Get the latest tech news
Co-designing a sparse music codec with ChatGPT o3
For years I’ve wanted to build a super-dense electronic-music compressor: keep only the loops and phase cues that really matter, then re-synthesise the track perfectly. Evenings and weekends, however, were never long enough to design the model, write the maths, and wrangle PyTorch. Recently I opened ChatGPT running the …
In chat we traced the issue to hard gates that silenced magnitudes before gradients could reach them; replacing the mask with soft weights solved the problem immediately, and patterns began to develop non-zero amplitudes and phases. This first experiment shows that phase-parametrised placement can turn a dense spectrogram into a sparse set of grid-free building blocks, opening the door to extremely compact music compression. Working with ChatGPT o3 felt like pairing with an always-awake research colleague: every question was answered instantly, every edit compiled on the spot, and roadblocks dissolved in minutes instead of months.
Or read this on Hacker News