LLMs as Compilers

Summary

LLMs as compilers7/2/2025 by KadhirSo far, I've only used LLMs as an assistant, where I'm doing something, and an LLM helps me along the way. Code autocomplete feels like a great example of how useful it can be when it gets it right. I don't doubt that over time this will improve, but I'm excited to see a more significant transition from this assistant mode to a compiler mode, at least for coding.It will be exciting when we focus solely on the context we fed the LLM, then test the features it generates rather than the code. And importantly, we let the LLM handle integrating new features into the existing codebase. That means we no longer examine the code. Our time as engineers will be spent handling context, testing features, and iterating on them.The consequence of that seems to be:Democratize access to engineeringYou don't need as specialized skillsets to build complex apps, you just need to know how to put context together and iterateIncrease the velocity of feature developmentMy gut says dealing with context will result in a better ratio of engineering time into features shipped than dealing with code directlyThe obvious pushback here is, well, compilers are provable. There's a straightforward mapping between inputs and outputs, and we can prove the outputs are the same each time. We can also write tests to ensure the outputs are optimized.But if we squint, a compiler transforms an input into an output. If we treat the code as an intermediate layer, viewing the input as context and the output as features, then we can demonstrate that the compiler is reliable through evaluations and testing. And importantly, we don't have to get the output right in the first go, we can let it iterate over and over until it gets it right. A new kind of compiler.So I propose that if we get LLM-as-a-compiler, as a software engineer, I will go through this cycle:Put together the contextWhich includes a series of tests for the final behavior (perhaps I use an LLM for this)I put it thr...