"AI code generators are like compilers for translating natural language into a programming language" – I have heard and read this unfitting analogy quite a few times already.
It is misleading, as it sweeps a crucial technical point under the carpet and downplays some of the more serious consequences for people who have to deal with AI-generated code.
Compilers are deterministic, usually generating functionally equivalent code for a given input program on every run, according to language specifications.
Programmers usually do not have to check the machine code or the assembly code a native compiler generates, as its behavior is well-specified and, with mature compilers, also well-tested.
Programmers can expect the compiler to "just work", transforming code that is comparatively easy to read and write for humans into a form that is simpler for the machine to process, but difficult to read for humans.
Also, assuming the input code is written in a standardized language and uses its features in a well-defined way, switching compilers is relatively easy.
Yes, AI code generators also transform something that is easier to read – in this case natural language – into something that is simpler for the machine to process – in this case program code.
However, this is where the similarity ends.
The path from given prompt input to output code is practically inscrutable, warranting a lot more skepticism about the result.
In the general case, can you expect to get functionally equivalent code with the same prompts every time? No!
Can you even expect correct output? No!
So as you may know, I've been getting interested in CRDTs lately. For the uninitiated, CRDTs (Conflict-Free Replicated Data types) are fancy programming tools which let multiple users edit the same data at the same tim
I’ve always loved building tools and platforms, and have long been fascinated with the world of operating systems. Apart from reading through the source code (where that’s legally available, of course…) I think there’s no better way to explore and understand a system - and the mindset that produced it - than to develop for it.
What follows is a brain-dump of what I’ve learned about developing for the AmigaOS, both on classic 68k-powered hardware to modern PowerPC systems like the X5000. I’ll cover development environments, modern workflows like CI builds on containerised infrastructure, distribution of packages and even a look back in time before C existed, thanks to AmigaDOS’s odd heritage.
Now that I’ve provided you with an introduction to Git and a brief overview of using Git with GitHub, it’s time to build on that knowledge by taking a closer look at one workflow often used when collaborating with Git. The “fork and branch” workflow is a common way of collaborating on open source projects using Git and GitHub. In this post, I’m going to walk through this workflow (as I understand it—I’m constantly learning), with a focus toward helping those that are new to this sort of thing.