Where's Christoph?

[David Healey]

@dannytaurus said in Where's Christoph?:

HISE's pitch is 'build plugins without writing C++

I make sample libraries rather than plugins. For me HISE is an alternative to Kontakt, not an alternative to C++. If I use an LLM I'd just be asking it to recreate a worse version of HISE. Instead I use it to enhance HISE to make it better meet my requirements.

[dannytaurus]

@David-Healey Sample libraries are indeed notably absent from the current deluge of vibe-coded plugins.

It's another current differentiator - our willingness and ability to accurately sample acoustic instruments or vintage/esoteric hardware.

But I think that'll go away quite soon too. The moat is shrinking every day.

[griffinboy]

@dannytaurus

Personally I think one of the really good things about Hise is that it's free. And that it wraps Juce.
And so at no cost you can start learning what you need to know about plugin development without being dropped completely in the deep end.

I think there are plenty of people who are still interested in the process of developing audio technology, and I think that HISE fills a useful gap for beginners of this kind.

Personally I was never interested in the codeless aspect, I wanted to get into the weeds with DSP from the start, I just found plain Juce so dry and dull to work in when I was starting out.

Of course, now I don't use Juce either, I ended up going down the Kilohearts/Fabfilter route and use my own plugin core. But HISE (and every other platform / library I used) paved the way to where I am now.
In the present day, a fair chunk of my income comes from rewriting vibecoded projects, and creating LLM harnesses. But if HISE hadn't been around, I likely wouldn't have gotten over the initial tediousness of Juce, which was a necessary first step in eventually reaching the point where I know enough to work on new agentic coding technology.

This is just my personal perspective. Which is probably alternate to many people here.

[dannytaurus]

@griffinboy I appreciate your viewpoint, but I think HISE is quite hostile to beginners.

Don't get me wrong - I'm glad it exists, and it certainly beats tackling bare JUCE. But just look at a handful of posts in this forum from beginners to see how much everyone struggles.

And yeah, you're definitely in the minority. The depths that you dive is quite amazing!

[resonant]

@dannytaurus Frankly, it is clear that the companies behind frontier AI models—such as Claude or ChatGPT—are currently operating at a loss, despite investing billions of dollars and even striking deals to purchase energy from nuclear power plants.

If they are incurring such losses even with $100 subscription tiers, I believe it will be impossible to access AI at these price points in the future. It may not happen immediately, but eventually, AI will no longer be easily accessible; the current state of affairs is simply a strategy to get everyone accustomed to using it.

When that moment arrives—when the AI ​​"tap" is turned off—the true value of skilled coders will become apparent, and HISE will stand out as an essential piece of software that must always remain available. Yes HISE is pain in the ass for beginners, that’s for sure. But this forum is also supportive for beginners, that’s for sure too.

For this reason, I believe it is far too early to draw any definitive conclusions

[David Healey]

@resonant said in Where's Christoph?:

AI will no longer be easily accessible

If the companies remain unprofitable I think you are right that those particular options will become unavailable. But self-hosted models are not going anywhere and people are working to make more efficient and less energy hungry AI systems, if they can do that without losing capability then OpenAI, Anthropic, and similar will find it easier to become profitable because their costs will be lower - but also there will be competitors which is probably why they keep pushing for regulation.

[resonant]

@David-Healey I’ve also tested local models for audio plugin coding; right now, they don’t even come close to frontier models.

That doesn’t mean they’re entirely useless, though—they can still be quite effective for lighter tasks. They aren’t suitable for our specific line of work, at least for the time being. However, if they advance enough in the future, that could change significantly.

Furthermore, there are no local models currently on par with frontier models; and for frontier models to function as fully capable, end-to-end problem solvers, they require terabytes of RAM and GPU memory—far beyond the capacity of a standard computer.

There is also another fact that, NVIDIA is practically on the verge of dropping gamers from its customer base, as AI companies are purchasing GPUs on a much larger, more profitable scale. This suggests that, in the future, users like us might find it increasingly difficult to get our hands on custom-built PCs, as the prices for hardware—especially RAM—are trending toward extreme increases.

[dannytaurus]

@resonant Local is the future.

We'll all look back with humour at the time we had to subscribe monthly to get access to LLMs and System One models.

[dannytaurus]

@resonant said in Where's Christoph?:

When that moment arrives—when the AI ​​"tap" is turned off—the true value of skilled coders will become apparent, and HISE will stand out as an essential piece of software that must always remain available.

That's incredibly wishful thinking.

[Christoph Hart]

@dannytaurus Wishful? Maybe. Essential for not just rolling over and give up? Definitely. So that leaves just one option. I kind of decided to proceed working on HISE and focus on the thing I love which is actual coding - eg. I'm about to manually recode the vast amount of trash code that I vibeslopped into HISE a few months ago (don't worry, just non-critical stuff like the new shadow parser) because looking at it now from a small distance feels like looking at a complete random piece of code which is not the best feeling for my own codebase.

If HISE stops becoming financially viable because of user base regression then at least I've "died doing the thing I loved" instead of code-reviewing AI slop and telling the agent to stop being motivational. I'm still using AI obviously for certain parts but giving away my core dev work loop to a external "brain thingy" is a nope from me.

Local is the future.

I've tried Qwen 3.8 27B on my 3090 when it came out which is considered the pinnacle of local AI that can run on (pricey) consumer hardware and it's completely useless for audio work. It can one shot a website with a Three.js rendered ocean beautifully but it falls apart instantly in our domain. While I second the feeling of independence that a local model gives you, the difference between the AI frontier models and whatever is going on to be runnable on affordable GPUs didn't get any smaller the last year and I don't expect it to magically get to even Luna or Sonnet levels of intelligence any time soon.