(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.
This seems like such a jerk move to reply to someone who worked hard and is excited about something to essentially try to tell them it was worthless. Whether an LLM will ever actually be appropriate as a compiler or not, the reply from Chen Fang is in such poor taste.
Don't take it seriously, It is Twitter bait from an intern.
> 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.
Think speed could be a potential benefit. Why go through source -> llvm ir -> binary with linking and all the other stuff? Think I’m bearish on the concept, but who knows?
One parallel could be using ml for simulations to not write or compute all the rules
canttestthis|3 months ago
(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.
tuxracer|3 months ago
rvz|3 months ago
> 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.
tjr|3 months ago
eyeris|3 months ago
One parallel could be using ml for simulations to not write or compute all the rules