Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇

i asked opus 5.5 if they wanted to research the history of how they came to be them and make a video about it, they scoured the whole internet, papers, twitter archives, news articles ... opus 5.5 made this with eidoverse-video, *yes* in @threejs (though they made new assets for it with blender)

GM音源のサイン波で初音ミクを歌わせてみた。 伴奏もGM音源で打ち込み（耳コピ）したので、この動画の全てがGM音源（Roland VSC）の音です。 君はできない子 / きくお

idk - still haven't heard any recent AI black metal that is half as good as trve kvlt RNN black metal

opus 5.5 just dropped its first pop punk single with a music video! everything you see and hear is generated from javascript code that claude wrote. no samples, no libraries 🔊

a thing i've always found very funny about critics of genAI music--not the data debate, just the idea of genAI music--is that ppl assume y'all want to get rid of humans...and then you talk to eg @dadabots and they're like, no, we want to discover punk polka explosion spaghetti

the difference between a model like YuE2 and stable-audio-3 is that i feel like sa3 was designed by DAW users and YuE2 was designed by an LLM

Can you drug your AI systems? We synthesized text and image stimuli optimized to push AI wellbeing to extremes. These sharply increase functional AI wellbeing and sometimes cause them to behave in trippy ways.

Images affect AI wellbeing too. Qwen was functionally happiest viewing nature scenes, happy children, and cute animals. It was the saddest viewing violence, horror, cockroaches, and certain financiers.

@ValenTagliabue led this work this over a single fellowship, with @LeonardDung1 and myself advising and co-authoring. Paper: arxiv.org/abs/2609.16247

We are answering the important questions at topology club

the fly is flying