Pilish
An Emacs frontend for the pi coding agent, begun with a wish for a flicker-free interface, separate chat and prompt windows, and conversation-tree navigation. Other contributors and a co-maintainer later joined.
I'm Daniel Nouri, an AI/ML engineer in Malmö. I build machine-learning systems and ways to check their answers. Recent work includes sustainability-document verification, financial-data querying, and an autonomous research loop. My CV has the details.
Whale-call traces morph into a bird. Listen plays a right-whale recording; Look switches to the bird and pauses playback.
Some work worth telling you about,
including the wrong turns.
In 2013 I detected right-whale calls in hydrophone recordings by turning audio into spectrograms and using a convolutional network designed for images. The model did well in Kaggle's whale-detection challenge. Then researchers at Oregon State University supplied much messier continuous recordings.
My shiny model was lousy on them. I had some listening to do. The competition examples had been preselected by another detector, so many confusing sounds were missing from training. I started again with a few hundred examples. I listened to the worst mistakes, labelled them, and fed them back into training. Then I repeated the process. The whale post explains what happened.
PhotoID began because I'm bad at identifying birds and wanted to learn their names. I built the recognition backend and public Twitter bots for birds, butterflies, and wildflowers. Asked to identify a moorhen, it answered mallard. Its second guess was moorhen.
In 2009 and 2010 I volunteered with Python African Tour, working with local organisers and fellow trainers. I co-taught Python and Django in Dakar, Senegal, and led the absolute-beginner group at the African University of Science and Technology in Abuja, Nigeria.
My beginner material wasn't quite beginning at the beginning. I adapted it with Turtle graphics and a Hangman game so learners had something concrete to make and change. The Python 2 tutorial shows how the course introduced functions, loops, and objects. Its examples have not been updated for Python 3.
At 4Catalyzer I worked with doctors and product teams on guidance intended to help non-experts acquire diagnostic-quality ultrasound images. I customized a U-Net and worked on data acquisition and annotation systems.
An Emacs frontend for the pi coding agent, begun with a wish for a flicker-free interface, separate chat and prompt windows, and conversation-tree navigation. Other contributors and a co-maintainer later joined.
Palladium is an open-source framework I co-developed with Otto Group BI colleagues to train and serve predictive models.
A hands-on introduction with faces as training data.
Running this blog’s generator again with Docker.
The interface complaints that started the project.
Here's my CV and PGP public key. For encrypted email, see the Email Self-Defense Guide.