[HN Gopher] Show HN: I used AI to recreate a $4000 piece of audi...
       ___________________________________________________________________
        
       Show HN: I used AI to recreate a $4000 piece of audio hardware as a
       plugin
        
       Hi Hacker News,  This is definitely out of my comfort zone. I've
       never programmed DSP before. But I was able to use Claude code and
       have it help me build this using CMajor.  I just wanted to show you
       guys because I'm super proud of it. It's a 100% faithful recreation
       based off of the schematics, patents, and ROMs that were found
       online.  So please watch the video and tell me what you think
       https://youtu.be/auOlZXI1VxA  The reason why I think this is
       relevant is because I've been a programmer for 25 years and AI
       scares the shit out of me.  I'm not a programmer anymore. I'm
       something else now. I don't know what it is but it's multi-
       disciplinary, and it doesn't involve writing code myself--for
       better or worse!  Thanks!
        
       Author : johnwheeler
       Score  : 126 points
       Date   : 2026-01-03 01:08 UTC (1 days ago)
        
       | gus_massa wrote:
       | Did you recreate the UI only or also the internal circuits? Does
       | it produce a similar distorsion?
        
         | johnwheeler wrote:
         | I created the UI and the internal circuits but it's a hundred
         | percent DSP. The SST206 is a recreation of the SST282 (in DSP)
         | and he expanded the bandwidth from 7 kHz to 22 kHz, so it
         | doesn't produce distortion but it can get dark like the
         | original. But yeah so the SST206 it's not grungy like the
         | original so it lacks some of the character. It makes up for it
         | in delay time.
        
       | tomhow wrote:
       | [under-the-rug stub]
       | 
       | [see https://news.ycombinator.com/item?id=45988611 for
       | explanation]
        
         | ndgold wrote:
         | Instant ROI
        
         | RiverStone wrote:
         | Nicely done!!
        
           | johnwheeler wrote:
           | Thank you!
        
         | BenjaminHas wrote:
         | This is really impressive! I love how you combined AI
         | assistance with schematics, patents, and ROMs to recreate it.
        
           | johnwheeler wrote:
           | Thank you so much. Yeah it's really cool. I also bought
           | myself a copy of Max MSP and I'm recreating it visually so I
           | can tweak all the parameters and really understand what's
           | going on because the AI did all of the theory for me but I
           | have all the numbers. When you tweak the numbers it makes it
           | sound totally different. So yeah I'm excited. This is what I
           | want to do with my life. I want to build electronic music
           | gear. I'm not saying AI is not going to be able to do that
           | one day but I just can't do web programming anymore. I don't
           | know. I've been doing it too long and I just don't like it
           | anymore.
        
             | chunkmonke99 wrote:
             | Wait you used Claude Code to recreate patents and
             | schematics? Are the schematics for this easily available
             | somewhere? Was Claude just able to one-shot this?
        
               | johnwheeler wrote:
               | I use Claude more as a learning tool in this context.
               | It's kind of funny actually got the idea because I heard
               | that in China they're basically replacing teachers with
               | AI, where we're trying to get AI out of our school
               | systems in the United States. So I went into it with that
               | mindset instead of trying to have Claude do the whole
               | thing to teach me how to do it so I understand it and I'm
               | still learning, trying to recreate things with Max so I
               | can have a lot more control and really play with it. I'm
               | learning that reverb creation is a real craft.
               | 
               | It's not able to one-shot it yet but I'm sure that's
               | coming this year sometime. I did the UI a hundred percent
               | by myself and I went in there and tweaked it and tried to
               | rebuild it and just try to understand how reverb works
               | etc. I also did a lot of the software licensing just
               | because I have experience with that.
        
         | deaux wrote:
         | 18 days late, but we needed one of those here:
         | https://news.ycombinator.com/item?id=46290617
        
       | atentaten wrote:
       | Nice! Which DAW are you using in the video?
        
         | bjelkeman-again wrote:
         | Apple Logic
        
         | 6581 wrote:
         | Looks like Logic Pro.
        
       | drcongo wrote:
       | Cmajor, for anyone wondering: https://github.com/cmajor-
       | lang/cmajor
        
         | reactordev wrote:
         | All I've ever known was JUCE. This looks nice!
         | 
         | *edit* well duh, it's the same guy!
        
           | johnwheeler wrote:
           | It's incredible
        
       | LatencyKills wrote:
       | This is fantastic. I'm currently building a combustion engine
       | simulator doing exactly what you did. In fact, I found a number
       | of research papers, had Claude implement the included algorithms,
       | and then incorporated them into the project.
       | 
       | What I have now is similar to
       | https://youtu.be/nXrEX6j-Mws?si=XdPA48jymWcapQ-8 but I haven't
       | implemented a cohesive UI yet.
        
         | johnwheeler wrote:
         | Right on that's awesome! I think I'm doing more what you did
         | vs. the other way around. Looks like you're pretty established.
         | How long did it take to build your YouTube to what it is?
         | What's that process been like?
        
       | franky47 wrote:
       | I used to do that exact job 10 years ago (without AI, obviously).
       | I figure that career would be very different now.
       | 
       | There was something exciting about sleuthing out how those old
       | machines worked: we used a black box approach, sending in test
       | samples, recording the output, and comparing against the digital
       | algorithm's output. Trial and error, slowly building a sense of
       | what sort of filter or harmonics could bend a waveform one way or
       | another.
       | 
       | I feel like some of this is going to be lost to prompting, the
       | same way hand-tool woodworking has been lost to power tools.
        
         | rmnclmnt wrote:
         | I wonder if we could then have released the *stressor in a few
         | months then...
        
           | franky47 wrote:
           | I'd love to see someone try.
           | 
           | Though using AI to build the devtools we used for signal
           | analysis would have been helpful.
        
         | mycall wrote:
         | It will be the future for sure, software as a tool for
         | everyone.
         | 
         | While there is something lost in prompting, people will always
         | seek out first-principles so they can understand what they are
         | commanding and controlling, especially as old machines become
         | new machines with new capabilities not even imaginable before
         | due to the old software complexity wall.
        
           | johnwheeler wrote:
           | It's exactly as you say: software as a tool for everyone and
           | it's hard for programmers like me to accept that because I've
           | spent so much time, read so many books, and work so hard
           | perfecting my craft.
           | 
           | But smart programmers will realize the world doesn't care
           | about any of that at all.
        
             | mycall wrote:
             | We will remain to be programmers but at a higher
             | abstraction where code is just the glue to our means and
             | imagination.
        
               | AstroBen wrote:
               | As a hobby I suppose. There's a very real chance there
               | won't be enough paid work available for that
        
               | Bombthecat wrote:
               | Exactly! There isn't enough woodworking jobs for
               | thousands of thousands of workers. Of course you have
               | people handcrafting things and people demanding
               | handcrafted things. Programming will be the same.
               | 
               | Way way way less developers.
        
               | moregrist wrote:
               | This doesn't seem right to me. Carpentry still seems like
               | a pretty solid line of work with a lot of jobs. I know at
               | least one guy who moved from EE work to contracting
               | because he could make a lot more money that way.
               | 
               | Given, a lot of it is framing houses and remodeling. And
               | there are fewer jobs in hardwood furniture these days.
               | But a lot of that is because US furniture manufacturing
               | was moved to China 20 years ago, not because of power
               | tools.
               | 
               | If anything, the advent of power tools in the 40s/50s
               | made single family homes more affordable and increased
               | construction demand.
        
               | airspresso wrote:
               | You're ignoring Jevons paradox. Everyone, both people and
               | companies, will be making exponentially more software
               | with these tools. Software that both needs to get
               | created, debugged and updated to realize the intention of
               | it. That's what our time will be spent on as programmers.
        
               | AstroBen wrote:
               | Do you have any evidence that the demand for developers
               | is largely price elastic?
               | 
               | People are _already_ struggling to find work from
               | oversupply of talent and not enough demand
        
         | ceva wrote:
         | I think you will like this talk
         | https://youtu.be/XM_q5T7wTpQ?si=Nyb4lZEZjsjCCGBg
        
       | dubeye wrote:
       | awesome, in 2025 I made a few apps for my small business that I
       | have spent hours trawling the web looking for, and I have little
       | coding skills.
       | 
       | Sometimes it feels like I'm living in a different world, reading
       | the scepticism on here about AI.
       | 
       | I'm sure there enterprise cases where it doesn't make sense, but
       | for the your everyday business owner it's amazing what can be
       | done.
       | 
       | maybe it's a failure of imagination but I can't imagine a world
       | where this doesn't impact enterprise in short order
        
         | hatefulheart wrote:
         | With all due respect you _are_ living in a different world. Not
         | in a bad way, it's just you haven't experienced what
         | maintenance on a large complicated code base is like.
        
           | kaffekaka wrote:
           | Different worlds yes, but they both exist.
        
             | hatefulheart wrote:
             | Sure, where one is ignorant of the other. That's not a pro.
        
               | kaffekaka wrote:
               | Small business owners not being aware of maintenance hell
               | in large org codebases, yes, is that a problem?
               | 
               | I work for a large org and maintenance hell is my job, so
               | I see both sides I think.
        
               | hatefulheart wrote:
               | I'm a small business owner and solo developer on that
               | business. Let's just say I'd rather know the costs of my
               | choices upfront. I'm sure there is not one small business
               | owner in tech who would turn their nose up at that.
        
               | dubeye wrote:
               | Good points. Works both ways though, you are splitting
               | your time between two worlds, and don't have a fully
               | clear view on the costs of bad choices on a small
               | business
               | 
               | to know this you need to know what processes these
               | businesses have been using for the past decade to run
               | real full time business with full time staff. for
               | example, you don't know just how bad the prior systems
               | were, that the self built systems replaced.
               | 
               | with all due respect you don't have all the info to make
               | the calculation on my world. just as I don't have it for
               | yours.
               | 
               | the same tool that helped me build our systems, is not
               | going to be the same tool that helps you maintain your
               | large code base. But my point is, that I'm on the front
               | line of change, and my guess is it's not going to be
               | limited to my size of business. I don't know what your
               | tool will look like, but I'd bet it's coming
        
               | kaffekaka wrote:
               | Fair enough, that is a good point.
        
               | cyberge99 wrote:
               | A pro is someone who makes money doing their profession.
        
               | hatefulheart wrote:
               | Pro as in pros and cons, not as in professional.
        
           | HPsquared wrote:
           | I think there will be a transition period.
        
           | mirsadm wrote:
           | The worst part of the new wave of vibe coders is their
           | confidence.
        
         | johnwheeler wrote:
         | No you're absolutely right. One of the things I'm starting to
         | see and I wrote another Hacker News post about this is that
         | more people are starting to come out talking about all the
         | mistakes AI is making even as it gets better. Then You've got
         | people like Karpathy talking about how drastic the landscape is
         | shifting
         | 
         | I've been doing this for 25 years and I can tell you that the
         | AI is a better coder than me, but I know how to use it. I
         | reviewed the code that it puts out and it's better. I'm
         | assuming the developers that are having a hard time with it are
         | just not as experienced with it.
         | 
         | If you think your job is going to stay programmer, I just don't
         | see it. I think you need to start providing value and using
         | coding as just a means to do that, more so than coding being
         | valuable in itself. It's just not as valuable anymore.
        
           | pengaru wrote:
           | > you're absolutely right.
        
       | Blackthorn wrote:
       | How can you say it's a 100% faithful recreation if you've never
       | programmed DSP before?
        
         | steveBK123 wrote:
         | Dude it's AI just trust him
        
           | bigfishrunning wrote:
           | He included "100% faithful" in the prompt!
        
             | steveBK123 wrote:
             | "You are an elite DSP programmer who never makes
             | mistakes.."
        
         | glimshe wrote:
         | Perhaps a subjective evaluation based on how it sounds.
        
           | steveBK123 wrote:
           | It's bold to call it 100% faithful without some rigorous test
           | harness though, isn't it?
        
         | utopiah wrote:
         | Indeed, same questions few days ago when somebody shared a
         | "generated" NES emulator. We have to make this answered when
         | sharing otherwise we can't compare.
        
           | le-mark wrote:
           | At some point the llm ingested a few open source NES
           | emulators and many articles on their architecture. So i
           | question the llm creativity involved with these types
           | examples. Probably also for dsps.
        
             | steveBK123 wrote:
             | Right, the amount of hallucinated response data I see at
             | work using any of these leading models is pretty
             | staggering. So anytime I see one of these "AI created a
             | 100% faithful ___" type posts that does not have detailed
             | testing information, I laugh. Without that, this is v0 and
             | only about 5% of the effort.
        
             | utopiah wrote:
             | > i question the llm creativity involved with these types
             | examples.
             | 
             | Indeed but to be fair I'm not sure anybody claimed much
             | "creativity" only that it worked... but that itself is
             | still problematic. What does it mean to claim it even
             | manage to implement an alternative if we don't have an easy
             | way to verify?
        
           | Xmd5a wrote:
           | I'm not claiming a 100% faithful physical recreation in the
           | strict scientific sense.
           | 
           | If you look at my other comment in this thread, my project is
           | about designing proprioceptive touch sensors (robot skin)
           | using a soft-body simulator largely built with the help of an
           | AI. At this stage, absolute physical accuracy isn't really
           | the point. By design, the system already includes a neural
           | model in the loop (via EIT), so the notion of "accuracy" is
           | ultimately evaluated through that learned representation
           | rather than against raw physical equations alone.
           | 
           | What I need instead is a model that is faithful to my
           | constraints: very cheap, easily accessible materials, with
           | properties that are usually considered undesirable for
           | sensing: instability, high hysteresis, low gauge factor. My
           | bet is that these constraints can be compensated for by a
           | more circular system design, where the geometry of the sensor
           | is optimized to work with them.
           | 
           | Bridging the gap to reality is intentionally simple: 3D-print
           | whatever geometry the simulator converges to, run the same
           | strain/stress tests on the physical samples, and use that
           | data to fine-tune the sensor model.
           | 
           | Since everything is ultimately interpreted through a neural
           | network, some physical imprecision upstream may actually be
           | acceptable, or even beneficial, if it makes the eventual
           | transfer and fine-tuning on real-world data easier.
        
             | utopiah wrote:
             | Well I'm glad you find new ways to progress on whatever you
             | find interesting.
             | 
             | This honestly though does not help me to estimate if what
             | you claim to be is what it is. I'm not necessarily the
             | audience for either project but my point remains :
             | 
             | - when somebody claims to recreate something, regardless of
             | why and how, it helps to understand how close they actually
             | got.
             | 
             | It's not negative criticism by the way. I'm not implying
             | you did not faithfully enough recreate the DSP (or the
             | other person the NES). I'm only saying that for outlookers,
             | people like me who could be potentially interested, who do
             | NOT have a good understanding of the process nor the
             | initial object recreated, it is impossible to evaluate.
        
               | Xmd5a wrote:
               | Oh. just to be clear first, I'm not the OP. Sorry for the
               | confusion.
               | 
               | I do understand your point, and I think it's a fair one:
               | when someone claims to "recreate" something, it really
               | helps readers to know how close the result is to the
               | original, especially for people who don't already
               | understand the domain.
               | 
               | I was mostly reacting to the idea that faithfulness
               | always has to be the primary axis of evaluation. In
               | practice, only a subset of users actually care about 100%
               | fidelity. For example with DSP plugins or NES emulators,
               | many people ultimately judge them by how they sound or
               | feel, especially when the original artifact is aesthetic
               | in nature.
               | 
               | My own case is a bit different, but related. Even though
               | I'm working on a sensor, having a perfectly accurate
               | physical model of the material is secondary to my actual
               | goal. What I'm trying to produce is an end result
               | composed of a printable geometry, a neural model to
               | interpret it, and calibration procedures. The physics
               | simulator is merely a tool, not a claim.
               | 
               | In fact, if I want the design to transfer well from
               | simulation to reality, it probably makes more sense to
               | intentionally train the model across multiple variations
               | of the physics rather than betting everything on a single
               | "accurate" simulator. That way, when confronted with the
               | real world, adaptation becomes easier rather than harder.
               | 
               | So I fully agree that clarity about "how close" matters
               | when that's the claim. I'm just suggesting that in some
               | projects, closeness to the original isn't always the most
               | informative metric.
               | 
               | One reason I find my case illuminating is that it makes
               | the "what metric are we optimizing?" question very
               | explicit.
               | 
               | Sure, I can report proxy metrics (e.g. prediction error
               | between simulated vs measured deformation fields, contact
               | localization error, force/pressure estimation error,
               | sensitivity/resolution, robustness across
               | hysteresis/creep and repeated cycles). Those are useful
               | for debugging.
               | 
               | But the real metric is functional: can this cheap,
               | printable sensor + model enable dexterous manipulation
               | without vision - tasks where humans rely heavily on
               | touch/proprioception, like closing a zipper or handling
               | thin, finicky objects - without needing $500/sq-inch
               | "microscope-like" tactile sensors (GelSight being the
               | canonical example)?
               | 
               | If it gets anywhere close to that capability with
               | commodity materials, then the project is a success, even
               | if no single simulator configuration is "the" ground
               | truth.
               | 
               | What could OP's next move be? Designing and building
               | their own circuit. Likewise, someone who built a NES
               | emulator might eventually try designing their own
               | console. It doesn't feel that far-fetched.
        
               | utopiah wrote:
               | Ah that makes more sense, I couldn't make the connection!
               | 
               | So on "So I fully agree that clarity about "how close"
               | matters when that's the claim. I'm just suggesting that
               | in some projects, closeness to the original isn't always
               | the most informative metric." reminds me of
               | https://en.wikipedia.org/wiki/Goodhart%27s_law
               | 
               | That being said as OP titled " I used AI to recreate X"
               | then I expect I would still argue that the audience has
               | now expectation that whatever OP created, regardless of
               | why and how, should be relatively close to X. If people
               | are expert on X then they can probably figure out quite
               | quickly if it is for them "close enough" but for others
               | it's very hard.
        
               | utopiah wrote:
               | Ah that makes more sense, I couldn't make the connection!
               | 
               | So on "So I fully agree that clarity about "how close"
               | matters when that's the claim. I'm just suggesting that
               | in some projects, closeness to the original isn't always
               | the most informative metric." reminds me of
               | https://en.wikipedia.org/wiki/Goodhart%27s_law
               | 
               | That being said as OP titled " I used AI to recreate X"
               | then I would still argue that the audience has now
               | expectation that whatever OP created, regardless of why
               | and how, should be relatively close to X. If people are
               | expert on X then they can probably figure out quite
               | quickly if it is for them "close enough" but for others
               | it's very hard.
        
         | baq wrote:
         | Maybe the OP has the hardware and can compare the sound both
         | subjectively and objectively? Does it have to be 100% exact
         | copy to be called the same? (Individual electronic components
         | are never the same btw)
        
           | Blackthorn wrote:
           | The OP didn't clarify. But if there's a claim of 100%
           | faithful recreation, I'd expect something to back it up, like
           | time- and frequency-domain comparisons of input and output
           | with different test signals. Or at least _something_. But
           | there isn 't anything.
           | 
           | The video claims: "It utilizes the actual DSP characteristics
           | of the original to bring that specific sound back to life."
           | The author admits they have never programmed DSP. So how are
           | they verifying this claim?
        
             | johnwheeler wrote:
             | Well it's a new project so give it some time. I feel
             | confident that I'm not lying so I can make that claim.
             | 
             | Also its target market is not a technical crowd but people
             | who make music. I'm optimizing more for what they want to
             | see (which are sound demos) rather than what a programmer
             | would want to see.
        
           | _DeadFred_ wrote:
           | That might make it 100% faithful for OPs use cases, but not
           | necessarily anyone else's.
        
         | johnwheeler wrote:
         | I had the hardware for both units and use them extensively so
         | 100% familiar with how they sound.
         | 
         | And I'm not doing it based off of my ears. I know the
         | algorithm, have the exact coefficients, and there was no
         | guesswork except for the potentiometer curves and parts of the
         | room algorithm that I'm still working out, which is a
         | completely separate component of the reverb.
         | 
         | But when I put it up for sale, I'll make sure to go into detail
         | about all that so people who buy it know what they're getting.
        
           | vunderba wrote:
           | Can you sell it, or would you have to do some renaming in
           | order to get around trademark/etc ?
           | 
           | Consider reaching out to Audiority - I know they have some
           | virtual recreations of Space Station hardware.
           | 
           | https://www.audiority.com/shop/space-station-um282
        
             | johnwheeler wrote:
             | Luckily the trademark is public domain!
        
               | psobot wrote:
               | Are the ROMs, though? (Not trying to be combative; I've
               | had to deal with this a lot when developing emulation-
               | based plugins.)
        
           | wrl wrote:
           | Are you also going to go into detail about the use of AI to
           | generate the code?
        
           | indigodaddy wrote:
           | Sell it?
        
             | johnwheeler wrote:
             | Wat?
        
         | gbraad wrote:
         | Standard AI response. Similar to " production-ready",
         | "according to industry standards" or "common practices" to
         | justify and action or indicating it is done, without even
         | compiling or running code, let alone understand the output. An
         | AI can't hear, and even worse, relate this. Ask it to create a
         | diode ladder filter, and it will boost it created a "physically
         | correct analog representation" while output ting clean and pure
         | signals...
        
           | Archit3ch wrote:
           | For context, I'm working on a proper SPICE component-level
           | Diode Ladder.
           | 
           | I tried this for laughs with Gemini 3 Pro. It spit out the
           | same ZDF implementation that is on countless GitHub repos,
           | originating from the 2nd Pirkle FX book (2019).
        
       | KellyCriterion wrote:
       | Great achievement!
       | 
       | Regarding your own titleing: you are now some type of "platform
       | operator/manager" of this agents :-))
        
       | hebejebelus wrote:
       | I was hoping that the video was a walkthrough of your process -
       | do you think you might share that at some point?
       | 
       | > I'm not a programmer anymore. I'm something else now. I don't
       | know what it is but it's multi-disciplinary, and it doesn't
       | involve writing code myself--for better or worse!
       | 
       | Yes, I agree. I think the role of software developer is going to
       | evolve into much more of an administrative, managerial role,
       | dealing more with working with whatever organisation you're in
       | than actually typing code. Honestly I think it probably was
       | always heading in this direction but it's definitely quite a step
       | change. Wrote about it a little incoherently on my blog just this
       | morning: https://redfloatplane.lol/blog/11-2025-the-year-i-didnt-
       | writ...
        
         | askonomm wrote:
         | As someone who works at a place where we do a lot of code
         | analysis and also research AI's effect on code quality, if you
         | do not even so much as look at your code anymore, I do not
         | believe you are creating maintainable, quality software. Maybe
         | you don't need to, or care to, but it's definitely not what's
         | sustainable in long-term product companies.
         | 
         | AI is a force multiplier - it makes bad worse, it _can_ make
         | good better. You need even more engineering disciplines than
         | before to make sure it's the latter and not the former. Even
         | with chaining code quality MCP's and a whole bunch of
         | instructions in AGENTS.md, there's often a need to intervene
         | and course adjust, because AI can either ignore AGENTS.md, or
         | because whatever can pass code quality checks does not always
         | mean the architecture is something that's solid.
         | 
         | That being said, I do agree our job is changing from merely
         | writing code, to more of a managerial title, like you've said.
         | But, there's a new limit - your ability to review the output,
         | and you most definitely should review the output if you care
         | about long-term sustainable, quality software.
        
           | hebejebelus wrote:
           | Yes, I didn't do a great job of managing my language in that
           | post (I blame flu-brain). In the case where _someone_ is
           | going to be reading the code I output, I do review it and act
           | more as the pilot-not-flying rather than as a passenger. For
           | personal code (as opposed to code for a client), which is the
           | majority of stuff that I've written since Opus 4.5 released,
           | that's not been the case.
           | 
           | I'll update the post to reflect the reality, thanks for
           | calling it out.
           | 
           | I completely agree with your comment. I think the ability to
           | review code, architecture, abstractions matters more than the
           | actual writing of the code - in fact this has really always
           | been the case, it's just clearer now that everyone has a
           | lackey to do the typing for them.
        
           | agentifysh wrote:
           | 6 months ago I agreed with your statement
           | 
           | but AI being solely a force multiplier is not accurate, it is
           | a intelligence multiplier. There are significantly better
           | ways now to apply skills and taste with less worry about
           | technical debt. AI coding agents have gotten to the point
           | that it virtually removes ALL effort barrierrs even paying
           | off technical debt.
           | 
           | While it is still important to pay attention to the direction
           | your code is being generated, the old fears and caution we
           | attributed to previous iteration of AI codegen is largely
           | being eroded and this trend will continue to the point where
           | our "specialty" will no longer matter.
           | 
           | I'm already seeing small businesses that laid off their teams
           | and the business owner is generating code themselves. The
           | ability to defend the thinning moat of not only software but
           | virtually all white collar jobs is getting tougher.
        
         | lifetimerubyist wrote:
         | Instead of becoming a people manager you're just a bot manager.
         | Same roles, different underlings.
        
       | utopiah wrote:
       | I'm not in the domain, even though I did dabble with DAW and
       | tinker with a PGB-1 and its open source firmware, but how far
       | would you say CMajor helped? I feel like solely picking the right
       | tool, being framework, paradigm, etc can make or break a project.
       | 
       | Consequently here for me to better understand how special this is
       | I'd appreciate how (especially since I don't see a link to code
       | itself) how does one go to e.g.
       | https://cmajor.dev/docs/GettingStarted#creating-your-first-p...
       | to a working DSP.
        
       | jvanderbot wrote:
       | On your "Scares the shit out of me" comment.
       | 
       | Use AI like a CNC machinist uses a mill. You're still in the
       | loop, but break it into manageable "passes" with testing
       | touchpoints. These touchpoints allow you to understand what's
       | going on. Nothing wrong with letting AI oneshot something, but
       | it's more fun and less ennui to jump in and look around and
       | exercise some control here and there. And, on larger systems,
       | this is basically required. (for now, perhaps).
       | 
       | This is how I do it now: https://jodavaho.io/posts/ai-
       | useage-2025.html
        
         | vardalab wrote:
         | Exactly this! I am a retired EE just messing around with AI in
         | my homelab datacenter and that has been my approach as well.
         | Amazing force multiplier, I can finally create more or less
         | what I want with sw based on first principles and basic systems
         | engineering approaches by just guiding AI. I have used golang
         | and ansible and terraform and typescript, languages I never had
         | time to learn and now I can create a working tools/solutions to
         | whatever is my need at the moment. Other day my STT
         | subscription app became too laggy so I asked Claude to spin up
         | an endpoint on one of my GPU boxes, create a proxy server,
         | intercept transcript cleanup calls and create traces in
         | langfuse, setup a prompt eval framework, etc. We make a plan,
         | iterate on it, I usually get Codex or Gemini in on the call as
         | well and in a couple of hours I have a good enough solutions
         | for my personal needs. This would have been probably a weekend
         | or more project before. Skepticism here does remind me a bit of
         | when I learned how to use handtools for woodworking. Ultimately
         | it was nice to be able to make mortises by hand with chisel but
         | damn if using festool dominoes is not that much more
         | productive.
        
       | Xmd5a wrote:
       | Very nice work. I'm curious: what kinds of projects are you guys
       | currently working on that genuinely push you out of your comfort
       | zone?
       | 
       | I had a small epiphany a couple of weeks ago while thinking about
       | robot skin design: using conductive 3D-printed structures whose
       | electrical properties change under strain, combined with
       | electrical impulses, a handful of electrodes, a machine-learning
       | model to interpret the measurements, and computational design to
       | optimize the printed geometry.
       | 
       | While digging into the literature, I realized that what I was
       | trying to do already has a name: proprioception via electrical
       | impedance tomography. It turns out the field is very active right
       | now.
       | 
       | https://www.cam.ac.uk/stories/robotic-skin
       | 
       | That realization led me to build a Bergstrom-Boyce nonlinear
       | viscoelastic parallel rheological simulator using Taichi. This is
       | far outside my comfort zone. I'm just a regular programmer with
       | no formal background in physics (apart from some past exposure to
       | Newton-Raphson).
       | 
       | Interestingly, my main contribution hasn't been the math. It's
       | been providing basic, common-sense guidance to my LLM. For
       | example, I had to explicitly tell it which parameters were fixed
       | by experimental data and which ones were meant to be inferred. In
       | another case, the agent assumed that all the red curves in the
       | paper I'm working with referred to the same sample, when they
       | actually correspond to different conducting NinjaFlex specimens
       | under strain.
       | 
       | Correcting those kinds of assumptions, rather than fixing
       | equations, was what allowed me to reproduce the results I was
       | seeking. I now have an analytical, physics-grounded model that
       | fits the published data. Mullins effect: modeled. Next up: creep.
       | 
       | We'll see how far this goes. I'll probably never produce anything
       | publishable, patentable, or industrial-grade. But I might end up
       | building a very cheap (and hopefully not that inaccurate),
       | printable proprioceptive sensor, with a structure optimized so it
       | can be interpreted by much smaller neural networks than those
       | used in the Cambridge paper.
       | 
       | If that works, the gesture will have been worth it.
        
         | brcmthrowaway wrote:
         | I would put more effort into algotrading to make $$$ for
         | yourself
        
       | newyankee wrote:
       | A similar approach might actually help build cheap, and decent
       | hearing aids too
        
       | gbraad wrote:
       | Isn't that like the Ursa Major Stargate 323 Reverb? Greybox audio
       | released code for this about a year ago:
       | https://github.com/greyboxaudio/SG-323
        
         | pera wrote:
         | Thanks for mentioning this project, I have been looking for a
         | good reverb plugin for Linux for a while now and this sounds
         | great.
        
           | gbraad wrote:
           | There might be a plugin based on freeverb, which is also a
           | good sounding one. I ohave it as a logue unit, so can't
           | recommend one immediately. At least I know greybox based on
           | actual device comparison, as he owns one and has been doing
           | this for 5 years sans AI.
        
       | agentifysh wrote:
       | We are all glorified QA testers with software architect title
       | now. Sure we set the structure of what we want but everything
       | else the AI does and most of our time is now spent testing and
       | complaining to the AI.
       | 
       | Pretty soon AI will do the QA portion as well. It will generate
       | any piece of software, even games for a cool $200/month from a
       | vendor of choice: Microsoft (OpenAI) or Google
       | 
       | Companies will stop paying for SaaS or complex ERP software, they
       | will just generate their own that only the AI knows how to
       | maintain, run, and add features.
       | 
       | It's ironic that software developers are the most enthusiastic
       | about automating their jobs out of existence. No union, no laws
       | that interfere with free market forces.
        
       ___________________________________________________________________
       (page generated 2026-01-04 23:01 UTC)