The proliferation of nondeterministically generated code is here to stay. Part of our response must be more dynamic, more comprehensive and more realistic workload simulation and testing frameworks.
replies(5):
AI is also great at looking for its own quality problems.
Yesterday on an entirely LLM generated codebase
Prompt: > SEARCH FOR ANTIPATTERNS
Found 17 antipatterns across the codebase:
And then what followed was a detailed list, about a third of them I thought were pretty important, a third of them were arguably issues or not, and the rest were either not important or effectively "this project isn't fully functional"
As an engineer, I didn't have to find code errors or fix code errors, I had to pick which errors were important and then give instructions to have them fixed.
The limit of product manager as "extra technical context" approaches infinity is programmer. Because the best, most specific way to specify extra technical context is just plain old code.
> A large percentage (at least 50%) of the market for software developers will shift to lower paid jobs focused on managing, inspecting and testing the work that outsourced developers do. If a median software developer job paid $125k before, it'll shift to $65k-$85k type outsourced developer babysitting work after.
This argument is common and facile: Software development has always been about "automating ourselves out of a job", whether in the broad sense of creating compilers and IDEs, or in the individual sense that you write some code and say: "Hey, I don't want to rewrite this again later, not even if I was being paid for my time, I'll make it into a reusable library."
> the same thing
The reverse: What pisses me off is how what's coming is not the same thing.
Customers are being sold a snake-oil product, and its adoption may well ruin things we've spent careers de-crappifying by making them consistent and repeatable and understandable. In the aftermath, some portion of my (continued) career will be diverted to cleaning up the lingering damage from it.
(It’s been said that Swift concurrency is too hard for humans as well though)
A good software engineering system built around the top LLMs today is definitely competitive in quality to a mediocre software shop and 100x faster and 1000x cheaper.
If it works 85% of the time, how soon do you catch that it is moving in the wrong direction? Are you having a standup every few minutes for it to review (edit) it's work with you? Are you reviewing hundreds of thousands of lines of code every day?
It feels a bit like pouring cement or molten steel really fast: at best, it works, and you get things done way faster. Get it just a bit wrong, and your work is all messed up, as well as a lot of collateral damage. But I guess if you haven't shipped yet, it's ok to start over? How many different respins can you keep in your head before it all blends?