this post was submitted on 01 Apr 2025

723 points (98.8% liked)

Programmer Humor

22222 readers

1645 users here now

Welcome to Programmer Humor!

This is a place where you can post jokes, memes, humor, etc. related to programming!

For sharing awful code theres also Programming Horror.

Rules

Keep content in english
No advertisements
Posts must be related to programming or programmer topics

founded 2 years ago

MODERATORS

[email protected]

723

Junior Prompt Engineering (lemmy.ml)

submitted 3 days ago by [email protected] to c/[email protected]

54 comments fedilink hide all child comments

top 50 comments

sorted by: hot top controversial new old

[–] [email protected] 9 points 2 days 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)

[–] [email protected] 218 points 3 days ago (1 children)

Tech guy invents the concept of giving instructions

[–] [email protected] 113 points 3 days ago (1 children)

With clear requirements and outcome expected

Why did no one think of this before

[–] [email protected] 19 points 3 days ago

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

[–] [email protected] 73 points 3 days ago (1 children)

Relevant xkcd:

[–] [email protected] 5 points 2 days ago (2 children)

Who even makes these comics? Is it like Simpsons

[–] [email protected] 6 points 2 days ago (2 children)

Web browsing 101: if you see a hyperlink on social media, you can click on it and then look around to see if it contains more links with useful information, often in the header or footer of the page. Here I found one for you: https://xkcd.com/about/

[–] [email protected] 0 points 2 days ago

Sorry, I assumed this was a place of discussion and conversation. You can either be helpful or don't, it's generally considered a dick move to taunt while being helpful.

[–] [email protected] 2 points 2 days ago* (last edited 2 days ago)

Human communication 101: sometimes humans ask a question without expecting an answer, it's called a rhetorical question

[–] [email protected] 16 points 2 days ago* (last edited 2 days ago) (2 children)

Randall Munroe. You may know him from such gems as xkcd 3472 and 6548.

[–] [email protected] 1 points 2 days ago (1 children)

https://xkcd.com/3472 and https://xkcd.com/6548

FTFY

[–] [email protected] 2 points 7 hours ago* (last edited 7 hours ago) (1 children)

This is weird, it's just directing me to the 404th comic? https://www.explainxkcd.com/wiki/index.php/404:_Not_Found

[–] [email protected] 1 points 2 hours ago* (last edited 2 hours ago)

You have be more patient, those ones will take a while to load.

[–] [email protected] 6 points 2 days ago

Getting a bit ahead of yourself, we're only on 3070 so far!

[+] [email protected] -7 points 3 days ago (3 children)

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

[–] [email protected] 4 points 3 days 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.

[–] [email protected] 35 points 3 days 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

[–] [email protected] 7 points 3 days ago

You're right, my bad.

[–] [email protected] 3 points 3 days 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

[–] [email protected] -3 points 3 days 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.

[–] [email protected] 2 points 3 days ago* (last edited 3 days 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.

[–] [email protected] 5 points 3 days 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.

load more comments