Programming

26563 readers

382 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

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

snowe@programming.dev

Ategon@programming.dev

UlrikHD@programming.dev

bugsmith@programming.dev

Spyro@programming.dev

245

I just tried vibe coding with Claude (programming.dev)

submitted 1 week ago by entwine@programming.dev to c/programming@programming.dev

141 comments fedilink hide all child comments

...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

[–] alex_riv@lemmy.org 1 points 8 hours ago

my experience has been similar for complex tasks but the sweet spot for me is small, well-defined scripts where i can verify the output easily.

like: i needed to parse some music metadata and normalize it across a few formats. gave it a spec, it produced something that mostly worked. i spent maybe 20 minutes fixing edge cases instead of 3 hours writing it from scratch. that exchange of time is what sold me.

for 3d math where correctness is hard to verify at a glance, i wouldn't trust it either. the tool is only as useful as your ability to test its output quickly.