Junior Prompt Engineering : programmer

[–] kayzeekayzee@lemmy.blahaj.zone 224 points 2 months ago (1 children)

Tech guy invents the concept of giving instructions

[–] ripcord@lemmy.world 119 points 2 months ago (1 children)

With clear requirements and outcome expected

Why did no one think of this before

[–] wtckt@lemm.ee 23 points 2 months ago

Who does that? What if they do everything right and it doesn't work and then it turns out it's my fault?

[–] bjoern_tantau@swg-empire.de 126 points 2 months ago (5 children)

It would be nice if it was possible to describe perfectly what a program is supposed to do.

[–] orvorn@slrpnk.net 83 points 2 months ago (1 children)

Someone should invent some kind of database of syntax, like a... code

[–] heavydust@sh.itjust.works 39 points 2 months ago (2 children)

But it would need to be reliable with a syntax, like some kind of grammar.

[–] peoplebeproblems@midwest.social 26 points 2 months ago (1 children)

That's great, but then how do we know that the grammar matches what we want to do - with some sort of test?

[–] Natanael@infosec.pub 22 points 2 months ago (1 children)

How to we know what to test? Maybe with some kind of specification?

[–] maiskanzler@feddit.nl 2 points 2 months ago* (last edited 2 months ago)

People could give things a name and write down what type of thing it is.

[–] monkeyslikebananas2@lemmy.world 5 points 2 months ago (1 children)

A codegrammar?

[–] Knock_Knock_Lemmy_In@lemmy.world 11 points 2 months ago

We don't want anything amateur. It has to be a professional codegrammar.

[–] spankmonkey@lemmy.world 19 points 2 months ago* (last edited 2 months ago) (1 children)

What, like some kind of design requirements?

Heresy!

[–] bjoern_tantau@swg-empire.de 8 points 2 months ago (3 children)

Design requirements are too ambiguous.

[–] spankmonkey@lemmy.world 10 points 2 months ago

Design requirements are what it should do, not how it does it.

[–] heavydust@sh.itjust.works 5 points 2 months ago

That's why you must negotiate or clarify what is being asked. Once it has been accepted, it is not ambiguous anymore as long as you respect it.

[–] psud@aussie.zone 2 points 2 months ago

I'm a systems analyst, or in agile terminology "a designer" as I'm responsible for "design artifacts"

Our designs are usually unambiguous

[–] drew_belloc@programming.dev 9 points 2 months ago (2 children)

What did you said?

[–] rayquetzalcoatl@lemmy.world 8 points 2 months ago (1 children)

I think our man meant in terms of real-world situations

[–] heavydust@sh.itjust.works 2 points 2 months ago (1 children)

And NOT yet another front page written in ReactJS.

[–] peoplebeproblems@midwest.social 1 points 2 months ago

Oh, well, that's good, because I have a ton of people who work with Angular and not React.

[–] xthexder@l.sw0.com 5 points 2 months ago* (last edited 2 months ago) (1 children)

This still isn't specific enough to specify exactly what the computer will do. There are an infinite number of python programs that could print Hello World in the terminal.

[–] drew_belloc@programming.dev 2 points 2 months ago

I knew it, i should've asked for assembly

[–] Venator@lemmy.nz 3 points 2 months ago

Yeah but that's a lot of writing. Much less effort to get the plagiarism machine to write it instead.

[–] peoplebeproblems@midwest.social 1 points 2 months ago (1 children)

Ha

None of us would have jobs

[–] MentalEdge@sopuli.xyz 10 points 2 months ago

I think the joke is that that is literally what coding, is.

[–] Lime66@lemmy.world 75 points 2 months ago

Relevant xkcd:

[–] undefinedValue@programming.dev 27 points 2 months ago (4 children)

OP just chatting with themselves so they can screenshot it?

[–] mexicancartel@lemmy.dbzer0.com 16 points 2 months ago (1 children)

That is some telegram group and both messages shows from left with profile icons(which got cropped). The screenshot person sent the last message which shows double ticks

[–] andrybak@startrek.website 4 points 2 months ago

In the desktop client the positions of bubbles also depend on the width of the window.

[–] bleistift2@sopuli.xyz 3 points 2 months ago

Great attention to detail!

[–] Talia@feddit.it 2 points 2 months ago (1 children)

That's just a fake conversation in general, look at the timestamps between the messages from the interlocutor. Several minutes to type a complete sentence?

[–] StellarSt0rm@lemmy.world 2 points 2 months ago

Hey, i can take a few hours to reply sometimes :c

[–] pufferfisherpowder@lemmy.world -1 points 2 months ago* (last edited 2 months ago)

Could be a group chat but we all know they're a twat

[–] Appoxo@lemmy.dbzer0.com 7 points 2 months ago

I wrote a shell script like this (it admin , notna dev) for private use.
The prompt took me like 5 hours of rewriting the instructions.
Don't even know yet if it works (lol)

[+] TrickDacy@lemmy.world -8 points 2 months ago (2 children)

Neural network: for when saying LLM doesn't sound smart enough

[–] raina@sopuli.xyz 10 points 2 months ago

It's just what it was called in the nineties.

[–] xigoi@lemmy.sdf.org 1 points 2 months ago

LLMs are a type of neural networks.

[+] kn0wmad1c@programming.dev -9 points 2 months ago (3 children)

Calling GPT a neural network is pretty generous. It's more like a markov chain

[–] brian@programming.dev 36 points 2 months ago (1 children)

it legitimately is a neutral network, I'm not sure what you're trying to say here. https://en.wikipedia.org/wiki/Generative_pre-trained_transformer

[–] kn0wmad1c@programming.dev 7 points 2 months ago

You're right, my bad.

[–] frezik@midwest.social 4 points 2 months ago

I've played with markov chains. They don't create serious results, ever. ChatGPT is right just often enough for people to think it's right all the time.

[–] peoplebeproblems@midwest.social 3 points 2 months ago (1 children)

The core language model isn't a nueral network? I agree that the full application is more Markov chainy but I had no idea the LLM wasn't.

Now I'm wondering if there are any models that are actual neutral networks

[–] kn0wmad1c@programming.dev -4 points 2 months ago (2 children)

I'm not an expert. I'd just expect a neural network to follow the core principle of self-improvement. GPT is fundamentally unable to do this. The way it "learns" is closer to the same tech behind predictive text in your phone.

It's the reason why it can't understand why telling you to put glue on pizza is a bad idea.

[–] lime@feddit.nu 6 points 2 months ago

the main thing is that the system end-users interact with is static. it's a snapshot of all the weights of the "neurons" at a particular point in the training process. you can keep training from that snapshot for every conversation, but nobody does that live because the result wouldn't be useful. it needs to be cleaned up first. so it learns nothing from you, but it could.

[–] frezik@midwest.social 2 points 2 months ago* (last edited 2 months ago)

"Improvement" is an open ended term. Would having longer or shorter toes be beneficial? Depends on the evolutionary environment.

ChatGPT does have a feedback loop. Every prompt you give it affects its internal state. That's why it won't give you the same response next time you give the same prompt. Will it be better or worse? Depends on what you want.

Programmer Humor

Rules