It wasn’t just on principle that those changes were rejected, they also stated the bun changes were not actually that great or general enough to upstream.
> I’d say that, in all the ways that matter, I understand the code. Sure, if I had to hand-edit it now, there’d be a serious learning curve. But I won't have to.
Famous last words, but point is taken.
The non deterministic nature of an llm breaks the metaphor that they are like a compiler.
However, it’s not foreign to compilers to receive feedback from the running program (PGOs), so there are still parallels to the feedback we provide LLMs that guide their “optimization”.
I think even calling LLMs a non-deterministic compiler isn’t accurate either so ultimately I agree the metaphor doesn’t quite work.
I do think LLMs are like compilers in terms of how they changed how we build programs from a historical context. But that’s about it.
The non-determinism is theoretical solvable. Chaos (prompt instability) isn’t. When you change a single word in the input, you get a completely different output. Because of this LLMs will never be compilers.
There’s not much of a difference because open models are distilling from frontier models. If frontier models cease to exist then many of these open models will as well
reply