I tried to AI a project at work. Once.

Yes it did the job but it had poor error handling, logging and zero standardization/structure.

I tried again with writing a template file with my own code snippets and blocks.

It did better. Still nowhere near done, but I used that as a first draft. I'd say half done to my standard. Deleted/reworked/added code.

I guess it saved time at that point. Still can't see a whole ass project being full AI gen.

Didn't catch the cases in which it failed.

And the ERP troglodytes don't seem to have tests, no. Obviously not for our stuff (unless they're testing to make sure it breaks), and it certainly doesn't look like they do any kind of testing for theirs either.

Good luck my dude!

Thanks.

Hope is at some point they'll break something important enough that the boss will consider that it's costlier to keep doing business with them than to migrate everything. 🤷‍♂️

Meanwhile we're porting as much as we can to in-house solutions. Trying to minimise the amount of work needed to transition away from them.

I'm in the same boat, although the vibe coders where I'm at are a bit more put together so sometimes they do get something out that's not entirely half baked but generally only CRUD apps.

They are however using it A LOT for research which is a huge fucking problem. I've had to read a bunch of "vibe papers recently" and it's been a mess.

Very unhappy.

Your not alone, Ive stopped using LLMs for any of my work. It's doesn't have any net value gains for me. The work is shittier, more expensive in the long run, less secure, I don't grow as a developer, and locks us in to using LLMs more.

Edit: and to add I am not old by any means

Sorry 2 mil in dollars. I should have specified.

I do like the specification and differentiation between llms and ai. Good point.

Good luck with that when management is dumb and only looks at number of lines committed and PRs reviewed. Then those who commit with reckless abandon and rubber-stamp PRs are seen as superstars while those who take care are seen as slow and holding up the process.

I remember when the numbers of lines of code per developer were a thing. Or fix in one go, where test failures counted against devs ratings. This is neither the beginning nor the end of shitty KPIs mandated by clueless management.

There's a reason the term "protoduction" was coined.

I don't grow as a developer

This for me. I code for computational physics stuff and I feel like it's when I implement stuff that I find out if I really understand things.

So many people at work are just implementing shitloads of useless shit entirely by Claude, while complaining about people using their codes as black boxes.