David Braun (dbraun.bsky.social)

So now that AI can do music really well too What remains human is - live performances - authenticity/emotional bond - using AI during live performances (imagine live generating music on the fly) - ultra-famous artists

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale "Autoregressive models—generating content step-by-step like reading a sentence—excel in language but struggle with images. Traditionally, they either depend on costly diffusion models or compress images into discrete, lossy tokens via vector quantization (VQ). NextStep-1 takes a different path: a 14B-parameter autoregressive model that works directly with continuous image tokens, preserving the full richness of visual data. It models sequences of discrete text tokens and continuous image tokens jointly—using a standard LM head for text and a lightweight 157M-parameter flow matching head for visuals. This unified next-token prediction framework is simple, scalable, and capable of producing stunningly detailed image"

Made this simple VR music visualization when testing FFT code in my app. The way it appears in VR is much different, as the start of the "tunnel" is head locked, so it appears that you are creating a psychedelic tunnel (that you can't look away from!) as you move your head.

Meet the new iPad Pro: the thinnest product we’ve ever created, the most advanced display we’ve ever produced, with the incredible power of the M4 chip. Just imagine all the things it’ll be used to create.