filled with legalese to restrict liability. This doesn't seem to apply in the realm I've been working in. We've had to do the exact opposite thing. In small, B2B software companies you may find that accepting an uncomfortable amount of liability is usually the only way to get your foot in the door. Certain promises have to be made (very carefully!) or no business would occur at all. For example, if…

This is a contractual SLA, which is certainly not the same thing as legal liability, and your contract might (obviously I haven't seen it) shield yourself from financial liability on top of your lack of legal liability. (Saying that you will respond within one hour is not the same thing as saying that they can sue you for every hour you're down.)

Re: Ask HN: Is prompt engineering just snake oil?

#116

Post by ZephyrBlu »

mdp2021 wrote: post #97
ZephyrBlu wrote: post #90

Earlier quoted context omitted.

I disagree it will ever be that easy for people to generate specifically what they’re looking for. I believe there will always be some amount of navigation of the latent space required, and people who don’t understand how to navigate it will struggle. To use your analogy, even if the horse is tame you still need to know how to ride it.

> that easy Can you code? Can you illustrate? Can you build? Piece by piece, you sketch, implement, hone, finetune, improve, correct, retry, go into detail, expand... The ease of the process is relative to the tools adopted. Of course there has to be knowledge behind it. Of course you have to know your tools. But "wild horse" and "diligent consultant", axe and scalpel require different degrees areas and modalities of…

My point is that even with improved tooling I don't think it will be accessible to a layman. You will need to develop some skill to wield the tool.

It seems like you agree based on parts of your comment like "A well built tool will build on the competences already natural for the professional".

Re: Ask HN: Is prompt engineering just snake oil?

#117

Post by cjbprime »

agentultra wrote: post #64
cjbprime wrote: post #11

It's okay; software engineering isn't real either. (In many countries, the word "engineer" is regulated -- you can't call yourself an engineer without professional qualifications and oversight.) https://en.m.wikipedia.org/wiki/Regulation_and_licensure_in_...

Yes it is. It’s a protected term in Canada and they have software engineers.

Are you saying that software engineers in Canada are P. Eng licensed?

(If not, then your example is one where software engineers are misusing the protected term, but as they usually do not set up shop and mislead the general public into thinking they are certified, which would be the activity the protection is designed to thwart, the protection is rarely enforced.)

Re: Ask HN: Is prompt engineering just snake oil?

#118

Post by thegginthesky »

coldtea wrote: post #71
thegginthesky wrote: post #68

Earlier quoted context omitted.

Truth to be told, Engineering license requirements have a bigger effect in gate keeping the profession and keep supply restricted, much like any other regulated profession. Gate keeping has some benefits, but is easily circumvented by bad actors all the time, such as all the sham degrees that just churn out the bare minimum to pass licensing tests. If all the licensing to architects, doctors, engineers, lawyers, and…

> Gate keeping has some benefits, but is easily circumvented by bad actors all the time, such as all the sham degrees that just churn out the bare minimum to pass licensing tests. Depends on the country and the educational system. In some countries no such sham degree is possible to be accepted for an engineering title.

I have yet to see a country where licensing equates to high quality in all the services. The examples I've used might not work in some places, but people find flaws in licensing systems all the time.

Sometimes licensing is so strict that things get done anyways ignoring license requirements because there is way more demand for some services than the supply of licensed professionals. In such cases, there are so many people violating regulation that policing becomes ineffective. It's the case with some Latin American countries.

And then you get to the problem that the license is ineffective and doesn't add to anything.

There's no perfect system to uphold quality of labor across a profession, we pick our poison and deal with it.

Re: Ask HN: Is prompt engineering just snake oil?

#119

Post by turtleyacht »

Prompt engineering is as valid as software engineering (of the non-certified kind). Why is it engineering?

Technical expertise. It is technical in nature, or only one level removed from having to look at code or internals. Unlike customer support--strictly speaking--you have access to additional tools or authorization to investigate the matter.

Domain expertise. You know that some phrases just don't help. You know about temperature and other jargon. You can look at someone's paragraph of prompt and immediately suggest something.

Stakeholder safety. You act in a manner that eliminates or reduces stakeholder harm. You care about your work.

If any of these are missing, it's not "engineering." Not to mention the importance of measuring things, data, etc--but I would hazard that being able to stare at graphs all day does not an engineer make.

At the end of the day, if your job title is "Prompt Engineer," who will object?

Versus professional (certified) engineers: https://news.ycombinator.com/item?id=35669226

Engineering as artful action: https://news.ycombinator.com/item?id=35670444

Tools of the AI Engineer: https://news.ycombinator.com/item?id=35669249

Re: Ask HN: Is prompt engineering just snake oil?

#120

Post by taeric »

ulrashida wrote: post #100
taeric wrote: post #80

Earlier quoted context omitted.

Causality will be tough here. I could also credit the certification regulations just as much. And truth to tell, construction techniques are vital, yet we don't value the construction workers in this way. That is, it is a whole system. And largely comes to costs and known building techniques. After all, certified engineers built "galloping gerdy." (And I didn't even get into maintenance costs and application. )

Construction techniques are vital, but a civil engineer is employed to conduct the correct QA/QC on those techniques. This doesn't devalue the effort of the work crew, but it does recognize you need accredited professionals at certain parts of the process to ensure public safety. To be a bit more pointed: causality isn't difficult here. This legislation and professional practice was deliberately designed as a result…

My point is that it is all of the regulation involved. Not just the single line worker that is the civil engineer. I know more than a few of those folks, and they are not some magical being. And it is more than the civil engineer. It is also the auditor. The inspector. Even the manager making sure they are all working together.
Post reply on HN