| ▲ | ToyKeeper 3 hours ago |
| It's funny to see someone using a LLM as a compiler, making it convert higher-level operations into assembly, instead of just using a compiler. |
|
| ▲ | vitally3643 23 minutes ago | parent | next [-] |
| Given how few programmers very seriously write lots of assembly, it's kind of astonishing how good LLMs are at working with assembly. They can compile and decompile all on their own with apparently very little effort. I suspect (with zero proof or understanding) that this has something to do with how well C maps to assembly. It's not a stretch to say the model's vector space maps this chunk of assembly with that line of C. And we all know how much C code exists online. |
|
| ▲ | pjmlp 2 hours ago | parent | prev | next [-] |
| Eventually that will be the way, revenge of COBOL and 4GLs. |
|
| ▲ | duskwuff 37 minutes ago | parent | prev | next [-] |
| "Congratulations! You've reimplemented compilers, except slower, less reliable, hopelessly proprietary, and you have to pay to use it." (Oh, and the "compiler" will also refuse to operate on certain types of programs.) |
|
| ▲ | idiotsecant 2 hours ago | parent | prev [-] |
| There is evidence that LLMs are capable of making assembly that runs a great deal more efficiently than the compiler can manage on its own. |
| |
| ▲ | wild_egg 2 hours ago | parent | next [-] | | There are a ton of optimization opportunities that hinge on the intent of a piece of code which static compilers can never detect at scale. LLMs can actually navigate that and write surprisingly optimal assembly. I've had all my side projects being written in x64 for the last 6 months and it is shockingly effective. | |
| ▲ | kibwen an hour ago | parent | prev | next [-] | | The purpose of an optimizing compiler is not merely to produce efficient assembly. The goal of an optimizing compiler is to produce efficient assembly while confidently preserving a program's observable logical semantics. Asking an LLM to spit out raw unstructured assembly based on inferred context from a specification given in English is a contender for one of the worst ideas I have ever heard; I award you no points, and may God have mercy on your soul. | | |
| ▲ | vitally3643 14 minutes ago | parent [-] | | Code is code my dude. If an LLM can turn English into Python, there's really no reason it can't do assembly. Assembly is not magic, it's just code that humans find difficult to grok. LLMs, it would seem, don't have the same kind of trouble understanding assembly that humans do. Have you ever compiled something by hand? You should try sometime, it's an illuminating experience. Humans find it hard because you have to remember a lot of details while simultaneously paying attention to a different large set of information while also generating instructions. It's tough, but not impossible, it takes humans a lot of time and effort. How might a computer fare if it could remember everything and pay attention to multiple inputs and outputs at once? That's what an LLM does. |
| |
| ▲ | Agingcoder an hour ago | parent | prev | next [-] | | Do you have references ? | |
| ▲ | throwaway613746 an hour ago | parent | prev [-] | | [dead] |
|