an agent in every cup
collecting bits & bobs about building alliances with other intelligences
an agent in every cup
txtai
neuml.github.io2025: The New Principles of Prompting
docs.google.com
This write-up is about practical patterns for integrating large language models (LLMs) into systems & products
GitHub - m-bain/whisperX: WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
github.com
Programming is hard — it's hard for beginners to create and understand programs which makes programming as an expressive medium inaccessible. It's hard for experts — even I (the library's maintainer!) had difficulty understanding Fuzzyset, fixing bugs, and adding features. Programming is not just hard, but in my opinion it's needlessly hard,... See more
Fuzzyset
Ultimately, I think programming models and UIs have to change to accomodate human cognition and social processes for dealing with complexity — once it does, programming will be a lot easier for experts and a lot more accessible to beginners. Until then!
GenAI is Our Polyester
culture.ghost.io
People assume that generative AI will lead to a tsunami of garbage content. I think the opposite problem is more interesting: what if you were drowning in amazing content? What if you’re so inspired and overwhelmed by awe that it’s stressful and addicting and life disorienting?
Extending AI chat with Model Context Protocol (and why it matters)
interconnected.org
Malleable software: Restoring user agency in a world of locked-down apps
Geoffrey Littinkandswitch.com