Programming languages, design languages and architecture are all inventions made to help humans write understandable source. LLMs don’t really need to do any of that. They can store very large trees of understanding and therefore implement any application in raw binary. Why bother with abstractions at all

▲

jeltz 4 days ago | parent | next [-]

LLMs for sure need those things. maybe not the same abstractions as humans do but without understabdable code an LLM will just fail to accomplish the task you ask it to do.

▲

flir 4 days ago | parent | prev [-]

It might be less ambitious and more practical to target bytecode.

But you effectively lose the human review component.

▲

_1 4 days ago | parent | next [-]

There's more python and typescript in the training data than bytecode.

	▲	flir 4 days ago \| parent [-]
		I was thinking about that. I reckon generating massive amounts of synthetic training data for that goal should be possible - you've already got the Python, after all. It's also possible for machine code, but you'd have to target more platforms. But ultimately, I think human readability outweighs any theoretical advantage you get from removing a step in the compilation process.

▲

redox99 4 days ago | parent | prev [-]

Targeting byte code or asm instead of high level would be silly for everyday tasks. You blow up the number of tokens, reduce your effective context, and there's just more places for it to make a mistake, which most likely won't be caught by the assembler (unlike compilers).