News for hackers. Stuff that matters.
Re:LLMs could be, but shouldn't be compilers by sureglymop on Friday February 06, 2026 @11:07AM (#46914561)
Don't LLMs create the same outputs based on the same inputs if the temperature is 0? Maybe I'm just misunderstanding.
Re:LLMs could be, but shouldn't be compilers by AlotOfReading on Friday February 06, 2026 @12:30PM (#46915663)
Unfortunately not. Various implementation details like attention are usually non-deterministic. This is one of the better blog posts I'm aware of:

https://thinkingmachines.ai/blog/defeating-nondeterminism-in...

Re:LLMs could be, but shouldn't be compilers by 8note on Friday February 06, 2026 @09:50PM (#46920861)
i dont think theres anything that makes it essentiall that llms are non-deterministic though

if you rewrote the math to be all fixed point precision on big ints, i think you would still get the useful LLM results?

if somebody really wanted to make a compiler in an LLM, i dont think that nondetermism is problem

id really imagine an llm compiler being a set of specs, dependency versions, and test definitions to use though, and you'd introduce essential nondetermism by changing a version number, even if the only change was the version name from "experimental" to "lts"

Re:LLMs could be, but shouldn't be compilers by AlotOfReading on Saturday February 07, 2026 @04:18PM (#46928148)
They're not inherently non-deterministic, correct. And floating point is deterministic enough, as that blog post is demonstrating.
Re:LLMs could be, but shouldn't be compilers by h3lp on Tuesday February 10, 2026 @11:36AM (#46962412)
When they run on the deterministic hardware, yes. When they run on some large, parallel, varying-unpredictable-load-dependent-latency hardware, no.