W̶h̶e̶r̶e̶'̶s̶ ̶C̶h̶r̶i̶s̶t̶o̶p̶h̶?̶ We found him and now we talk about AI

[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.

[dannytaurus]

@Christoph-Hart said in Where's Christoph?:

at least I've "died doing the thing I loved"

I also fully intend to continue doing what I love, I just won't die doing it. I'll adapt and move on.

@Christoph-Hart said in Where's Christoph?:

which is considered the pinnacle of local AI

And how long ago was it that you, and most others in this forum, said the frontier models were useless for writing code? All it takes is time.

Not only is model quality improving, but speed too. Look at ChatJimmy. It's a model hardcoded into the silicon, bypassing all the bandwidth overhead of moving to/from memory. It responds almost immediately at 15,000 tokens per second. Right now it's a simpler model compared to frontier, but try out how fast it is in conversation: chatjimmy.ai

[dannytaurus]

@Christoph-Hart said in Where's Christoph?:

trash code that I vibeslopped into HISE

Out of interest, what's your definition of 'vibeslopped' here?

[Yinxi]

For me, HISE was the perfect tool for creating my first plugin projects, thanks to David’s tutorials and the help of the community. The DIY satisfaction of building something with one’s own hands along with the actual process of learning and understanding is something I never would have experienced using AI.

Some people may choose not to use AI for various reasons, and HISE will always remain an excellent gateway for those who prefer not to be overwhelmed by that technology.

I think Hise still has a bright future ahead the community might evolve, but I find it really fun to create my own plugins without having to worry about whether I could have done it faster.

The conversation seems to have revolved largely around HISE and AI, while overlooking all the other aspects that make HISE far more interesting for the user than using an LLM.

[David Healey]

@dannytaurus said in Where's Christoph?:

ChatJimmy

Very fast! These are the sort of efficiency improvements that will make AI companies profitable.

[Christoph Hart]

yup that's fast AF but it's a 8B model which is basically useless for anything more than asking basic questions. It would be interesting to know how much that hardsoldered device would cost though if they would sell it.

Out of interest, what's your definition of 'vibeslopped' here?

Well I gave it the task of implementing a HiseScript parser that runs in parallel to the actual compilation (so it doesn't touch any code that runs in a plugin or actually builds up the data model of the scripting engine) to allow better diagnostics - eg. multi-error recovery etc. which is better for a CLI agent. Coming back after months now and looking at the code it's clear that I have to rewrite everything - it implemented the features super shallow as in "what's the least amount of code that I need to add to make this work" with no concept of a architecture or anything.

Could this be a "skill issue" in the sense that I would have to use a better prompt / harness / multi-agent orchestrator, whatever? Maybe, but I find it much more enjoyable working out the code myself.

On the other hand the hise-cli app is fully vibecoded and I haven't looked at the code a single time - it's written in Typescript which I'm not very fluent in anyways. But since it's just a shallow wrapper around the Rest API in HISE, slopping away is perfectly fine for this sub project :)

[dannytaurus]

@Christoph-Hart said in Where's Christoph?:

it's a 8B model which is basically useless for anything more than asking basic questions

Again, time. And at a rate we're still not really used to for technological innovation.

I'm looking back at the technology of my 80s/90s youth the same way I would've then looked back at the Victorians.

[dannytaurus]

@Christoph-Hart said in Where's Christoph?:

Could this be a "skill issue" in the sense that I would have to use a better prompt / harness / multi-agent orchestrator, whatever?

Definitely a "skill issue" but not in an insulting way. Detailed prompts and interview sessions can pin down specs much better than 'shoot and hope' prompts. Not that I'm saying that's what you did.

Also, multi/sub-agent stuff has come on leaps and bounds in the last weeks/months.

Maybe, but I find it much more enjoyable working out the code myself.

I love that people feel this way, and will continue to for a long time. I'm just not one of them.

I would think of myself more of a product person than a developer. Coding is a means to an end for me, not the main enjoyable activity in itself. When coding becomes faster and more accessible I'm all for it. But I salute those who still want to hand write code line by line.

the hise-cli app is fully vibecoded and I haven't looked at the code a single time

Wow, I'm shocked! But also not surprised, given the circumstances.

[David Healey]

@dannytaurus I'm working on a large C++/JUCE app in Claude at the moment. And as the program has grown in complexity I'm starting to see some cracks.

Taken in individual chunks the code is pretty good, but as a whole it's messy. Lots of unnecessary repetition, some huge functions/files that need to be split up, and a general sense of spaghetti code emerging.

Overall it's saved me a ton of time. Literally something like a year of work done in about a week - I'm cheap and using the Pro Plan. I will continue to clean up the code myself, then back and forth with Claude. I find that the more examples I give it by editing its output the more it "learns" what I consider good code. But left to a none-developer I wouldn't expect the final code quality to be acceptable.

There were a few chunks of code that the various agents had repeated (with slight changes) in multiple place. I told Claude to avoid repetition, which it read as "no repetition". I corrected it that repetition can be used where it makes more sense than abstracting the code. Which it read as no abstraction unless there are at least 3 repetitions... this went on for a while. To a human it's instinctive but "teaching" an AI when repetition is the right choice and when it isn't is a funny thing.

[dannytaurus]

@David-Healey said in Where's Christoph?:

I find that the more examples I give it by editing its output the more it "learns" what I consider good code.

100% and a massively important aspect of the whole experience. AI seems like magic but it very much needs our input.

But left to a none-developer I wouldn't expect the final code quality to be acceptable.

Agreed. It believe it still takes a developer-brain to write a good spec and monitor the output.

Your CLAUDE.md files are crucial too. Don't let your model keep too much stuff in memory. Project/session memory is transient and I find it can rot. Hardcode behaviour into your CLAUDE.md files - one per repo and one high-level one in your Claude profile (~/.claude/CLAUDE.md on Mac, you'll know where to find it on Windows). And read/edit those files, don't let Claude be the only one who knows the content.

Regarding your iterations to get it understanding your repeat/don't repeat needs - just imagine describing it to a complete non-developer. Do it like that, by defining a lot context, and it might go better. And like I said above, READ the rules it writes for itself. Any failings are right int here, in plain text that you can change.

Finally, make sure you're using the best model you can. Even if that means you run out of tokens early. Fable is better than Opus for code, and I wouldn't consider ever letting Sonnet or lower models loose on code. Not even tests or docs.

Going from £20/mo Pro to £90/mo Max gives you a huge amount of headroom. Saying that, I've approached my weekly limit on Max several times lately. But there's a setting in your Usage page that occasionally allows you to reset your limit before the end of the week. When the Anthropic gods deign to offer it.

[Lindon]

@dannytaurus @Christoph-Hart @David-Healey

So this is an interesting discussion. I've realised I cant continue with my free Gemini, Chat-GPT and and Claude usage if I want to step away form getting basic Faust script generated. That sorta works with a fair bit of tweaking from me, but I'ts become clear I should start using these things (and get a pro account).

So..... I think it would be a good idea to get some documentation: "How to set up a starting config. in Claude if you want to use it for HISE-based development" sort of thing. I recall there was some stuff mentioned a few months back but Im pretty sure its out of date now...

Im also sure some of our more Claude-for-Hise savvy developers : looking at you Danny.... could just ask Claude to list a useful config. based on their current set up...

Yes I know everyone's aims are different, and every ones coding style is (slightly) different etc. etc. and it will all be out of date by next week.... but offering newbies to the approach (such as myself) a starting point would be good.

OK thats it - lets get back to asking where Christoph is....

[iamlamprey]

It's very bittersweet: on the one hand I love the current technological renaissance we're in, on the other I feel bad about ditching HISE since it's where I first cut my teeth learning to code, and Christoph has obviously put years of his life into it (as well as answering my dumb as shit questions on the forum).

As for the LLM part of the discussion - the harness is 80-90% of the output quality, I "vibe-coded" my own harness (I'm sick of that term at this point) that has my C++ syntax force-loaded as a skill, as well as a working (bot-detection avoiding) web browser and other goodies. I use Deepseek Flash and the combination works as well or better than any standard Claude / Codex setups at 1/100th the price. It also uses grill-with-docs and ponytail liberally, two of the most popular coding skills - in fact my harness doesn't even have "editing" tools, it just writes python files and executes them to modify code, which works WAY better (at least for my setup).

Last thing I'll touch on is the idea of breaking things into reasonable chunks, the more tasks you give the model, the less effort it spends on each (I guess that's where subagents come in but I haven't needed to use them at all yet). A small list or one large feature per prompt / run, and make sure the agent cleans up after itself (diff checks, delete temp scripts etc).

Caveat in case someone thinks I'm stealing their .ch1 files with my "ch1 extractor" - I'm building out an MVP to see if I can convert my existing sample libraries into a synth and I can't be bothered downloading the original sample files lol