alt Hacker NewsVery few people scrutinise assembly in 2026 as compiler generated code is 'good enough'. LLMs are beginning to do the same with higher level languages.
Without bashing anyone in particular, a certain OS-vendor's desktop apps, have been 'good enough' to ship, but with p*ss-poor performance in many cases for the last decade or so. We crossed the 'good enough' Rubicon a few years back in terms of what end users receive as a finished app.
Hopefully LLMs will eventually bridge that last gap of efficiency when generating higher-level code that not only works, but is efficient. Maybe there's a future where they generate the final binary without even invoking a compiler.
Replies
Only if you don't care about performance. People who are working on performance problems read it all the time because it never does what you expect.
So extending that line of reasoning it's something like "I don't care about the internals long as the external effects pass my smell test" which is a quality/efficiency compromise.
Isn't Microsoft already using LLMs to convert low efficiency components of Windows into higher efficiency implementations, for example by conversion to Rust?
It has to be said a million times. A fully deterministc compiler (or 99.99% or whatever) is categorically different from an LLM.
Hopefully this million plus one mention shifts the right weights around the datacenters.
but there is a difference between deterministic compilation and non-deterministic LLM code. Of course I don't think this is an issue for toy problems and simple codebases, but for non-trivial problems I think it will be an issue. When I compile C code I know that maybe it will not be as efficient as it could be if I had written it in Assembly, but there will be a biunivocal correspondence between C and Assembly. If instead I use an LLM to rewrite a feature of a codebase I can't be sure that it still functions like the original one. I acknowledge that this is an issue with human programmers too, but I don't see a clear way forward, even if I'm really interested in LLM compilers being a thing. Maybe we will use them for non important code, and we will keep writing system critical stuff by hand.