ModularGrid uses so-called cookies to ensure it's so-called functionality. We also use dubious tracking scripts. Find out more in the Privacy Policy. We use cookies and wanna let you know.
i just dont understand why 'im not welcome' to post new rack configuration concepts for discussion if some cool new modules come out 6 months from now; what did i even do?
yall are so anti 'bots' that you are keeping regular users from 'interacting normally'.
if im leaving, its because 'yall' are making it not-fun, not because you won on ideas, ... ...
(because you didnt, etcetera.)
...
((sue me for wanting the last word in my own thread. yall have me feeling gaslit.))
Betting my firstborn you'll be back in no time
-- Fruarse
uh, fyi, this is called 'baiting'... and i am leaving forever, as long as yall will stop posting snarky ish after you are pretty sure that im gone already. leave me alone.
If you refer to anything other than your point of view as the "hivemind", and feel like "threatening" to stop using this forum as means to ask for attention... Man, talk about being self absorbed and self entitled.
Your contribution starts and ends at copying questions into LLMs, pasting back the reply and calling it a day. I can do that already on my own, and would rather keep this forum a place to interact with other people, and not vomit-inducing "AI" garbage slop disguised as something genuine.
On a final note, as others already told you, if you want a faster paced forum, go on modwiggler.
-- Fruarse
i just wanted to come on here to discuss some ideas around modular synthesis and designing cases. clearly i am not welcome. leaving forever, for real, this time. 'peace'.
Used to copypaste user questions into Chatbots... Cool
-- Fruarse
if im a bot, then why havent the captchas caught me yet? beep. beep. :|
(edit)
if i really am going to be bothered in every thread i make about not agreeing with 'the hivemind' i really will just stop using this website. all i did was slightly disagree, etc.
maybe yall want a super slow paced forum, and i get that, but in my opinion, all i have been doing is suggesting ways to make this place more noob friendly, etcetera. "peace"
I understand your challenge with the Hemisphere apps. Since you're using Vector LFO and Dual Quantizer, there are some specific considerations for making this patch work properly.
For your application, Vector LFO isn't ideal for feeding into the MMI then into a sample and hold setup. Here's a better approach using your two O_C modules:
For the first O_C:
- Instead of Vector LFO, try using "LOFI" or "Quadraturia" for generating more interesting CV sources
- These will give you more complex modulation to feed into your MMI
For the second O_C:
- Rather than Dual Quantizer, use "ASR" (Analog Shift Register) or the dedicated "Sample and Hold" app in Hemispheres
- Make sure to set up a clock source for the S&H function - you could use the internal clock or patch in an external trigger
The critical issue might be that Dual Quantizer isn't really a true sample and hold - it's designed to quantize incoming CV to musical scales. For proper S&H functionality to trigger Braids, you specifically want one of the sampling apps.
For patching, try:
1. First O_C: LOFI/Quadraturia output → MMI input
2. MMI CV output → Second O_C input
3. Second O_C: ASR/S&H app output → Braids V/Oct and trigger inputs
If you're still having trouble, consider trying the full O_C firmware rather than Hemispheres on one of your modules - the "Piqued" app is excellent for this kind of sample and hold application with extensive trigger options.
Does that help clarify what might be going wrong with your current patch approach?
i was mentioning that i thought the admins should implement ai chat assistance at a fair and democratized price for the site's benefit, so, i plugged this question into Claude 3.7 Sonnet to show off a demo of why i thought this would be a good idea, in general, ... ... ...
Claude:
I'd be happy to help you with your eurorack patching question!
Yes, you can definitely run CV outputs from your Ornament & Crime (O_C) into the Herzlich Labs MMI and then back into the O_C for sample and hold functions to trigger and modulate your Braids. This kind of feedback patching is absolutely possible in a eurorack system.
Here's how you could set this up:
Use one of your O_C outputs to send CV to the MMI inputs
Take the CV output from your MMI (which will now be influenced by your gestural control)
Route that back into an input on your O_C
Configure one of your O_C apps (likely Hemispheres) to use its S&H functionality
Use the resulting modulated output to control parameters on your Braids
Your setup is perfectly capable of this kind of patching. The MMI is designed specifically for these kinds of performance-oriented signal manipulations. Since you have two uO_C modules, you could even use one for generating the initial CV and the other for the S&H processing.
The buffered multiples in your rack will also come in handy here, as you might want to split some of these signals to multiple destinations.
As you mentioned, the ZOIA could accomplish this as well - it's extremely flexible for this kind of signal routing and processing. But using the O_C as you described would work great and give you a more hands-on, hardware-focused approach to the patch.
Is there anything specific about this patch flow you're having trouble with?
...
(and if this model was further fine tuned and continuously retrained on more new and annotated data, pretty soon it would know more than anyone on this forum.)
oops, i just realized i had multipliers and dividers mixed up. ... ... is a 3 5 or 7 ratio multiplier even possible? (i was thinking dividing the intervals between the clock.) can anyone tell me from experience how interchangable clock and gate signals are and any other issues related to trying to do gate sequencing from mostly clock sources? (i think it would be really cool to experiment with 1/7th notes, especially for glitch noise.)
finally, to stay totally within budget, you could consider these three modules, (image wont load right, sorry.) and this case, and have a good amount of room to experiment with and expand with more modules later, and just treat this as the beginning of a journey, as opposed to 'finally' possessing a 'fully complete case' with infinite percussive sequencing options 'built right in'.
another approach you might consider, if money wasnt an issue, you could just try to put together some of the modules that most interest you, that all together would give you the greatest possible ability to explore and experiment with. i tried to put together something like that for you, but including the cost of case it is already 2x over your budget, and im not even sure how to refine this concept fully yet, but this is what i have:
i cannot design your case for you, but good luck.
peace. ✌️
(edit)
oops, the eisei i think its called, i thought was mostly an lfo, because that seemed to be how it was categorized on this site. i was just trying to make a point about choosing the type of modules that make you curious to explore possibilities of everything they offer, as a personal aesthetic choice that i am encouraging o.p. to make for themselves. sorry for not reading the spec sheet on that.
i didnt want to give a single sentence half thought through response, so i did a bit of a deep dive into 'generative'. it seems to me like it can mean anything from random, quasi-random, to procedural, and you have a lot of leeway in defining what it means for you. one option to consider is the moog labyrinth, it is a fully self-contained instrument, falls inside your budget, and gives you everything you need to start playing around with some of the many possibilities of 'generative'. (moog is a quite well respected brand, etc.) another option would be to really think long and hard about what you actually mean by 'generative', design your own custom sequencer in pd (pure data) controlled from a laptop, that you could then use some kind of interface to send cv note data out to a eurorack case, where you use your budget to create your take on a dark ambient voice chain signal path, something i dont know a ton about. i would recommend the strange-r bighat as a starting point for the generative aspect, but it already eats up into too much of your budget, all by itself. maybe check out the channel "not_a_creative" on youtube for some inspiration. unfortunately, i was not able to just design the perfect thing for you.
sorry. peace.
(edit)
{im not the right guy to ask about staying inside a budget. i tend to design stuff that ends up looking like this, etc.: ... ... ... ... ... }
id like to resolve any tensions between me and this website. i have been trying for a certain type of concept, and this is the closest it has ever been to being complete, by adding some modules that 'just released'. the top row is everything i absolutely need, and the second row is almost exclusively for modulation sources. you are free to have differences of opinion on the second row, but the first row is things i really think belong in this design, so only comment on the first row if i truly miscalculated and something wont work the way i think it will. "peace offering".
so, can you imagine jamming out on this etc?
if yall dont like it i really will just leave. ✌️✌️
just, in case anybody didnt get my point, about what i actually want to have fully resolved here at the end of this thread, is:
I am saying, if we went back to the days where 'computer' was a name of a human job, it might take one human and one room to emulate what one 'parameter' does, and; we are about to have trillions of parameters so that the argument that: 'LLMs can never understand nuance, because a room could never understand nuance' does not hold, because this "room" would be way effing bigger than it even makes sense to think about, and it basically would not even be a room at that point. Sorry for the derail.
Peace. Out.
🧐
(edit)
sorry i got un-laid-back just there. i have a long standing slightly different perspective than that of 'chalmers'. got triggered. etc....
i just wanted to have substantive dialogue about design and it felt like i was getting a bunch of one-line quips; guilty: i was not intending to immediately build the case designs i first posted. guilty: i was trying to have fun, and maybe not take this forum seriously enough as a serious place. guilty: i could have not let not-what-im-looking-for advice get to me, as much, when this is just an enthusiast forum. but, i swear, you had equally ample opportunity to just drop this, as well. peace, ... ... ... ... ... ... out, ... ... ... ... ... ...
If you look back at your old posts, you can see pretty easily where it derailed. You can actually go to your profile and look back at all of them.
-- Zacksname
all i see is, me saying: "nah, @Zacksname, that specific feedback is not exactly what i had in mind." then, you grilling me endlessly about my 'life purpose' etc. look for yourself.
Get into a totally pointless argument with @Zacksname.
Harass The Admins about features that don't work perfectly for 'me'.
...
I came on here, to:
"Have a 'fun' dialogue about design and modular synthesis, as a eurorack noob."
...
Honestly, ... i cant even remember the place where exactly this all derailed, like it is. I am fully intending to 'leave forever' unless any 1 has a post about my 'thought-experiment'.
@Zacksname I thought, you might have gotten the impression that i thought you were a fraud, and refused to listen to anything you would say, but, in reality, I just had certain design criteria that your advice was not factoring in, and i still feel a 'pay for tokens' automated configuration design assistant would be good for 'modulargrid', because i remain convinced that it would have offered an experience that just one dedicated enthusiast could not provide for possibly a few many users who might find this website fleetingly on a whim, but who would still desire to 'fully demo' the case creation features of this website. Etcetera.
peace
(edit)
yous guiz own the data. everyone is saying data is the new gold. why dont yall mine your own gold and offer an ai service that charges whats ethical. im talking business.
(hi zacksname. i dont hate you. i dont even know where you got that idea from, etc. ...)
again, i felt this deserved its own full post.
The thought experiment goes: "Let's say, a big tech corporation discovered new mind-amplification technology, and they 'decided' to automate the process of using this to their own advantage using the tech-pipeline that they already control, and that this could be made analogous to how some ad placement procedures already function; how would we, as a whole society, get to influence how this 'automated-xavier' uses 'these abilities' that the big tech players dont want you to know they have, or exist?" It is 'brand new work'.
I did not come on to ""modulargrid.net"" to discuss specifically this, but do comment if you think you can share any constructive criticism. I doubt i can convince @Fruarse .
One is a thought experiment. It deals with imaginary, impossible to replicate scenarios, and it serves to prove a point of view by means of articulating an argument. Also, who says you couldn't build a real world chinese room scenario? But that's not the point.
-- Fruarse
It is the point, because what i am saying, is that the way that what i have described as 'working' AI models are programmed, is in a way loosely inspired, not identical, and with some extra math and computer science thrown in, by physical human neurons, and if you wanted to somehow turn 'that', what is already being built, into some kind of manual card filing system, there would literally not even be enough "rooms" on earth to implement anything close to it.
I do not think this forum should just replace zacksname with an LLM. I am saying it is my opinion that with how my experience with specifically Claude 3.7 Sonnet has gone, that I think that there is reasonable opportunity for 'this forum' to benefit from something like that being integrated, "if the admins even want to".
Sorry, but I more believe in the "Automated Professor Xavier's Psychic Helmet" thought experiment, which puts forward that the infotech sphere might be already creating more psychic amplification type effects than it even realizes, and from this point of view, in fact, the most urgent point of order is actually to 'train the algorithm' that we all already live with, to behave more like that character, Professor Xavier, would. It is my own work. I did not intend to derail my own thread, but "it's an issue, I work on". Etc. ...
(I know an LLM is not a human, but i value helpful knowledge, and AIs are improving.)
P E A C E .
(edit)
im sorry if anyone felt disrespected... i just had an idea about how to use this forum to discuss general design, related to ideas in my head, but i guess yalls mods are just too wiggled to put up with that kind of nonsense
...
peace 💐
((edit edit))
the 'point' of 'my' thought experiment is: "its not a question whether or not the algorithm is like a human or not and in what ways, the question is... knowing that billions of 'action type decisions' are already being transacted autonomously every minute, ... how can we coax what-we-already-have to behave, at the very least, as ethically as the leader of 'the x-men'." you can respond to 'that' if you want, @Fuarse , if that even is your real name. ...
One more point i feel deserves its own whole post:
You cannot actually build a "room" that operates in that way described. Frontier AI is actually more designed in a way similar to the structure of 'human neurons'. That is why the most leading figures in the field are all 'neuroscientists'. The whole premise is flawed, in my view. Like: "If you had to build a cpu out of scuba tank regulators, then it would be too big to even think about, there fore, there is no relationship between 'regulators' and 'transistors'." (there is.)
Like, the way LLMs are typically built to be implemented on a CPU, you would need a whole "room" just to calculate one neuron.
(I, somewhat publicly, have a slightly different view than "Chalmers". I dont want to get into a big 'what is consciousness' debate here on 'modulargrid', but the point I am trying to make is: hey, got good results with Claude, maybe, if 'yall' no-code add it to your site, you could drive "premium subs".)
OK, I guess 'all' the leading figures aren't neuroscientists, but Nobel Prize winner Demis Hassabis is, and, so are quite a few other people on the former 'Google Brain' team. If you want to nit-pick, there are also a lot of pure mathematicians and computer scientists in the frey, but, fundamentally I just don't buy that correctly automating some knowledge work is never a good idea even though at this point the technology has almost completely proved itself. Etcetera.
im just saying, i did the experiment. claude gave me the kind of feedback i was looking for. zacksname came off as hostile to me. i have a diagnosis. (much different than your clocks and flooding analogy, and with fine tuning on 'the data yall could scrape from yourself', the output could keep getting better and better, almost automatically.) im not saying the whole website is broken. im sharing my opinion of how it could be made better. if the admins had any inclination to do this in the first place, then all i did was share a helpful link. "im helping". peace out.
(edit)
i get it. ... MLOps is not free, but, maybe with Calude 3.75 it will be 'almost' free. peace out.
((edit edit))
and yes, it is, of course, a completely fair point that i can just separately use claude in the claude app, but im saying the experience would be more seamless, and available to the average user, if the admins leveraged their own data, and offered some kind of built in chatbot service, requiring minimum total oversight, that might even, perhaps, prove to be a driver of 'upgrades to pro'. im not a moron who thinks you should replace all toaster ovens with an llm. im sharing my feedback in regards to user experience. ...
(((peace out. ✌️)))
final edit:
(i didnt mean to offend anyone. im just a modular noob trying to use a forum. 🤖 )
yikes. arguments on the internet. something i try to avoid. all fair points, but like, Claude 3.7 does 'work', regardless of how 'identical it is' to human grey matter, and there is a philosophy called the patternist perspective that makes this whole argument irrelevant. i am not going to aim suborbital ion cannons at the admins until they listen to all my suggestions, im just pointing out that with all the push toward democratizing advanced ai technologies, all of these things are becoming more and more affordable, with more and more of the tasks, such as verifying that patch points detected by algorithms in the image data are true patch points, ... are becoming things you 'can' delegate to the now becoming increasingly more inexpensive reasoning models.
i dont like getting into big arguments on the internet, i just wanted to share my opinion.
and yes, i did just take the longer-than-you-might-think amount of time to program in a patch configuration on this site, using an android device, and it 'was not fun'. there were a lot of 'bugs' as in 'things that bugged me' and, i know that has more to do about the built in android gesture detection logic, and is not 'the fault of the admins', but im claiming that an ai overhaul would be an all round more enjoyable experience, at least on this device. am i wrong? peace out. ✌️
hey, thats my design. the interface was fighting me in extreme ways on this android device, but i sketched up a quick patch to show you more what i was thinking, in therms of the mixing already being well sufficient. the kermit was intended as a sample and hold, and i just like the general concept of trying to use a clocky for drum sequencing, even if maybe i am still not completely sure the best way to do that. right now i am thinking stackable cables where signal is doubled to the mandala.
I just want to design cool stuff, and talk about design, and enjoy a little community, related to modular synthesis, in a low pressure environment, like I'm pretty sure I have told you at least twice, already. Yes, i have aspirations of mod wiggling my own rig. No, i do not have any immediate actionable plans towards that. The "Wumpus" module idea i shared in a previous thread, that could even toggle between ar and lfo, was something i had already previously built myself in pd. Why are you so hostile to me posting that sort of thing? Why, after posting: "Hey, do yall think this is a cool case or not?" did i get the impression of: "Naw. Get money and build something or your not worth our time." ??? Instead, that all could have been a fun AI experience using a built in chat interface. You probably havent even tried Claude 3.7 Sonnet, have you "zack" ? Try it out. There is an android app. You get about 5 free queries a day. Anthropic behaves ethically. Etcetera.
I do not use the internet to start arguments, @zacksname . I just had an idea about mod wiggling four melodic voices sequenced by a brainstep, and yall basically told me to go back to kindergarten and made fun of me for not having $6,000. What if four melodic voices is what a brainstep craves """zack""".
I would have, if i was ready to start planning a case, but it is a detail that i was confused about, that you missed an opportunity to help clarify for me, that if there was an on site bot that I could dialogue with, that i asked for help putting things together, could have just resolved this in the natural flow of things. I came on here as a noob wanting to bounce around ideas about design concepts and was treated with hostility. AI would have had emotional sensitivity training. What the eff makes you still think that there is zero chance I will ever become a modular performer @zacksname , its just disrespect.
(I did google it. Google actually did give me the right answer as the first result, which i wasnt expecting, because tbh i barely trust Google anymore, but, Fair Point. Etcetera.)
It's just, wouldnt it be nice if The Admins could train a chatbot on that data, and i could get an answer without having to bother the forum? I don't think im wrong about that. Of course, i would do a little more research before entering my card details, but what i really intended was to come on here to start a meta dialogue about instrument design. I don't understand why @zacksname needs to 'come at me' for that.
I stated that I was confused about, when buying a case, if cases typically do come bundled with all the power components and a supply that connects from the outside of the case, or if its more typical to always need a spot on your rack for a dedicated power module, and you 'ignored' this 'misunderstanding' and 'i still dont have an answer'.
I don't want to sound angry, zack, but you basically literally told me you didnt think that I was welcome here in earlier thread.
What kind of "little misunderstandings" do you think AI could improve?
-- Zacksname
For instance @wishbonebrewery suggested a starting case that had a power module. You never cleared up my post stating confusion about this. A fine tuned frontier model could clear this up in 0.3 seconds.
You are entitled to your opinion @Fruarse , but can you not agree that if ai at least detected patch points on the module graphics, you could implement an interface that would create a much more seamless experience in posting patch configurations? I fundamentally disagree with the Chinese Room theoretical premise. I personally believe it is not even possible to create such a room without somehow also in some sense copying the relevant structure from a human brain, thereby implying that 'the room understands Chinese'. I dont want to get into a philosophical debate about AI. I just think a certain usefulness threshold has been crossed, and would personally rather get an instant reply from Claude 3.7, than a reply 2 days later, from, say, @zacksname . If perhaps only the Haiku model was used, all accounts were limited to one use per day or week, and the right kind of data sharing toward mutual advancement deal could be struck, this could likely be implemented nearly free with very little impact. Etcetera.
I do not think it is possible to convince everyone to love our new AI overlords.
(Also, the gap width indicators are broken, because everything is not treated enough lile a state-machine.)
Peace. "✌️";
(edit)
I just think the whole community would be improved if little misunderstanding could be cleared up by AI, and the forum could be reserved for all the more "human" parts.
Sorry I made an 'AI overlords' joke. Don't come at me modulargrid. Kidding. Peace.
(((edit edit edit)))
Yeah, ok. Maybe im just a bit frustrated. If you want to just ignore all my threads etc. then thats perfectly within your own free choice. I did not 'mean' to offend. Peace. ...
hey @zacksname , it is bothering me that you are giving me a hard time about not owning any modules and having no exact plans to pick up any new modules in the immediate future. i spend a good deal of time researching models. i have a beyond novice understanding of synthesis. i follow a lot of eurorack creators. why do you think i dont deserve to interact with 'this' forum community? if collecting modules is the ultimate pursuit of modular synthesis, zack, then, please, for us, list out every eurorack module that you actually own, so we can all see how seriously you take eurorack. etc. ...
(you think youre freaking bob moog zacksname but you aint. 'reference'.)
I, personally, feel this site is due for a total overhaul. I dont think it would be anywhere near impossible to gather enough data to fine tune a frontier model, like Claude 3.7 Sonnet, to perform the task of answering modular questions, giving feedback and advice on in progress case designs, and detecting where patch points are in your image database to greatly simplify the patch diagram creation process, etcetera.
nothing wrong with that rack configuration, but im trying to do my own thing. yeah, i wasnt sure if power needed to be its own module or if most cases took care of that from the back. ai is getting pretty advanced right now, and i still wish the admins would consider fine tuning claude 3.7 sonnet to be a total advice and feedback ai chat feature to provide the kinds of hints i was seeking. ...
yeah, but im leaving forever, tho. i will most likely never pick up any eurorack modules.
im used to more active forums. modwiggler doesnt seem like exactly my thing. last post.
im leaving forever. i cant seem to get enough respect about wanting to share my case layout ideas on here. etcetera. ...
yall should check out 'muezig' on youtube, though. he posts new live content regularly, and it really embodies the 'concept' of a unique sound and all-in-one ness that i was looking for yalls feedback on. he could use the engagement. etcetera. ...
@zacksname i just told you the modules i would get first. i cannot afford them. i just want to post ideas for rack configurations on here as creative stimulation. get a life.
yes. im all set up with "arrangements" on a daily, very limited budget, and i spent $30 of my own money on a yoyo from amazon. in fact, that $30 one is almost my fav right now.
why? what of it?
i "cant" save up on my daily spending for a $6,000 eurorack case, etc. so, why ask? etc.
i spent $120 on a yoyo. (it was a gift actually.) a yoyo made of solid titanium can be $500. the $120 was a yoyofriends tachyon, but mostly i use another $80 yoyofriends, a $30 almost no brand amazon thing that plays above its price, and a few cheaper plastic ones so i dont forget how to play on the cheaper ones.
i could ask some person on here; "you spend $36,000 on eurorack modules?" etcetera. ... ...
yoyo is super rewarding. more people should get into it. etcetera. etcetera. ...
i do. notice how my designs kept making more and more sense after every time i came back over every couple of months, but i have very specific constraints im trying to work inside of, and so, due to issues with things like module availability, yes, my designs could use some improvement.
i still think if this site was a little different then the community here can grow more.
