www.digitalmars.com         C & C++   DMDScript  

digitalmars.D - D Lang and Vibe Coding

reply Derrick J <microbrainz gmail.com> writes:
First off, hats off to everyone who makes and maintains this 
project! I am not a professional programmer of any sort, more 
like an enthusiast who hasn't had the time to get up to speed as 
I got older. I did buy the Vibe.d book back in the day trying to 
learn though. Now, AI is upon us and as an IT generalist I like 
to learn and keep up with new and emerging technology and have 
devoted time toward learning how to use locally hosted and cloud 
based models, as well as vibe coding tools and I have stumbled 
across something interesting.

Using a few different AI coding tools (where I could get free 
trials) have coded a 3D Print Tracking system with Vibe.d running 
as the API backend that feeds the node next.js frontend and it 
works incredibly well! In my current dev environment, I am using 
the sql lite library. It is lightning fast and npm offers an 
expansive set of prebuilt features that makes building up a 
productive prototype much easier. The coding tools seem to for 
the most part do well at writing D code (model dependant), I have 
had some instances where it was running into a syntax issue and 
it did a quick search of the dlang webpage and was able to figure 
out it's error. I was able to make it create tests and fix the 
errors if the tests failed which seemed to really help the coding 
agent make more reliable code. Mixing my 3D Printing hobby and 
vibe coding has allowed me to scratch my own itch and see just 
how far these tools can be pushed. Which has been a lot further 
than I has previously thought.

I have read through some of the posts here over the years and I 
can tell that there is some pessimism about the future of the 
language, and as a layman I don't know the nitty details of what 
you go through. But I wanted to tell you that what you have built 
here is impressive and worthy of respect! Thank you for providing 
fertile ground to pursue learning about and building with these 
tools!
Oct 30
next sibling parent reply Dejan Lekic <dejan.lekic gmail.com> writes:
On Thursday, 30 October 2025 at 18:42:58 UTC, Derrick J wrote:

 I have read through some of the posts here over the years and I 
 can tell that there is some pessimism about the future of the 
 language, and as a layman I don't know the nitty details of


Ignore those guys. Many of them actually love D too much for 
their own good. :)

Future of D is Bright. Pun intended.
Oct 30
next sibling parent reply monkyyy <crazymonkyyy gmail.com> writes:
On Thursday, 30 October 2025 at 18:55:22 UTC, Dejan Lekic wrote:

 
 Future of D is Bright. Pun intended.


He's kinda old and his management philosophy is "complain 
sometimes about 80 bit floats, but Im never telling anyone what 
to do", I have doubts there will be any change in speed of dev. 
Can you train an old dog without a shock collar? Walter will do 
as he been doing; and insanity is expecting different results.

If d has a future its with opend or one of *many* children 
languages it has spawned.
Oct 30
next sibling parent reply Derrick J <microbrainz gmail.com> writes:
On Friday, 31 October 2025 at 01:53:44 UTC, monkyyy wrote:

 On Thursday, 30 October 2025 at 18:55:22 UTC, Dejan Lekic wrote:

 
 Future of D is Bright. Pun intended.


 He's kinda old and his management philosophy is "complain 
 sometimes about 80 bit floats, but Im never telling anyone what 
 to do", I have doubts there will be any change in speed of dev. 
 Can you train an old dog without a shock collar? Walter will do 
 as he been doing; and insanity is expecting different results.

 If d has a future its with opend or one of *many* children 
 languages it has spawned.


I see that you are listed on the OpenD GitHub repo. It looks like 
you are nearly a year in forking the code and making a new 
standard library. It doesn't look like there has been much 
progress with it. It would seem to me that you are more upset 
that things aren't going the way that you would like because 
having to write it yourself is a lot more work than just 
complaining. The person who pays the bills, makes the rules. 
Whatever he's doing seems to be working, we're here aren't we!?
Oct 30
next sibling parent reply monkyyy <crazymonkyyy gmail.com> writes:
On Friday, 31 October 2025 at 04:57:08 UTC, Derrick J wrote:

 On Friday, 31 October 2025 at 01:53:44 UTC, monkyyy wrote:

 On Thursday, 30 October 2025 at 18:55:22 UTC, Dejan Lekic 
 wrote:

 
 Future of D is Bright. Pun intended.


 He's kinda old and his management philosophy is "complain 
 sometimes about 80 bit floats, but Im never telling anyone 
 what to do", I have doubts there will be any change in speed 
 of dev. Can you train an old dog without a shock collar? 
 Walter will do as he been doing; and insanity is expecting 
 different results.

 If d has a future its with opend or one of *many* children 
 languages it has spawned.


 I see that you are listed on the OpenD GitHub repo. It looks 
 like you are nearly a year in forking the code and making a new 
 standard library. It doesn't look like there has been much 
 progress with it. It would seem to me that you are more upset 
 that things aren't going the way that you would like because 
 having to write it yourself is a lot more work than just 
 complaining. The person who pays the bills, makes the rules. 
 Whatever he's doing seems to be working, we're here aren't we!?


Why are you psychoanalyzing me before having a single interaction 
with me. I suggest getting a daybed and asking about my childhood.

Most of the progress in opend is adr and mojo; not me, and by all 
means compare it. Adr really should self promote more; he is 
quite the work horse. I was never confident that I could write an 
std solo and said as much to anyone who would listen; I tried to 
start, no one followed, I lost motivation.
Oct 30
parent reply Derrick J <microbrainz gmail.com> writes:
On Friday, 31 October 2025 at 05:34:02 UTC, monkyyy wrote:

 On Friday, 31 October 2025 at 04:57:08 UTC, Derrick J wrote:

 On Friday, 31 October 2025 at 01:53:44 UTC, monkyyy wrote:

 On Thursday, 30 October 2025 at 18:55:22 UTC, Dejan Lekic 
 wrote:

 
 Future of D is Bright. Pun intended.


 He's kinda old and his management philosophy is "complain 
 sometimes about 80 bit floats, but Im never telling anyone 
 what to do", I have doubts there will be any change in speed 
 of dev. Can you train an old dog without a shock collar? 
 Walter will do as he been doing; and insanity is expecting 
 different results.

 If d has a future its with opend or one of *many* children 
 languages it has spawned.


 I see that you are listed on the OpenD GitHub repo. It looks 
 like you are nearly a year in forking the code and making a 
 new standard library. It doesn't look like there has been much 
 progress with it. It would seem to me that you are more upset 
 that things aren't going the way that you would like because 
 having to write it yourself is a lot more work than just 
 complaining. The person who pays the bills, makes the rules. 
 Whatever he's doing seems to be working, we're here aren't we!?


 Why are you psychoanalyzing me before having a single 
 interaction with me. I suggest getting a daybed and asking 
 about my childhood.

 Most of the progress in opend is adr and mojo; not me, and by 
 all means compare it. Adr really should self promote more; he 
 is quite the work horse. I was never confident that I could 
 write an std solo and said as much to anyone who would listen; 
 I tried to start, no one followed, I lost motivation.


No, just noting how you seem to be using this forum as a place to 
promote a project that looks dead on arrival and trying to point 
out that a project like that needs a lot more than just a few 
developers, it needs a vibrant community and money. If you feel 
so strongly about it, create content online that gets people 
excited. It is a toxic trait to just complain all of the time. I 
am old enough to remember a time where the goal was to always 
build people up, not to tear them down to fill some gap in their 
own psyche. Get a therapist, find real life a community of people 
to support you, etc. Getting onto every thread to complain is not 
the way. Read the room, I just wanted to share something that I 
figured out, that maybe doesn't get talked about very much here. 
That many people dread the idea of even. Things are good, there 
is a way forward, and all you can see is the deficits. We're all 
on a journey to be better today than yesterday.
Oct 31
parent reply Serg Gini <kornburn yandex.ru> writes:
On Friday, 31 October 2025 at 14:44:55 UTC, Derrick J wrote:

 No, just noting how you seem to be using this forum as a place


How many r's in a word "strawberry"?
Oct 31
next sibling parent Derrick J <microbrainz gmail.com> writes:
On Friday, 31 October 2025 at 14:54:21 UTC, Serg Gini wrote:

 On Friday, 31 October 2025 at 14:44:55 UTC, Derrick J wrote:

 No, just noting how you seem to be using this forum as a place


 How many r's in a word "strawberry"?


That's an odd question to ask, are you trying to say that because 
they haved failed at this in the past, that they always will? 
They are pretty good at working around problems these days. Here 
is what Gemini 2.5 Pro had to say (I including their "thinking"):

Considering Character Counts

I've been examining a straightforward string operation: counting 
'r' occurrences in "strawberry." Python code seems like the ideal 
approach here, and I'm currently leaning towards that solution 
for its simplicity and effectiveness.

Evaluating Code Solutions

I've determined that Python code is the most efficient method for 
this task. It's a direct computation, so a search wouldn't be 
useful. I'm focused now on crafting the Python code to count the 
'r's in "strawberry." The output should be the integer count.

Providing the Result

I've completed the code execution, and the final tally of "r"s in 
"strawberry" is in. The program functioned perfectly, confirming 
three occurrences. Now, I'm ready to share the accurate answer.

The word "strawberry" contains 3 'r's.
Oct 31
prev sibling parent monkyyy <crazymonkyyy gmail.com> writes:
On Friday, 31 October 2025 at 14:54:21 UTC, Serg Gini wrote:

 On Friday, 31 October 2025 at 14:44:55 UTC, Derrick J wrote:

 No, just noting how you seem to be using this forum as a place


 How many r's in a word "strawberry"?


holy shit, fake urls and everything
Oct 31
prev sibling parent reply GrimMaple <grimmaple95 gmail.com> writes:
On Friday, 31 October 2025 at 04:57:08 UTC, Derrick J wrote:
ages it has spawned.

 I see that you are listed on the OpenD GitHub repo. It looks 
 like you are nearly a year in forking the code and making a new 
 standard library. It doesn't look like there has been much 
 progress with it. It would seem to me that you are more upset 
 that things aren't going the way that you would like because 
 having to write it yourself is a lot more work than just 
 complaining. The person who pays the bills, makes the rules. 
 Whatever he's doing seems to be working, we're here aren't we!?


What I don't understand is why people are so reluctant on
seeing the point and just stick their head
in the sand and go "no you're wrong we're fine".

OpenD wasn't really made to bring in as many new features as 
possible;
in fact, it had quite an opposite goal - to bring in _stability_ 
to the
lang, because at the time every new DMD release would break or 
deprecate
something that was in the wild. Mind you, at the time releases 
were much more
common too; having a new release almost every month compared to 
just 2 (!)
releases this year. (Btw, still not seeing anything wrong with 
that? :)

Regarding your original post,


 Using a few different AI coding tools


I tried vibecoding D as well, but it yielded poor results. I use 
LLMs for

I think
it would be possible to circumvent the wrong sin tax and 
hallucinations -
at some point the LLM was trying to convince me that std.zip 
doesn't exist,
and when I pointed out that it does - it just started making up 
stuff. But
I'd much rather just use a lang that Works (tm), instead of 
having to endlessly
fight a loosing battle against the compiler and tooling around it.

Honestly, the whole D experience is like this - trying to 
circumvent stuff,
while in other langs things Just Work (tm). In retro spec, I 
think D would
have benefited much more from a working auto-completion server 
than from
Import C or the dreaded borrow checker.
Oct 31
next sibling parent Derrick J <microbrainz gmail.com> writes:
On Friday, 31 October 2025 at 08:12:47 UTC, GrimMaple wrote:

 On Friday, 31 October 2025 at 04:57:08 UTC, Derrick J wrote:
 ages it has spawned.

 I see that you are listed on the OpenD GitHub repo. It looks 
 like you are nearly a year in forking the code and making a 
 new standard library. It doesn't look like there has been much 
 progress with it. It would seem to me that you are more upset 
 that things aren't going the way that you would like because 
 having to write it yourself is a lot more work than just 
 complaining. The person who pays the bills, makes the rules. 
 Whatever he's doing seems to be working, we're here aren't we!?


 What I don't understand is why people are so reluctant on
 seeing the point and just stick their head
 in the sand and go "no you're wrong we're fine".

 OpenD wasn't really made to bring in as many new features as 
 possible;
 in fact, it had quite an opposite goal - to bring in 
 _stability_ to the
 lang, because at the time every new DMD release would break or 
 deprecate
 something that was in the wild. Mind you, at the time releases 
 were much more
 common too; having a new release almost every month compared to 
 just 2 (!)
 releases this year. (Btw, still not seeing anything wrong with 
 that? :)

 Regarding your original post,


 Using a few different AI coding tools


 I tried vibecoding D as well, but it yielded poor results. I 
 use LLMs for

 issues. I think
 it would be possible to circumvent the wrong sin tax and 
 hallucinations -
 at some point the LLM was trying to convince me that std.zip 
 doesn't exist,
 and when I pointed out that it does - it just started making up 
 stuff. But
 I'd much rather just use a lang that Works (tm), instead of 
 having to endlessly
 fight a loosing battle against the compiler and tooling around 
 it.

 Honestly, the whole D experience is like this - trying to 
 circumvent stuff,
 while in other langs things Just Work (tm). In retro spec, I 
 think D would
 have benefited much more from a working auto-completion server 
 than from
 Import C or the dreaded borrow checker.


The unlock for me was realizing that the coding agents really 
seem to work well when they have documents that they can follow, 
detailing step by step what they need to accomplish with spaces 
to check of their work and very detailed directions what success 
looks like and how to debug and troubleshoot. I came across a 
youtube channel that showed have they develop full applications 
with AI and that was the process. I had developed a web app in 
Firebase Studio, mainly because it was free when you used a free 
tier Gemini API key. I got down to a pretty sophisticated system 
and after digging into the cost structure, I really didn't like 
the limited control and one demand pricing structure if I went 
over their free allowance. So I took that entire chat history and 
had Gemini create a PRD and TODO documents detailing step by step 
what to implement. I have had some ups and downs along the way, 
but when the backend Vibe.d program compiled and the front end 
was able to query it and retrieve and store data I knew that I 
was onto something.

I use VScode and use the DLang extensions that runs a full syntax 
checker. I have it utilize DFMT in order to make sure that the 
source files are formatted properly, and it writes unit tests to 
verify expected functionality. There were times where they failed 
and it had to correct the code to get it to pass. So far I have 
trialed Windsurf, Zencode, Gemini Coding Assistant, and Github 
Copilot. Each has certain strengths and weaknesses. Goodle Gemini 
Code CLI works really well, but consumes tokens pretty quickly, 
but the free key can get you pretty far. Github CoPilot has a 
pretty generous "Premium" AI allotment with several models to 
switch between. Claude Code works pretty good, GPT 4.1 is not 
great, but the newest models work pretty well. After I ran out of 
premium AI tokens, I find that GPT 5 Mini works really well and 
has unlimited tokens. I haven't used Claude Code CLI but the 
videos I have seen, it is very feature rich, including the 
ability to call other AI models via cli tools. The models are 
only part of mix, the extension or client that hosts the MCP 
servers is an important element as to how well it will be able to 
read and write files locally, retrieve webpages or run search 
queries if it needs help resolving an issue, which I have found 
that they can find what they need from the DLANG website and 
generally resolve their errors.

Like any tool it is how you wield the tool that makes it 
effective or not. I was kind of down on it too as I just lacked 
the creativity to specify what I wanted. That was until I 
realized that I could use a chatbot to create those files for me 
based off what I described, it could then fill in the blanks to 
go from idea to implementation. Now I am just making a web app. I 
don't know how well it is going to code something low level like 
a compression or crytography algorithm. I can't imagine it will 
work very well, even with explicit step by step directions, but 
maybe it would surprise us using a multi-model approach that used 
the models best for the task on same project. Just my 2 cents 
anyway, I'm not trying to push anything, just sharing what I've 
learned.

I've read in other posts how D lang can be interfaces with 
llama.c which interesting and exciting. You can build an app with 
local intelligence built in. Something that I want to play around 
with at some point. Maybe make my app be able to make suggestions 
to the user or something. There are some very small models that 
can easily run on a standard system with good performance and 
decent enough intelligence.
Oct 31
prev sibling parent monkyyy <crazymonkyyy gmail.com> writes:
On Friday, 31 October 2025 at 08:12:47 UTC, GrimMaple wrote:

 
 I tried vibecoding D as well, but it yielded poor results.


I got acceptable results resently with kaps lib which presumably 
isnt in the traning set at all. I think this had to do with him 
providing a cheatsheet or if not agents got better at finding 
apis.

I think the issue will be tech debt manigment, im seeing instant 
scripts but unable to follow instructions on how to compile a 
project.
Oct 31
prev sibling parent reply Kapendev <alexandroskapretsos gmail.com> writes:
On Friday, 31 October 2025 at 01:53:44 UTC, monkyyy wrote:

 Can you train an old dog without a shock collar?


Um... Are you a Hasan Piker fan?
Oct 31
parent reply Kapendev <alexandroskapretsos gmail.com> writes:
On Friday, 31 October 2025 at 11:09:09 UTC, Kapendev wrote:

 On Friday, 31 October 2025 at 01:53:44 UTC, monkyyy wrote:

 Can you train an old dog without a shock collar?


 Um... Are you a Hasan Piker fan?


BTW no answer... very sus...

![sus](https://media1.tenor.com/m/M6OS8r2GGHwAAAAd/nekoella-ella-neko.gif)
Oct 31
parent monkyyy <crazymonkyyy gmail.com> writes:
On Friday, 31 October 2025 at 15:51:40 UTC, Kapendev wrote:

 On Friday, 31 October 2025 at 11:09:09 UTC, Kapendev wrote:

 On Friday, 31 October 2025 at 01:53:44 UTC, monkyyy wrote:

 Can you train an old dog without a shock collar?


 Um... Are you a Hasan Piker fan?


 BTW no answer... very sus...

 ![sus](https://media1.tenor.com/m/M6OS8r2GGHwAAAAd/nekoella-ella-neko.gif)


As we all know Im far left, of course I love the best left wing 
streamer
Oct 31
prev sibling parent Derrick J <microbrainz gmail.com> writes:
On Thursday, 30 October 2025 at 18:55:22 UTC, Dejan Lekic wrote:

 On Thursday, 30 October 2025 at 18:42:58 UTC, Derrick J wrote:

 I have read through some of the posts here over the years and 
 I can tell that there is some pessimism about the future of 
 the language, and as a layman I don't know the nitty details of


 Ignore those guys. Many of them actually love D too much for 
 their own good. :)

 Future of D is Bright. Pun intended.


Yeah, it comes with the territory I suppose. Thank you for your 
reply!
Oct 30
prev sibling parent reply Kapendev <alexandroskapretsos gmail.com> writes:
On Thursday, 30 October 2025 at 18:42:58 UTC, Derrick J wrote:

 code. Mixing my 3D Printing hobby and vibe coding has allowed 
 me to scratch my own itch and see just how far these tools can 
 be pushed. Which has been a lot further than I has previously 
 thought.


Interesting project. I haven't really used AI for code, but I 
like some things I have seen with it. It helped me write a script 
recently.


 I have read through some of the posts here over the years and I 
 can tell that there is some pessimism about the future of the 
 language, and as a layman I don't know the nitty details of 
 what you go through.


We are all a bit dramatic sometimes :)
Oct 30
parent Derrick J <microbrainz gmail.com> writes:
On Thursday, 30 October 2025 at 19:57:57 UTC, Kapendev wrote:

 On Thursday, 30 October 2025 at 18:42:58 UTC, Derrick J wrote:

 code. Mixing my 3D Printing hobby and vibe coding has allowed 
 me to scratch my own itch and see just how far these tools can 
 be pushed. Which has been a lot further than I has previously 
 thought.


 Interesting project. I haven't really used AI for code, but I 
 like some things I have seen with it. It helped me write a 
 script recently.


 I have read through some of the posts here over the years and 
 I can tell that there is some pessimism about the future of 
 the language, and as a layman I don't know the nitty details 
 of what you go through.


 We are all a bit dramatic sometimes :)


Yeah, I really got started with AI in any real way was when I 
started using Google Gemini. When I fed it different ideas that I 
had and it built me a quick one file prototype. For work, they 
needed an app for taking messages from the clients who live in 
the facility. I grew up using Visual Basic and the WYSIWYG form 
builder was always just more intuitive to me and I struggled with 
creating the UI just as code. When I was trying to use the YAML 
for DotNet library, I was struggling finding detailed code 
examples and so I was getting stuck and making little progress 
until I remembered I had Gemini Pro to use and with it I was able 
to get it all to work and so the system is actually implemented 
and running right now. I was also working on rules for Wazuh and 
was able to make progress on understanding how that system worked 
and how to create rules and code the scripts to respond to those 
events. I was able to get to the point where it could detect that 
an unwanted file extension had been written to the user folder 
(ex: executables) and to then delete it automatically.

It is an excellent tool, I don't really talk to it more than 
working through problems that I am trying to solve. I have 
experimented a little bit with running self hosted models, and 
connecting n8n workflows to achieve different things in a low 
code manner. Sometimes I will have Gemini create Javascript as a 
"glue" node if needed. It is an exciting future with a lot of 
things to be mindful of and a lot of ways in which it can go 
wrong, but for now it is a tool that is amplifying what I am 
capable of on my own.
Oct 30