(disclaimer: I'm a software engineer with minimal compiler theory experience outside classes in college) I wonder whether its possible to trust an LLM to "compile" your code to an executable and trust that the compiled code is faithful to the input without writing a static validator that is pretty much a compiler itself.
> I wonder whether its possible to trust an LLM to "compile" your code to an executable and trust that the compiled code is faithful to the input without writing a static validator that is pretty much a compiler itself.
"LLMs as compilers" do not make any sense.
Traditional compilers must be deterministic to compile to the correct machine code for the correct architecture otherwise the executable will break.
One parallel could be using ml for simulations to not write or compute all the rules
The title is even more meaningless given that such a suggestion sounds totally at fundamental odds with today's state of the art compilers which need to be deterministic.
Replacing today's compilers, linkers and assemblers with LLMs (which are fundamentally stochastic preditcion models) for the use-case to compile software (not just generating correct code syntax) makes absolutely no sense whatsoever.
> Their formal education/background is in ML however.
Maybe whoever this person is should read up on what the Gell-Mann Amnesia Effect is.
Ask any compiler author on this very suggestion and they will question if this person is really a "Principal Engineer".