Re: EDG open source C++ front end

From	anton@mips.complang.tuwien.ac.at
Newsgroups	comp.compilers
Subject	Re: EDG open source C++ front end
Date	2026-10-07 07:10 +0000
Organization	Compilers Central
Message-ID	<26-10-008@comp.compilers> (permalink)
References	<26-10-002@comp.compilers> <26-10-003@comp.compilers> <26-10-004@comp.compilers> <26-10-006@comp.compilers> <26-10-007@comp.compilers>

Show all headers | View raw

Derek M Jones <derek@knosof.co.uk> writes:
>Anton,
>
>> My sentence was phrased in a misleading way.  What I meant is: Not the
>> prompts (or not only), but primarily the generated code is stored in
> > the version control systems.
>
>Imagine if, when high level languages were new, that companies
>stored the compiler generated assembler in the version control system,
>rather than the source code.

Why would they?  The compiler always produces the same binary from the
source code.

>It is the specification used to generate the source that needs to
>be stored.
>
>The source is currently stored because coding agents are unreliable,

The prompts are not a complete specification, and that's why
unreliability is inherent in LLM code generation.  The superpower of
LLMs is that it takes a request that is missing a lot of things, and
guesses the missing things based on the stuff in the training data.
But the guesses can vary, so the unreliability is inherent in this
development model.

There is also the other unreliability where an LLM produces some stuff
that is not aligned with what is explicitly asked for in the prompt,
and maybe they will get that fixed (or, hopefully not; imagine what
will happen once our oligarchs no longer need humans to build and
control their machines, including swarms of killer drones, because the
machines are reliably aligned with the oligarchs' prompts).

>Going to assembler will certainly require more tokens.

That's a good reason to keep higher-level languages.

>Can coding agents generate smaller and/or more efficient assembler
>compared to going via source/compiler?

Even if they can, for most programs, and for the largest part of the
rest, efficiency is not important, and higher-level languages will be
used for that code in order to reduce token costs.

>>        What about human review that still happens AFAIK?  What about
>> programs that need to run on several architectures?
>
>The review should happen at the specification stage.

It's a benefit of LLMs that the need for a complete specification is
avoided, but that means that reviewing at the prompt level is
insufficient, even if the alignment problem is solved.

- anton
--
M. Anton Ertl
anton@mips.complang.tuwien.ac.at
http://www.complang.tuwien.ac.at/anton/

Back to comp.compilers | Previous — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

EDG open source C++ front end Derek M Jones <derek@knosof.co.uk> - 2026-10-02 23:05 +0100
  Re: EDG open source C++ front end anton@mips.complang.tuwien.ac.at - 2026-10-03 16:01 +0000
    Re: EDG open source C++ front end Derek M Jones <derek@knosof.co.uk> - 2026-10-04 13:40 +0100
      Re: EDG open source C++ front end anton@mips.complang.tuwien.ac.at - 2026-10-05 17:33 +0000
        Re: EDG open source C++ front end Derek M Jones <derek@knosof.co.uk> - 2026-10-06 22:00 +0100
          Re: EDG open source C++ front end anton@mips.complang.tuwien.ac.at - 2026-10-07 07:10 +0000
  Re: EDG open source C++ front end Cóilín Nioclásín Glostéir <thanks-to@Taf.com> - 2026-10-05 16:55 +0000

csiph-web