this post was submitted on 05 Feb 2025
380 points (97.3% liked)

Greentext

4975 readers
1100 users here now

This is a place to share greentexts and witness the confounding life of Anon. If you're new to the Greentext community, think of it as a sort of zoo with Anon as the main attraction.

Be warned:

If you find yourself getting angry (or god forbid, agreeing) with something Anon has said, you might be doing it wrong.

founded 1 year ago
MODERATORS
 
you are viewing a single comment's thread
view the rest of the comments
[–] SkunkWorkz@lemmy.world 49 points 4 hours ago (3 children)

Yeah fake. No way you can get 90%+ using chatGPT without understanding code. LLMs barf out so much nonsense when it comes to code. You have to correct it frequently to make it spit out working code.

[–] threeduck@aussie.zone 3 points 43 minutes ago (3 children)

Are you guys just generating insanely difficult code? I feel like 90% of all my code generation with o1 works first time? And if it doesn't, I just let GPT know and it fixes it right then and there?

[–] surph_ninja@lemmy.world 2 points 19 minutes ago

A lot of people assume their not knowing how to prompt is a failure of the AI. Or they tried it years ago, and assume it’s still as bad as it was.

[–] UnsavoryMollusk@lemmy.world 1 points 32 minutes ago

Garbage for me too except for basic beginners questions

[–] Earflap@reddthat.com 1 points 39 minutes ago

Can not confirm. LLMs generate garbage for me, i never use it.

[–] dilroopgill@lemmy.world 1 points 59 minutes ago

deepseek rnows solid, autoapprove works sometimes lol

[–] xor@lemmy.dbzer0.com 1 points 3 hours ago (1 children)

i guess the new new gpt actually makes code that works on the first time

[–] Eheran@lemmy.world 4 points 2 hours ago (1 children)

You mean o3 mini? Wasn't it on the level of o1, just much faster and cheaper? I noticed no increase in code quality, perhaps even a decrease. For example it does not remember things far more often, like variables that have a different name. It also easily ignores a bunch of my very specific and enumerated requests.

[–] xor@lemmy.dbzer0.com 2 points 2 hours ago (2 children)

03 something… i think the bigger version….
but, i saw a video where it wrote a working game of snake, and then wrote an ai training algorithm to make an ai that could play snake… all of the code ran on the first try….
could be a lie though, i dunno….

[–] Bronzebeard@lemm.ee 1 points 32 minutes ago

Asking it to write a program that already exists in it's entirety with source code publicly posted, and having that work is not impressive.

That's just copy pasting

[–] Eheran@lemmy.world 2 points 2 hours ago

o3 yes perhaps, we will see then. Would be amazing.