How does it differ other than that people aren't currently choosing to write clear, well-defined high-level specs and feeding that into their agent?
I don't think I've seen a Sol 5.6 or later model fail at a task with a verifiable outcome.
It's when I try to do too little of the defining that I get LLM bugs. In which case maybe programming hasn't changed that much, LLMs really can be reliable compilers, and we're all just being lazy.
I don't really care about what "most engineers" do. I did phrase it lazily but I am trying to point out something fundamental about LLMs and compilers.
The model itself is more or less a black box - if tokens come out that you don't like, it seems like there's no equivalent to "this LLVM release fixed a code generation issue on platform X relating to situation Y".
I'm not sure why people are so motivated to say these are the same thing when they are clearly not.
And yes, rigorous approaches can be taken to systems built on and with LLMs, as you say. That doesn't make them the same as compilers.
LLMs are not magic things that are out of your control, they are simply complicated. But there are concrete issues that are identified, people sit down and decide to fix it, build evals, run ablations, and they produce a model without that deficiency. It happens every day.
I suppose if LLVM's source code has a similar size in bytes then it would be similarly difficult to work with. However, it would still remain source code readable by a human, not binary data with no semantic content when examined plainly.
https://www.linkedin.com/pulse/coding-agents-idea-compilers-...