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

Tech’s hottest new job: Prompt engineer

washingtonpost.com

Post reply on HN
Print view View original

101–110 of 123 posts

Re: Tech’s hottest new job: Prompt engineer

#101

Post by barking_biscuit »

Syntonicles wrote: post #85
barking_biscuit wrote: post #35

Earlier quoted context omitted.

It has been amazing to watch the feedback loop with tools like Stable Diffusion where you see two types of strategy for solving problems of missing functionality. The first strategy is coming up with some long winded manual process involving disparate tools and several steps. The other is simply train a model to do what it is you want automatically. It has fast taught me that there is no competing with this new parad…

Could you give me some concrete examples that come to mind? I'm new to Stable Diffusion but have been using it a lot lately.

ControlNet was a stepwise improvment when in being able to generate a character in a specific pose as compared to trying to coax SD into giving you an approximation of what you wanted through Prompt Engineering.

People training and releasing custom models that can replace entire workflows of disparate steps needed to produce an image that would normally result from that workflow.

There was that video or maybe it was an article where the guy made it so he could just use natural language to describe the edits he wanted made and it would make them etc.

Re: Tech’s hottest new job: Prompt engineer

#102

Post by mycall »

ThrowawayTestr wrote: post #94
vba616 wrote: post #84

Earlier quoted context omitted.

How do you know?

Because I tried the code and it worked.

There are lots of people with misconceptions of LLMs. It will take time to adjust.

I reached the same conclusion as yourself, but do see a totally different path to take regarding information propagation (how GPT works). For example, cells merge information monotonically. This is how neural networks balance too, but could be applied in new/undiscovered ways.

https://www.youtube.com/watch?v=HB5TrK7A4pI&list=LL&index=4

Re: Tech’s hottest new job: Prompt engineer

#105

Post by grufus »

krackers wrote: post #92
superdisk wrote: post #8

I just can't believe how idiotic such a thing is. It's like calling a person who uses a toaster a Toast Engineer with a salary of 300k.

>This morning, I brushed and flossed, which makes me a Plaque Removal Engineer. I then used my skills as a Room Tidyness Engineer to make the bed. After that, I engineered the harness onto my dog and took her on a walk: Canine Fitness Engineer. I engineered the water to a higher temperature using the kettle, and poured it over some coffee grounds to create a chemical reaction in my morning brew: Yeah, that's right, C…

> At this point the word "engineer" has lost its original meaning. Until there's a formal theory of how we can interact with LLMs and you make use of that in a systematic fashion, "prompt engineering" is really closer to "prompt artist."

Interesting angle. Are you saying there are rarely any "software engineers" out there, that they are all merely "software artists"? Cause none of these uses a formal theory for their craft. If they were then all those highly opinionated discussions of whether to use goto in C or what are the greatest flaws of node.js would just not exist.

Re: Tech’s hottest new job: Prompt engineer

#106

Post by grufus »

super256 wrote: post #81
TrackerFF wrote: post #50

Earlier quoted context omitted.

Not too different from analysts writing SQL queries all day long.

Complex SQL requires knowledge about relational algebra (Cartesian products, set theory, domain relational calculus yada yada) and understanding of how RDBMS and their query planners work. At least, if performance is important to you. I don't see this in this prompt engineering. In my limited experience (I played a few hours with Stable Diffusion and more hours with the OAI davinci-003 model), you can get good at it…

[flagged]

Re: Tech’s hottest new job: Prompt engineer

#107

Post by grufus »

Art9681 wrote: post #96

Reading the comments here, there is something to be said about how much naysaying there is in regard to this technology. I should expect it. You see the same pattern everywhere in one way or another. I urge people to shift their mindsets and approach cutting edge technology from a perspective of what it could be in the future, vs what it is today. What I mean is, by the time you realize something has fundamentally ch…

> I urge people to shift their mindsets and approach cutting edge technology from a perspective of what it could be in the future, vs what it is today

Maybe they realized that too many jumped on the blockchain BS train.

Re: Tech’s hottest new job: Prompt engineer

#108

Post by teaearlgraycold »

grufus wrote: post #106
super256 wrote: post #81

Earlier quoted context omitted.

Complex SQL requires knowledge about relational algebra (Cartesian products, set theory, domain relational calculus yada yada) and understanding of how RDBMS and their query planners work. At least, if performance is important to you. I don't see this in this prompt engineering. In my limited experience (I played a few hours with Stable Diffusion and more hours with the OAI davinci-003 model), you can get good at it…

[flagged]

I don’t think that’s Dunning-Kruger but I get what you’re saying.

Re: Tech’s hottest new job: Prompt engineer

#109

Post by TrackerFF »

super256 wrote: post #81
TrackerFF wrote: post #50

Earlier quoted context omitted.

Not too different from analysts writing SQL queries all day long.

Complex SQL requires knowledge about relational algebra (Cartesian products, set theory, domain relational calculus yada yada) and understanding of how RDBMS and their query planners work. At least, if performance is important to you. I don't see this in this prompt engineering. In my limited experience (I played a few hours with Stable Diffusion and more hours with the OAI davinci-003 model), you can get good at it…

At this point, we're very much at an exploratory stage of LLM queries - you could of course be a ML/DL researcher or engineer that's intimately knowledgeable with the current architectures, but still - they're very large and very complex due to the sheer parameter size, so you'd still have to map out what inputs will predictably give what outputs on a finished model.

I'd imagine that being a "prompt engineer" entails finding out and mapping the structures that gives you the desired result. Think of it as a novice user of search engines VS expert user of search engines.

Re: Tech’s hottest new job: Prompt engineer

#110

Post by krackers »

grufus wrote: post #105
krackers wrote: post #92

Earlier quoted context omitted.

>This morning, I brushed and flossed, which makes me a Plaque Removal Engineer. I then used my skills as a Room Tidyness Engineer to make the bed. After that, I engineered the harness onto my dog and took her on a walk: Canine Fitness Engineer. I engineered the water to a higher temperature using the kettle, and poured it over some coffee grounds to create a chemical reaction in my morning brew: Yeah, that's right, C…

> At this point the word "engineer" has lost its original meaning. Until there's a formal theory of how we can interact with LLMs and you make use of that in a systematic fashion, "prompt engineering" is really closer to "prompt artist." Interesting angle. Are you saying there are rarely any "software engineers" out there, that they are all merely "software artists"? Cause none of these uses a formal theory for their…

Correct, in my eyes "software engineering" in the sense of "person who glues libraries together to build systems" should not yet be called an engineering discipline because there isn't yet a rigorous enough theory on why something should be designed one way as opposed to another. We are still in the stage of figuring out best practices and making things more rigorous (maybe the functional programming folks will end up contributing something here, but I don't know enough about category theory).

There are other narrower senses of "software engineer" such as "person who optimizes code" and to me those more qualify as engineering because we not only have a decent enough theoretical background (see Agner Fog's work) but also can experimentally verify things. On the other hand it's a lot harder to quantitatively say if one design is better than another.

I think there's also some work in terms of rigorously modeling concurrent/distributed systems (Lamport's TLA+) work which I'd like to see more of.

Post reply on HN