Scott H. Hawley
banner
drscotthawley.bsky.social
Scott H. Hawley
@drscotthawley.bsky.social
Mostly: ML for music production workflows.
Professor of Physics & Senior Data Fellow at Belmont University, Nashville TN
Head of Research for Hyperstate Music AI.
Teacher of audio engineers, Opinions my own.
Explainer blog: https://drscotthawley.github.io
Overall, I'd have to say that the LLM approach tends to be faster and works better, because the search is instantaneous and the answer is tailored to my use case. However, we learned more when we did it the old way. ;-)
November 12, 2025 at 6:05 AM
I've heard tell of a blind Nashville session musician who uses them to read lead sheets, but I have no details. (Presumably hands-free beats holding up a phone when you're already holding an instrument).
November 5, 2025 at 2:50 PM
October 31, 2025 at 4:18 PM
haha, This was all "honor system". However, the reason we made the models unconditional was because this week's tutorial is on Guidance! So, this week we used the classifier to impose classifier guidance on the models. I'll release a new blog post on this very soon.
October 24, 2025 at 1:08 AM
At this rate, Trons #10 through Infinity will all be released in 2042! ;-)
October 16, 2025 at 5:18 AM
/monologue
September 30, 2025 at 4:30 PM
Another good excuse to go visit my colleagues in philosophy. "How many examples do you know of where reasoning is presented in the form of an inner dialogue?"
September 30, 2025 at 4:29 PM
I know people throughout the ages have thought they were living in the last days, but still... I find it unfathomable that any future AntiChrist could be any more AntiChrist-y than our current instance.
September 24, 2025 at 2:20 PM
Congratulations! :-)
September 24, 2025 at 1:35 AM