This article is spot on. I'm feeling the exact same way watching the industry aggressively promote the idea that it's safe to deploy unverified code just because an AI wrote the tests.
We are playing with fire. If we keep treating "I don't read the code I ship" as a feature rather than a liability, it's going to cause a massive, real-world disaster. The resulting regulation will be so heavy that software engineering will end up needing a Bar Council or Medical Board just to ship a basic feature. We're cheering for a trend that is going to regulate us into a corner.
But people code also cause real world disasters; most human programmers are terrible, never held accountable (they usually left a while ago), they cannot read/comprehend code (either) and cannot write tests (either). Only in a echo chamber like HN you can believe that the majority human programmers are any good / better than a 1bit 7B model ; they are not. Go out in the real world; most people are really really bad at what they do, including programmers.
> It’s just incapable of the thing that makes a real architect valuable: saying “no.”
I have had Claude many times tell me "not really, here's a better way" when asked "hey Claude, is this a good idea?". Granted, Claude would just do it if I just asked it to just do it, but that's by design. LLMs, at least today, are capable of pushing back, if suitably prompted.
That's an incredibly thorough analysis. And if we wanted to be even more picky: why on earth would we want to form so many opinions about the world using a single LLM model?
This article is spot on. I'm feeling the exact same way watching the industry aggressively promote the idea that it's safe to deploy unverified code just because an AI wrote the tests.
We are playing with fire. If we keep treating "I don't read the code I ship" as a feature rather than a liability, it's going to cause a massive, real-world disaster. The resulting regulation will be so heavy that software engineering will end up needing a Bar Council or Medical Board just to ship a basic feature. We're cheering for a trend that is going to regulate us into a corner.
But people code also cause real world disasters; most human programmers are terrible, never held accountable (they usually left a while ago), they cannot read/comprehend code (either) and cannot write tests (either). Only in a echo chamber like HN you can believe that the majority human programmers are any good / better than a 1bit 7B model ; they are not. Go out in the real world; most people are really really bad at what they do, including programmers.
> It’s just incapable of the thing that makes a real architect valuable: saying “no.”
I have had Claude many times tell me "not really, here's a better way" when asked "hey Claude, is this a good idea?". Granted, Claude would just do it if I just asked it to just do it, but that's by design. LLMs, at least today, are capable of pushing back, if suitably prompted.
"The craft still matters" - may be, but nobody is paying for it anymore. So, let that Jenga tower wobble ...
> I’m not saying don’t use AI agents. I use Claude Code every day.
It shows, man. You even had it write this article for you.
That's an incredibly thorough analysis. And if we wanted to be even more picky: why on earth would we want to form so many opinions about the world using a single LLM model?