Mishearings: compose Dadaist poems with a hallucinating speech-to-text model
What happens when you force a tiny speech recognition model to find patterns in mangled speech?
I'm Evan, an Applied Research Scientist and Software Engineer. My specialty is developing and integrating human-centric AI and ML into user-facing products. In my free time I'm a musician, creative coder, and cyclist. This site hosts a mix of my personal and professional projects. Any views expressed here are my own.
Adding eurorack features to a multitrack tape recorder
A brief write-up of my hardware hacking project to add independent audio outputs and gates to a TASCAM Porta 03 tape recorder.
Using LLMs to control a smart home
Experimenting with GPT models to build a smarter smart home assistant.
Turning sea levels into music with CSV to MIDI
A brief write-up on my csv-to-midi data sonification tool, which I used in a mixed-media art project.
