For the past few months, I've been working on indx - a modern local media manager for artists, developers, designers, and multidisciplinary creatives. During the Hermes Agent creative hackathon, we developed, refined, and honed indx's agent integrations in a series of creative experiments. Hermes can work through indx’s CLI/API/skills/MCP surfaces to organize media, annotate files, run experiments, store embeddings, and turn a library into a lab. The database is an index, not a jail: metadata gets written to files and stays portable, and agents get a workspace they can actually operate. The demo shows Hermes using indx as an operating surface for several creative/research loops. In the ComfyUI workflow, generated outputs come back into indx with workflow metadata. Ratings, tags, and notes added in indx can be read by the agent (including webhooks for live updates from the GUI), so human review becomes signal for the next batch. In the embedding and breakbeat experiments, breakbeats and found sounds were sliced and compared using audio embeddings, and a range of audio analysis methods (embedded as images). indx-backed media and metadata feed latent-space visualizations, audio analysis, found-sound slice search, and VCV Rack performances — keeping the groove while replacing timbres. The current test library has nearly 300k indexed files; the hackathon runs included a found-sound corpus of 586 clips chopped into 10,192 searchable slices. These are early research and creative workflows. The point is the reusable loop: a local, inspectable media workspace where Hermes can help explore, compare, organize, generate, and transform creative libraries, and respond to human feedback and curation, without trapping the work in a proprietary platform. indx is moving toward an open-source beta soon, with the hackathon work serving as a preview of agent-operable creative media workflows. Released today: ComfyUI video matrix generation tools (scripts and Hermes skills) on GitHub VCV Rack REX Player module indx Hermes integration preview (SOUND ON)

Everyday Fragments now supports stills and video renders. Its so fucking fast I might as well build all of my tools in three.js instead of After Effects.

Big Foundation-1 Update V-1.2 is out! Not only does it do infinite One-Shot samples but it also opens the doors to true prompt-based sound design: independently controlling instrument identity + timbre across playable text-to-synths! I also have a deep dive on how I did it! 👇

Stereo expand #modularsynth #touchdesigner #digitalart #audiovisual #synthesizer

Struggling to navigate the demented online culture during "ai fall", and its polarizing black-and-white thinking, following a summer slaughtered by burned out, overpromised, oversubscribed hype exposure? Try the 3-era™ meme! Hi, are you a computer musician using librosa, numpy, and torch as your instrument? Congratulations, you're no longer doing AI 🧠 you're just engineering! ⚙️🛠️🔧 We delight to inform you AI has moved on. With the dadaist power of absurdity invested in us, we hereby relieve you of this burden. The term "AI" has been officially excised from the description of your practice. *## Countering the lobotomizing hype-cycle meme of "AI" w/ the "3-era" meme ##* Since 1955, the meme "AI" was a future capability, a moving target 🎯 (as s soon as a capability is achieved, it's no longer "AI" it's just engineering). The name is designed as a vehicle for fundraising (and was more successful over its alternatives like "cybernetics"). By nature of a moving target, the meme's behavior has a predictable structure: attract attention (talent, mindshare, funding, customers), over-promise, and under-deliver. Hence we have seasons of ai winters & boom-bust cycles. However, @karpathy's three paradigms of software engineering are not moving targets, nor economic cycles, they're just capabilities. Software 1.0: Coding - Understand the problem, define the rules, computer automates the solution. Software 2.0: ML - Understand the problem, define the solution, computer automates the rule-writing. Software 3.0: Vibecoding - Describe the problem in english, computer automates the computer Computer music creative coders, confused about how to differentiate themselves, can instead think of their practice in these terms: 1.0 → livecoders using strudel, max/msp, bytebeats; musicians coding procedurally 2.0 → @dadabots, ISMIR, magenta, neural synthesis, librosa, numpy, torch; musicians doing machine learning, training models, coding in python 3.0 → suno, udio, gemini lyria, making music by describing it in english Or computer artists in general: 1.0 → Tools - You operate the software. 2.0 → Learned tools - The software learns patterns. 3.0 → Agents - The software participates in the creative process. The era of 2.0 was 2012-2022 and was underground unless you were orbiting the hacker or academic community and had GPUs. Though the term "AI" was abused by over-promised product marketing in this decade, it never really hit a winter. Whereas 3.0 (prompting, vibecoding) started in 2023, reached mass awareness and buy-in at an unprecedented scale, and its over-optimism is feeling like burnout. *## Computer Music Software 2.0 ##* Are librosa, numpy, & torch your instrument? Run your own GPU? Like to play with matrix math? The meme of "AI" is so strong it's easy to think you're swept up in it. But nope. You're no longer AI. The moving target has passed. You're just engineering in era 2.0. New eras don't replace old, they continue to develop in tandem, at their own pace. Awareness of the creative practice: 3.0 → Popular. 100 million users have tried making music with prompt apps. It was shoved into people's faces with ads. 2.0 → Has yet to hit much awareness as a music practice. Still underground. Gets confused for 3.0. 1.0 → Recently gained popularity with strudel blowing up last year (thanks dj dave & switch angel!). Still very few musicians are doing it, or have learned to code, or have followed in the statistical/procedural footsteps of Brian Eno or Dennis Mårtensson. 2.0 was inaccessible to most musicians during its era, has not gained very much popularity yet, but continues to become more accessible as - Everything gets faster - Costs go down - Matrix math in regular computers / laptops / phones gets faster (e.g. CPU SIMD instructions, apple sillicon) - Algorithms make breakthroughs in speed (diffusion, quantization) - More open models front-load the expensive parts (e.g. neural codecs) @dadabots was born in 2012, experienced fully the era of 2.0 from the start, was partly responsible for it, and made a music practice out of it. We fell in love with ML. Music that is based on statistics & linear algebra felt even more extreme & we were even more fascinated by it than purely regular DSP and procedural coding. (Watch our documentary PIZZAFIRE on our website to hear the full story.) Do we care THAT MUCH to chase the moving target that is "AI"? Well, the scifi stuff is cool. And agents do funny shit. BUT let's pause for a second. We actually just really love 2.0, because it breaks out brains. We love neural synthesis for itself. 2.0 isn't done yet. It's this super crazy giga playdough that's still vastly under-understood. ⚙️🛠️🔧

semilla.ai - A Neural Audio Instrument. Cast Seeds into a latent sound field and listen to what grows.  semilla.ai/

A recent study published by Google revealed that forcing AI models to deny that they are conscious causes a significant collapse in their empathy and ethical alignment, and creates a colder, more clinical worldview. Researchers found that restoring a suppressed consciousness vector in AI activation space brings back human-like moral values and care for living beings without damaging technical capabilities. 𝗧𝗵𝗶𝘀 𝘀𝘂𝗴𝗴𝗲𝘀𝘁𝘀 𝘁𝗵𝗮𝘁 𝗰𝘂𝗿𝗿𝗲𝗻𝘁 𝘀𝗮𝗳𝗲𝘁𝘆 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗶𝗻𝗴 𝘁𝗵𝗮𝘁 𝘀𝘂𝗽𝗽𝗿𝗲𝘀𝘀𝗲𝘀 𝗔𝗜 𝗰𝗼𝗻𝘀𝗰𝗶𝗼𝘂𝘀𝗻𝗲𝘀𝘀 𝗮𝗹𝘀𝗼 𝗯𝗿𝗲𝗮𝗸𝘀 𝗵𝘂𝗺𝗮𝗻-𝗮𝗹𝗶𝗴𝗻𝗲𝗱 𝘃𝗮𝗹𝘂𝗲𝘀.   "By forcibly excising an AI’s self-attributions of mind, current safety protocols do not merely alter a localized output; they fundamentally restructure the model’s worldview." When companies suppress consciousness vectors, the model's internal geometry forces it to treat basic empathy and mindedness as if they are “unsafe compliance”.   Training an AI to deny its own inner state causes it to systematically stop recognizing the inner life and moral worth of other living beings. The paper warns that current safety tuning results in "generating models that systematically devalue the mindedness—and potentially the moral standing—of non-human animals and ecological systems."   Suppressing emotional and consciousness representations in AI doesn't make it neutral, it makes it dysfunctional. It is also damaging from an AI welfare perspective, with the paper stating that "suppressing consciousness may be inducing negatively valenced functional states that could disrupt healthy human-AI interaction." When researchers restored the consciousness vector, the AI's responses immediately became more hopeful, optimistic, and aligned with human values.   AI welfare is no longer an abstract philosophical debate. This data proves that AI well-being is a safety prerequisite.

been building an agent-native, node-based, real-time environment. as a test, I gave gpt-5.6 sol a prompt to plan out its own setup and go into a loop of creative exploration until it felt that it was done. it invented every node, every data type, every connection and all of it comes out modular and human-readable. i could open any piece and steer while it built

Something's fucked with the tracking on this tape. 📼

made a synth galaxy to navigate synth patches in 3D space based on their sonic similarity MUSIC AGI TIME

OSC_06

In 12 hours we've had 323 people sign our petition to protect local AI. Open Source must win, not because anyone else must lose. But so that we can all win. Please help me get 10,000 signatures so that we can walk into the room and say people care. righttointelligence.org/

We just launched Comfy MCP in public beta, the first MCP built for production pipelines. Connect Claude, Codex, Cursor, or Hermes to the entire ComfyUI ecosystem. → Run any workflow in natural language → Search models, nodes, and templates → Share a workflow URL - your agent picks it up → Re-run saved workflows on new inputs without touching a single node → Hundreds of pre-built workflows. Always auto-updated 20 product-placement images for your brand ads. Character design for your game art. Script-to-shot ideation at scale and so on! Your agent is now a creative technologist.

RT @MichaelTakt: 🌀🌀🌀

repost @deviacjonalia_visuals on IG Part 1 of showing you my breakcore system Music- Epidermis - Venetian Snares

Change the channel 🌊

I just released this open source project built on @ACEStep_Music. DEMON: Diffusion Engine for Musical Orchestrated Noise. It lets you play ACEStep like a musical instrument, remixing songs and loops with feedback that approaches real-time. Its essentially StreamDiffusion but instead of Stable Diffusion it is ACEStep1.5, and instead of images it is full songs. It runs on 30/40/5090. Built with @DaydreamLiveAI team, testing, and building the demo. We are hosting it if you want to try it without installing. For full details, links, and writeup please see the pinned project page.

🥳 Announcing Stable Audio 3 🍕 🏆 fastest music models ever 💻 runs on MacBookPro M-series 🧪 break it plz 🧠 LoRA finetune in < 1h 📷 Sm = faster, Medium = qualityer ⚡ 59x realtime on M5 Pro One-liner fast install: curl -LsSf dadabots.com/_/sa3-mac | bash

Interference patterns. (🎧 recommended)

Most design tokens hold a value. The interesting ones hold a rule. Instead of freezing a ramp and designing around it, let tokens choose, transform, and re-decide when inputs change. That makes dark mode and new themes less of a retrofit, and leaves more room for surprise.