“No Duh,” say senior developers everywhere.
The article explains that vibe code often is close, but not quite, functional, requiring developers to go in and find where the problems are - resulting in a net slowdown of development rather than productivity gains.
There’s some real perks to using AI to code - it helps a ton with templatable or repetitive code, and setting up tedious tasks. I hate doing that stuff by hand so being able to pass it off to copilot is great. But we already had tools that gave us 90% of the functionality copilot adds there, so it’s not super novel, and I’ve never had it handle anything properly complicated at all successfully (asking GPT-5 to do your dynamic SQL calls is inviting disaster, for example. Requires hours of reworking just to get close.)
More reliable ones.
Deterministic ones
So much of the AI hype has been pointing to ten year old technology repackaged in a slick new interface.
AI is the iPod to the Zune of yesteryear.
Repackaging old technology in slick new interfaces is what we have been calling progress in computer software for 40+ years.
I mean… I like to think we’ve done a bit more than that. FFS, file compression alone has made leaps and bounds since the 3.25" floppy days.
Also, as a T-SQL guy, I gotta say there’s a world of difference between SQL 2008 and SQL 2022.
But I’ll spot you that a lot of the last 10-15 years has produced herculean efforts in answering the question “How can we squeeze a few more ads into your GUI?”
There have been a few “milestone moments” like map-reduce Hadoop, etc. Still, there’s a whole lot of eye candy wrapped around the same old basic concepts.
Fair, I’ve used it recently to translate a translations.ts file to Spanish.
But for repetitive code, I feel like it is kind of a slow down sometimes. I should have refactored instead.
This is a thing people miss. “Oh it can generate repetitive code.”
OK, now who’s going to maintain those thousands of lines of repetitive unit tests, let alone check them for correctness? Certainly not the developer who was too lazy to write their own tests and to think about how to refactor or abstract things to avoid the repetition.
If someone’s response to a repetitive task is copy-pasting poorly-written code over and over we call them a bad engineer. If they use an AI to do the copy-paste for them that’s supposed to be better somehow?
Some code is boilerplate and can’t be distilled down more. It’s nice to point an AI to a database schema and say “write the Django models, admin, forms, and api for this schema, using these authentication permissions”. Yeah I’ll have to verify it’s done right, but that gets a lot of the boring typing out of the way.
I use it for writing code to call APIs and is a huge boon.
Yeah, you have to check the results, but it’s way faster than me.
Similarly I find it very useful for if I’ve written a tool script and really don’t want to write the command line interface for it.
“Here’s a well-documented function - write an argparser for it”
…then I fix its rubbish assumptions and mistakes. It’s probably not drastically quicker but it doesn’t require as much effort from me, meaning I can go harder on the actual function (rather than keeping some effort in reserve to get over the final hump).