[m-users.] (cough) "AI"
Mark Brown
mark at mercurylang.org
Sun Oct 26 13:42:40 AEDT 2025
Hi Tomas,
On Sun, Oct 26, 2025 at 7:31 AM Tomas By <tomas at basun.net> wrote:
>
> Hi all,
>
> Just read this on Slashdot:
>
> | I'm a programmer who started out hesitant about AI, and at first I
> | thought all that it could do was auto-complete better.
> | Then I tried Claude Code, and it really is like having your own
> | personal junior dev assisting you're every need. Like a junior, it
> | makes mistakes, but using the *massive* amount of good code that it
> | creates, and fixing what's left, is so much faster than writing it
> | all from scratch yourself.
> https://slashdot.org/story/25/10/25/0324244/meet-the-people-who-dare-to-say-no-to-ai
>
> and wonder if anybody has tried this with Mercury?
>
> I suspect that (1) this person uses C[*]/Java, and (2) the usefulness
> of this "AI" stuff for Mercury will be proportionally less in a
> similar magnitude as code length for same functionality, ie a factor
> ten or so.
>
> Anybody has any experiences?
At my work we've been trying out AI for a few things, for example
using Claude to generate a test plan for some CSS specs, for a user
agent that does pagination. I'm impressed with the results in this
case: it seems to give a good overall idea of the areas of coverage
required, as well as identifying priority areas, providing test
templates, and giving guidance on best practices for writing tests.
To me this sort of thing looks to be a far more effective use for AI
right now than generating code. For one thing it's a mature project
and relatively little of the code is being written from scratch, which
is the premise of the above comment. Development proceeds in
iterations, so most of the code being written needs to be tightly
integrated with what is already there. More generally, I only spend a
fraction of my time actually writing the code: I spend more time and
resources reading and analysing the code and its behaviour, studying
the specs, and desperately trying to understand what the users expect
the software to actually do! Getting help with these things is more
important than the actual coding.
Generating low-level code from a high-level description is, after all,
what the Mercury compiler already does :-)
Cheers,
Mark
>
> /Tomas
> _______________________________________________
> users mailing list
> users at lists.mercurylang.org
> https://lists.mercurylang.org/listinfo/users
More information about the users
mailing list