There's an enormous lump of complexity that this chap seems to be unaware of: the type system. This is the semantic analysis bit that he seems to think is done by LLVM, but it isn't.
It's like he mostly thinks of compilers as turning statements and expressions into executable code, but IMO that's one of the easier bits. Defining how different values interact, what operations are legal and aren't, and the runtime support - this is a lot of work, and in particular, it's different for every language, because it's what makes languages distinct.
I think she's a woman not a "chap". But anyways, you'd be relying on the IR semantics and checking to do the legwork for you. LLVM IR is a language after all.
It's like he mostly thinks of compilers as turning statements and expressions into executable code, but IMO that's one of the easier bits. Defining how different values interact, what operations are legal and aren't, and the runtime support - this is a lot of work, and in particular, it's different for every language, because it's what makes languages distinct.