administrators group

Christoph Hart

@iamlamprey have you tried the pi agent? It‘s also highly customizable and embeddable - I actually integrated it into hise-cli for fun and hardwired the tool usage to directly call the Rest API of HISE.

Christoph Hart

@dannytaurus nice post buddy! I would add the Pi agent as a viable harness option as I found this to be the most token efficient one - although it might not work with a claude sub as they restrict sub usage to claude code last time I checked (and subsequently cancelled the sub and went over the the street to ChatGPT.

One detail: if you use the hise-cli to edit external files instead of the native edit tool you get a diagnostic back which uses the shadow parser I‘m about to rewrite :) I found that just giving direct feedback for most obvious coding issues saves you from spamming your md files with HISE gotchas.

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 :)

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.

Dominik Mayer

Hey @jimbo

We are currently in a big refactor and refresh of the HISE Activate service.

It's up and running solidly, but in the future will have much better onboarding, Product creation and smooth embedding in your HISE project.

If you want i can send you the current unlocker_demo (which is the scripts + UI that connects the plugin to the Activation server) which still works with the current setup. But if you have a few weeks to spare I think i would wait for this update. (can't promise exact ETA, though ;)

All best
Dominik

Christoph Hart

I‘m in Japan for a theatre production but things calm down on the theatre side next week then I‘ll pick up the work on HISE. Maybe we kick things off with a meetup so I can gather some feedback on what‘s the most requested tasks for me for whoever still uses HISE…

Christoph Hart

@Lindon so can we finally get back to discussing whether Claude was better 1 month ago please?

Christoph Hart

anyways, back to the original problem. I'd say you have two options:

Use a script voice start modulator if all the parameters have a corresponding mod chain (gain, pitch & filter all have that). The logic of selecting the next value from your array can be calculated in the onVoiceStart callback and if the mod target is rendered polyphonically (which is the case for pitch, gain & filter), then everything should be click free as the rendering pipeline is reset before starting the voice.
Make a custom FX with either an extra mod chain, then go back to 1 for other modulation targets.

I wouldn't touch event data here if you get by with scripted voice start.

Christoph Hart

@ustk upcoming as in the base is implemented but there's no real world usage yet which hardens the feature set.

The docs of the current website is nonexistent, but the new website has this covered thoroughly, you can take a sneak peek at the GitHub repo that hosts the new website content:

https://github.com/christoph-hart/hise_api_generator/blob/main/ui_enrichment/pages/components/ScriptDynamicContainer.md

Let me know if you run into problems (which you definitely will as first user)...

Christoph Hart

@ustk multipagedialog is deprecated but dynamic container is the upcoming solution.

administrators

Posts

Member List