Comment by Krssst
15 hours ago
OS and compilers have a deterministic public interface. They obey a specification developers know, so you they can be relied on to write correct software that depends on them even without knowing the internal behavior. Generative AI does not have those properties.
Yes but developers don’t have a deterministic interface. I still had to be careful about writing out my specs and make sure they were followed. At least I don’t have to watch my tone when my two mid level ticket taking developers - Claude and Codex - do something stupid. They also do it a lot faster
But the code you’re writing is guard railed by your oversight, the tests you decide on and the type checking.
So whether you’re writing the spec code out by hand or ask an LLM to do it is besides the point if the code is considered a means to an end, which is what the post above yours was getting at.
Tests and type checking are often highway-wide guardrails when the path you want to take is like a tightrope.
Also the code is not a means to an end. It’s going to be run somewhere doing stuff someone wants to do reliably and precisely. The overall goal was ever to invest some programmer time and salary in order to free more time for others. Not for everyone to start babysitting stuff.
> They obey a specification developers know
Which spec? Is there a spec that says if you use a particular set of libraries you’d get less than 10 millisecond response? You can’t even know that for sure if you roll your own code, with no 3rd party libraries.
Bugs are by definition issues arise when developers expect they code to do one thing, but it does another thing, because of unforeseen combination of factors. Yet we all are ok with that. That’s why we accept AI code. They work well enough.
> Is there a spec that says if you use a particular set of libraries you’d get less than 10 millisecond response?
There can be. But you’d have to map the libraries to opcodes and then count the cycles. That’s what people do when they care about that particular optimization. They measure and make guaranties.
That’s not realistic with any processor that does branch prediction, cache hits vs cache misses etc
3 replies →