this post was submitted on 11 Apr 2026
161 points (89.7% liked)

Programming

26473 readers
430 users here now

Welcome to the main community in programming.dev! Feel free to post anything relating to programming here!

Cross posting is strongly encouraged in the instance. If you feel your post or another person's post makes sense in another community cross post into it.

Hope you enjoy the instance!

Rules

Rules

  • Follow the programming.dev instance rules
  • Keep content related to programming in some way
  • If you're posting long videos try to add in some form of tldr for those who don't want to watch videos

Wormhole

Follow the wormhole through a path of communities !webdev@programming.dev



founded 2 years ago
MODERATORS
 

...and I still don't get it. I paid for a month of Pro to try it out, and it is consistently and confidently producing subtly broken junk. I had tried doing this before in the past, but gave up because it didn't work well. I thought that maybe this time it would be far along enough to be useful.

The task was relatively simple, and it involved doing some 3d math. The solutions it generated were almost write every time, but critically broken in subtle ways, and any attempt to fix the problems would either introduce new bugs, or regress with old bugs.

I spent nearly the whole day yesterday going back and forth with it, and felt like I was in a mental fog. It wasn't until I had a full night's sleep and reviewed the chat log this morning until I realized how much I was going in circles. I tried prompting a bit more today, but stopped when it kept doing the same crap.

The worst part of this is that, through out all of this, Claude was confidently responding. When I said there was a bug, it would "fix" the bug, and provide a confident explanation of what was wrong... Except it was clearly bullshit because it didn't work.

I still want to keep an open mind. Is anyone having success with these tools? Is there a special way to prompt it? Would I get better results during certain hours of the day?

For reference, I used Opus 4.6 Extended.

you are viewing a single comment's thread
view the rest of the comments
[–] RamenJunkie@midwest.social 1 points 1 hour ago

Yeah, I wonder sometimes if people who fail tonget usable code are

1- Asking it to do much at once.

2- Don't actually understand the problem or coding enough to ask it to do the right thing.

If you say, "Write a program that does X", it will most likely fail to give you what you want.

It works great if you break it down into parts.

Write a program that takes this databas input and converts it this way.

Now uodate it so the output gets displayed this way.

Adjust the colors.

Add the ability to save the output in this format.

This looks good but I need to swap these parts of the output and add this data to the output.

That sort of iterative, step by step process. Or even just, when there are bugs, give it the error output, explain that X needs to be Y. Also, at some point you may need to also look at the code. I had an issue where it was running twice on some data and after looking at it I realized it was processing things as images and links, because the links had images (but images did not always have links). I explained this problem, and pointed to where it was and it fixed it.